CN109740020A - Data processing method, device, storage medium and processor - Google Patents
Data processing method, device, storage medium and processor Download PDFInfo
- Publication number
- CN109740020A CN109740020A CN201811604135.3A CN201811604135A CN109740020A CN 109740020 A CN109740020 A CN 109740020A CN 201811604135 A CN201811604135 A CN 201811604135A CN 109740020 A CN109740020 A CN 109740020A
- Authority
- CN
- China
- Prior art keywords
- target
- time
- voice
- service
- acquisition module
- 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.)
- Pending
Links
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of data processing method, device, storage medium and processors.This method comprises: obtaining target video data, wherein target video data is shot to obtain by image capture module to the service behavior of target object in the target time period；Obtain target audio data, wherein target audio data are recorded to obtain by voice acquisition module to the service voice of target object in the target time period；Multiple object times are determined from target time section, and the target audio data in the target video data and each object time on each object time are handled, obtain target process outcome, wherein target process outcome is used to indicate the service quality of target object in the target time period.Through the invention, the technical effect handled comprehensively data has been reached.
Description
Technical field
The present invention relates to data processing field, in particular to a kind of data processing method, device, storage medium and
Processor.
Background technique
Currently, needing the Service Quality to target objects such as waiter, sales promotion persons in service trade, sale property industry
Amount is determined.Usually only by monitor video, sound pick-up outfit, the method manually spot-check obtain data and to data at
Reason, to determine the service quality of target object.
Although the above method may be implemented to be determined the service quality of target object, but monitor video can not be recorded
To the sound interacted between target object and service object；Sound pick-up outfit can not also be recorded whole usually without camera
The situation of a coverage can not also detect voice in addition, waiter does not go to interact with customer；Artificial selective examination can not be covered
Cover all places, all time.Thus, it is not comprehensive to data processing, cause to determine not the service quality of target object
Comprehensively.
For carrying out handling incomplete problem in the prior art to data, currently no effective solution has been proposed.
Summary of the invention
The main purpose of the present invention is to provide a kind of data processing method, device, storage medium and processors, at least
Solution carries out data to handle incomplete technical problem.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of data processing method.This method packet
Include: obtaining target video data, wherein target video data by image capture module to target object in the target time period
Service behavior is shot to obtain；Obtain target audio data, wherein target audio data are by voice acquisition module to target pair
As service voice in the target time period is recorded to obtain；Multiple object times are determined from target time section, and to every
The target audio data in target video data and each object time on a object time are handled, and target processing is obtained
As a result, wherein target process outcome is used to indicate the service quality of target object in the target time period.
Optionally, to the target audio data in the target video data and each object time on each object time into
Row processing, obtaining target process outcome includes: to handle the target video data on each object time, obtains each mesh
The first processing result engraved when mark, wherein the first processing result on each object time is used to indicate target object every
The service behavior quality of service behavior on a object time；Target audio data on each object time are handled,
Obtain the second processing result on each object time, wherein the second processing result on each object time is used to indicate mesh
Mark the service voice quality of service voice of the object on each object time；Pass through the first processing knot on each object time
Second processing result on fruit and each object time determines target process outcome.
Optionally, the target video data on each object time is handled, obtains on each object time
One processing result includes: by the mesh on service behavior and object time indicated by the target video data on each object time
Mark behavior is compared, and obtains the first comparison result, and the first comparison result is determined as the first processing result；To each target
When the target audio data that engrave handled, obtaining the second processing result on each object time includes: by each target
When the target audio data that engrave indicated by target voice on service voice and object time be compared, obtain the second ratio
Compared with as a result, and the second comparison result is determined as second processing result.
Optionally, pass through the second processing result in the first processing result and each object time on each object time
Determine that target process outcome includes: to convert the first value for the first comparison result, and convert second value for the second comparison result；
By the first value and second value sum of the two, it is determined as target process outcome.
Optionally, target video data is obtained, and before acquisition target audio data, this method further include: adopt to image
The local zone time of the local zone time and voice acquisition module that collect module synchronizes, wherein the local zone time of image capture module
For when being shot by service behavior of the image capture module to target object, instruction service behavior occurred when
Between, the local zone time of voice acquisition module by service voice of the voice acquisition module to target object for recording
When, indicate the time that service voice is occurred.
Optionally, the local zone time of the local zone time of image capture module and voice acquisition module is synchronized and includes:
The local zone time of image capture module and the local zone time of voice acquisition module are synchronized by time server.
Optionally, the local zone time of the local zone time of image capture module and voice acquisition module is synchronized and includes:
Timing synchronizes the local zone time of image capture module and the local zone time of voice acquisition module.
Optionally, image capture module and voice acquisition module are disposed on the target device, the sheet of image capture module
The local zone time of ground time and voice acquisition module is the local zone time of target device, and the local zone time of image capture module is used
In when being shot by service behavior of the image capture module to target object, the time that instruction service behavior is occurred,
The local zone time of voice acquisition module is used for when being recorded by service voice of the voice acquisition module to target object, is referred to
Show the time that service voice is occurred.
To achieve the goals above, according to another aspect of the present invention, a kind of data processing equipment is additionally provided.The device
It include: first acquisition unit, for obtaining target video data, wherein target video data is by image capture module to target
The service behavior of object in the target time period is shot to obtain；Second acquisition unit, for obtaining target audio data,
In, target audio data are recorded to obtain by voice acquisition module to the service voice of target object in the target time period；
Processing unit, for determining multiple object times from target time section, and to the target video data on each object time
It is handled with the target audio data on each object time, obtains target process outcome, wherein target process outcome is used for
Indicate the service quality of target object in the target time period.
To achieve the goals above, according to another aspect of the present invention, a kind of storage medium is additionally provided.The storage medium
Program including storage, wherein at the data that equipment where control storage medium executes the embodiment of the present invention in program operation
Reason method.
To achieve the goals above, according to another aspect of the present invention, a kind of processor is additionally provided.The processor is used for
Run program, wherein the data processing method of the embodiment of the present invention is executed when program is run.
Through the invention, target video data is obtained, wherein target video data is by image capture module to target object
Service behavior in the target time period is shot to obtain；Obtain target audio data, wherein target audio data are by voice
Acquisition module is recorded to obtain to the service voice of target object in the target time period；Determination is multiple from target time section
Object time, and to the target audio data in the target video data and each object time on each object time at
Reason, obtains target process outcome, wherein target process outcome is used to indicate the Service Quality of target object in the target time period
Amount.That is, on same object time video data and audio data handle, reached comprehensive to target object
The purpose that is determined of service quality, avoid by manually spot-check, according only to monitor video content, according only to audio content
It determines the service quality of object, has reached the technical effect handled comprehensively data, solve and data are handled
Incomplete technical problem.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow chart of data processing method according to an embodiment of the present invention；
Fig. 2 is that a kind of pair of data according to an embodiment of the present invention are handled with the service quality progress to target object really
Fixed schematic diagram；And
Fig. 3 is a kind of schematic diagram of data processing equipment according to an embodiment of the present invention.
Specific embodiment
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
Embodiment 1
The embodiment of the invention provides a kind of data processing methods.
Fig. 1 is a kind of flow chart of data processing method according to an embodiment of the present invention.As shown in Figure 1, this method includes
Following steps:
Step S102 obtains target video data, wherein target video data exists to target object by image capture module
Service behavior in target time section is shot to obtain.
In the technical solution that the application above-mentioned steps S102 is provided, image capture module can be video monitoring equipment,
For being shot to the service behavior of target object in the target time period, can dispose in the target area, the target area
Domain is region of the target object where when servicing client, that is, being coverage, wherein target object can be
Waiter, sales promotion person etc. need the object being determined to its service quality, and target time section is the clothes needed to target object
The period that business behavior is assessed.
The target video data of the embodiment is used to indicate the service behavior of target object in the target time period, Ke Yiyong
In generating video pictures to indicate the service behavior of target object in the target time period, the service behavior can be target object
The behavior shown by limbs, for example, the behaviors such as nod, shake hands.Optionally, when which carries
Between information, the temporal information be time of the image capture module when being shot to obtain target video data to target object,
It can serve to indicate that the time that the service behavior of target object occurs, be objective time.
Optionally, after obtaining target video data, target video data and corresponding temporal information are saved.
Step S104 obtains target audio data, wherein target audio data exist to target object by voice acquisition module
Service voice in target time section is recorded to obtain.
In the technical solution that the application above-mentioned steps S104 is provided, voice acquisition module can be sound pick-up outfit, be used for
The service voice of target object in the target time period is recorded, target audio data are obtained, which is
The audio data generated when target object is exchanged by voice with client can serve to indicate that target object in the object time
Service voice in section, for example, the voices such as " you are good ", " welcome ".Optionally, which carries having time letter
Breath, the temporal information are that voice acquisition module is recorded to obtain mesh to the service voice of target object in the target time period
Time when audio data is marked, can serve to indicate that the time that the service voice of target object generates, is objective time.That is,
The target video data and target audio data temporal information having the same of the embodiment.
Optionally, after obtaining target audio data, target audio data and corresponding temporal information are saved.
Step S106 determines multiple object times from target time section, and to the target video on each object time
Target audio data in data and each object time are handled, and obtain target process outcome, wherein target process outcome
It is used to indicate the service quality of target object in the target time period.
In the technical solution that the application above-mentioned steps S106 is provided, target video data and target audio data are being obtained
Later, target video data and target audio data can be analyzed respectively, obtains target object within the object time
The information of service behavior quality and the information of service voice quality.
The object time of the embodiment can be the time point assessed the service quality of target object, for record
Objective time handles the target video data on each object time, can be by video information analysis module to every
Service behavior indicated by target video data on a object time is analyzed, and the information of service behavior quality is obtained.It should
Embodiment is associated target video data and target speech data by object time, on same each object time
Target audio data handled, can be by audio information analysis module to the target audio data on each object time
Indicated service voice is analyzed, that is, to same with service behavior indicated by the target video data on object time
The service voice of Shi Fasheng is analyzed, to obtain the information of service voice quality.
The embodiment using the information of service behavior quality and service voice quality information be used as to target video data with
The target process outcome that target audio data are handled, so that comprehensive determine the clothes of target object in the target time period
Quality of being engaged in realizes the mesh evaluated the service quality of target object that is, determining the service quality on duty of target object
's.
S102 to step S106 through the above steps obtains target video data, wherein target video data is adopted by image
Collection module is shot to obtain to the service behavior of target object in the target time period；Obtain target audio data, wherein mesh
Mark audio data is recorded to obtain by voice acquisition module to the service voice of target object in the target time period；From target
Multiple object times are determined in period, and to the mesh in the target video data and each object time on each object time
Mark audio data is handled, and obtains target process outcome, wherein target process outcome is used to indicate target object in target
Between service quality in section.That is, on same object time video data and audio data handle, reach
The comprehensive purpose that the service quality of target object is determined, avoid by manually spot-check, according only to monitor video content,
The service quality that object is determined according only to audio content has reached the technical effect handled comprehensively data, has solved
Data are carried out to handle incomplete technical problem.
As an alternative embodiment, step S106, to the target video data on each object time and each
Target audio data on object time are handled, and obtaining target process outcome includes: to the target on each object time
Video data is handled, and the first processing result on each object time is obtained, wherein on each object time first at
Reason result is used to indicate the service behavior quality of service behavior of the target object on each object time；To each object time
On target audio data handled, obtain the second processing result on each object time, wherein on each object time
Second processing result be used to indicate the service voice quality of service voice of the target object on each object time；By every
The second processing result in the first processing result and each object time on a object time determines target process outcome.
In this embodiment, to the target sound in the target video data and each object time on each object time
It, can be respectively to the target in the target video data and each object time on each object time when frequency is according to being handled
Audio data is handled.Optionally, the target video data on each object time is handled, it can be from each target
When the target video data video pictures generated that engrave in determine the practical service behavior executed of target object, to actually holding
Capable service behavior is assessed, for example, judging whether the service behavior meets specification, or judges that the service behavior meets rule
The service behavior is met specification, does not meet specification, meets the degree of specification as the first processing result by the degree of model, thus
Determine the service behavior quality of service behavior of the target object on each object time.
Optionally, the target audio data on each object time are handled, it can be from each object time
The service voice that target object is actually sent out is determined in target audio data voice generated, to the service voice being actually sent out
It is assessed, for example, judging whether the service voice meets specification, or judges that the service voice meets the degree of specification, it will
The service voice meets specification, does not meet specification, meets the degree of specification as second processing as a result, so that it is determined that target object
The service voice quality of service voice on each object time.
It is handled to the target video data on each object time, obtains the first processing on each object time
As a result, and the target audio data on each object time are handled, obtain the second processing knot on each object time
After fruit, target is determined by the second processing result in the first processing result and each object time on each object time
Processing result, that is, target video data and target audio data are associated by object time, to same on object time
The target video data of Shi Fasheng and target audio aggregation of data assess the service quality of target object, avoid logical
It crosses artificial selective examination, determine the service quality of object according only to monitor video content, according only to audio content, reached comprehensive right
The effect that data are handled.
As an alternative embodiment, handling the target video data on each object time, obtain every
The first processing result on a object time includes: by service behavior indicated by the target video data on each object time
It is compared with the goal behavior on object time, obtains the first comparison result, and the first comparison result is determined as at first
Manage result；Target audio data on each object time are handled, the second processing knot on each object time is obtained
Fruit include: by the target voice on service voice and object time indicated by the target audio data on each object time into
Row compares, and obtains the second comparison result, and the second comparison result is determined as second processing result.
In this embodiment, the target video data on each object time is handled, obtains each object time
On the first processing result when, available goal behavior, the goal behavior be for target object service behavior carry out
The standards service behavior of assessment, for measuring the service behavior quality of target object.By the target video on each object time
Goal behavior on service behavior and object time indicated by data is compared, and obtains the first comparison result, first ratio
It can be the target line on service behavior and object time indicated by the target video data on each object time compared with result
For similarity between the two, when can be from service behavior indicated by the target video data on each object time and target
Main behavioural characteristic is extracted in the goal behavior engraved to be compared, using the first obtained comparison result as at first
Manage result.
Optionally, it handles, is obtained on each object time to the target audio data on each object time
When second processing result, available target voice, the target voice is assessed for the service voice to target object
Standards service voice, for measuring the service voice quality of target object.By the target audio data on each object time
Target voice on indicated service voice and object time is compared, and obtains the second comparison result, this second compares knot
Fruit can be the target voice two on service voice and object time indicated by the target audio data on each object time
Similarity between person, can be from service voice and object time indicated by the target audio data on each object time
Target voice in extract main phonetic feature to be compared, using the second obtained comparison result as second processing knot
Fruit.
As an alternative embodiment, passing through the first processing result on each object time and each object time
On second processing result determine that target process outcome includes: to convert the first value for the first comparison result, and second is compared
As a result it is converted into second value；By the first value and second value sum of the two, it is determined as target process outcome.
In this embodiment, passing through second in the first processing result and each object time on each object time
When processing result determines target process outcome, the first value can be converted by the first comparison result, which can be score,
For example, by both goal behaviors on service behavior and object time indicated by the target video data on each object time
Between similarity be converted into score, wherein service behavior indicated by the target video data on each object time and mesh
The goal behavior engraved when mark similarity between the two is big, then score is higher, on the contrary, then score is lower；Optionally, the implementation
Example can also convert second value for the second comparison result, which can be score, for example, by each object time
Target voice on service voice and object time indicated by target audio data similarity between the two is converted into score,
Wherein, both target voices on service voice and object time indicated by the target audio data on each object time it
Between similarity it is bigger, then score is higher, on the contrary, then score is lower.
The first value is being converted by the first comparison result, and after converting second value for the second comparison result, by first
Value and second value sum of the two, are determined as target process outcome, and then export target process outcome, which can be with
The comprehensive score assessed for the service quality to target object.Optionally, in the service of same object time target object
In the case where behavior quality and service voice quality height, for example, in the service behavior quality of same object time target object
Up to standard with service voice quality, then the service quality of target object is just higher.
It should be noted that determining that target process outcome is only that the present invention is real above by both the first value and second value
A kind of citing for applying example, not representing the set the goal really method of processing result of the embodiment of the present invention is only the above method, any
It can be used for assessing the assessment result of the service quality of target object all within the scope of the embodiment of the present invention, it is not another herein
One illustrates.
As an alternative embodiment, obtaining target video data in step S102, and step S104 obtains target
Before audio data, this method further include: the local zone time of local zone time and voice acquisition module to image capture module into
Row synchronizes, wherein the local zone time of image capture module is used in the service behavior by image capture module to target object
When being shot, the time that instruction service behavior is occurred, the local zone time of voice acquisition module is for passing through voice collecting
When module records the service voice of target object, the time that service voice is occurred is indicated.
In this embodiment, target video data is being obtained by image capture module, and is being obtained by voice acquisition module
Before taking target audio data, the local zone time of local zone time and voice acquisition module to image capture module is synchronized,
Local zone time namely objective time after synchronizing so that by image capture module obtain target video data indicated by
Service behavior time of origin and by voice acquisition module obtain target audio data indicated by service voice hair
The raw time is synchronous, that is, when target object is serviced, the service behavior and service language that occur on synchronization
Sound can correspond, and comprehensive assessment be carried out for the service quality to target object, so as to comprehensively to target object
Service quality assessed.
As an alternative embodiment, when the local of local zone time and voice acquisition module to image capture module
Between to synchronize include: by time server to the local zone time of image capture module and the local zone time of voice acquisition module
It synchronizes.
In this embodiment, time server is a kind of computer network instrument, obtains real time, then benefit from reference clock
Time information is passed to user with network, can dispose on the internet, can also be deployed in local area network.The embodiment exists
When the local zone time of local zone time and voice acquisition module to image capture module synchronizes, time server can be passed through
The local zone time of local zone time and voice acquisition module to image capture module synchronizes, that is, image capture module
Local zone time and the local zone time of voice acquisition module are synchronous with time server, so that being obtained by image capture module
Target video data indicated by service behavior time of origin and by voice acquisition module obtain target audio data
The time of the generation of indicated service voice is synchronous, so that the service behavior occurred on synchronization and service
Voice can correspond, and improve the accuracy being determined to the service quality of target object.
As an alternative embodiment, when the local of local zone time and voice acquisition module to image capture module
Between synchronize include: timing the local zone time of image capture module and the local zone time of voice acquisition module are synchronized.
In this embodiment it is possible to which timing is to the local zone time of image capture module and the local zone time of voice acquisition module
Synchronize, for example, at regular intervals automatically to the local of the local zone time of image capture module and voice acquisition module when
Between synchronize, in this way the service behavior of target object in the target time period is shot to obtain by image capture device
Target video data and the service voice of target object in the target time period record by voice capture device
To target audio data can be associated by the object time in target time section, and then on each object time
Target video data and each object time on target audio data handled, obtain being used to indicate target object in mesh
The target process outcome for marking the service quality in the period has reached and has comprehensively been assessed the service quality of target object
Purpose.
As an alternative embodiment, image capture module and voice acquisition module are disposed on the target device,
The local zone time of image capture module and the local zone time of voice acquisition module are the local zone time of target device, Image Acquisition
The local zone time of module is used for when being shot by service behavior of the image capture module to target object, indicates service rows
For the time occurred, the local zone time of voice acquisition module is used in the service language by voice acquisition module to target object
When sound is recorded, the time that service voice is occurred is indicated.
In this embodiment, image capture module and voice acquisition module can dispose on the target device, that is, image
Acquisition module and voice acquisition module, which can be set, to be integrated, and target device can facilitate target object to take for mobile phone, brooch etc.
The equipment of band.In this case, the local zone time of image capture module and the local zone time of voice acquisition module are target
The local zone time of equipment can not have to time server to the local zone time of image capture module and the local of voice acquisition module
Time synchronizes.
As an alternative embodiment, being located in advance after obtaining target video data to target video data
Reason, for example, resolution ratio, size, clarity etc. based on target video data pre-process target video data；It is obtaining
After target audio data, target audio data are pre-processed, for example, the size based on target audio data, transmission speed
Rate etc. is pre-processed, and easily storage, the data easily transmitted is become, in order to the target video number on each object time
It is handled according to the target audio data on each object time, obtains target process outcome, improve at data
The efficiency of reason, and then achieved the effect that comprehensively to handle data, reached the comprehensive service quality to target object into
The determining purpose of row.
The embodiment is by deployment image capture module, voice acquisition module, in conjunction with image capture module to target object
The target video data that service behavior in the target time period is shot, voice acquisition module is to target object in mesh
The target audio data that service voice in the mark period is recorded, to the target video data on each object time
Integrated treatment is carried out with the target audio data on each object time, has achieved the effect that comprehensively to handle data, into
And achieve the purpose that the service quality of comprehensive assessment target object, human intervention is not needed, and avoid by manually spot-check,
It determines caused by the service quality of target object according only to monitor video content, according only to audio content to target object
The incomplete problem of service quality assessment has achieved the effect that the service quality of comprehensive determining target object.
In the present embodiment, upper data processing method can be applied to the hardware environment being made of server and terminal
In.Server is attached by network and terminal, and above-mentioned network includes but is not limited to: wide area network, Metropolitan Area Network (MAN) or local area network.This
The data processing method of inventive embodiments can be executed by terminal, be can also be and executed jointly by server and terminal.
Embodiment 2
Technical solution of the present invention is illustrated below with reference to preferred embodiment.
In this embodiment, the monitoring view being monitored to waiter is obtained by deployment video monitoring equipment
Frequently, the sound pick-up outfit worn by waiter obtains the audio recorded to the voice of waiter, and then combines monitor video
The service quality for carrying out comprehensive assessment waiter with audio without human intervention, and is able to solve due to according only to prison
Control video content, or according only to audio content come determine caused by the service quality of object to the service quality of waiter into
Row assesses incomplete problem.
Fig. 2 is that a kind of pair of data according to an embodiment of the present invention are handled and are determined with the service quality to waiter
Schematic diagram.As shown in Fig. 2, process to the determination of the service quality of waiter the following steps are included:
Step 201, deployment time server.
Time server can be disposed on the internet, can also be disposed in deployment time server by the embodiment
In local area network, herein with no restrictions.
Step S202 carries out time calibration to sound pick-up outfit and video monitoring equipment by time server and the time is same
Step, and the audio data of the service voice by sound pick-up outfit acquisition waiter, pass through video monitoring equipment and obtain waiter's
The video data of service behavior.
In this embodiment it is possible to which timing carries out time school to sound pick-up outfit and video monitoring equipment by time server
Quasi- and time synchronization.Waiter with calibration with it is synchronous after sound pick-up outfit, which can be used for waiter's
Service voice is recorded, and audio data is obtained, which can serve to indicate that the sound that waiter is exchanged with client
Frequently.Calibrate with it is synchronous after video monitoring equipment be deployed in coverage, shot for the service behavior to waiter,
Video data is obtained, which can serve to indicate that the service behavior of waiter, and then by audio data and corresponding visitor
It sees time and video data and corresponding objective time is recorded and saved.
Step S203 analyzes audio data by voice messaging analysis module, to determine service behavior quality, and
Video data is analyzed by video information analysis module, to determine service voice quality.
In the audio data for the service voice for obtaining waiter by sound pick-up outfit, is obtained and serviced by video monitoring equipment
After the video data of the service behavior of member, audio data can be analyzed by speech analysis module, be obtained for referring to
Show the service quality Speech Assessment of the service behavior quality of waiter as a result, and record it is corresponding with the assessment result objective when
Between, video data is analyzed by video information analysis module, obtains the service voice quality for being used to indicate waiter
Service quality video evaluations are as a result, and record objective time corresponding with the assessment result.
Step S204, the audio-video service quality comprehensive assessment module of time synchronization is according to the objective time of record, to every
One service quality Speech Assessment is as a result, in conjunction with simultaneous service quality video evaluations as a result, obtaining service quality assessment
As a result, providing evaluation to the service quality of waiter with synthesis.
The embodiment incoherent audio data, video data alignment will be established connection originally, be convenient for by time synchronization
Carry out the service quality of evaluation services person in conjunction with voice data and video data.
In this embodiment, all high with the service quality Speech Assessment result of time and service quality video assessment result
, then Integrated Services Quality assessment result is also high, final output service quality assessment result.
Optionally, in this embodiment, the equipment that waiter can wear collection recording, camera shooting one, in this case
It can not have to time server to come synchronization time, but the higher cost of this method investment.
Optionally, which can also pre-process audio/video information, be made by audio/video information preprocessing module
Treated that audio/video information is more advantageous to storage, transmission, operation, to improve the efficiency handled data.
By dispose video monitoring equipment, sound pick-up outfit, in conjunction with video monitoring equipment to waiter in the target time period
The video data that is shot of service behavior, sound pick-up outfit carries out the service voice of waiter in the target time period
Obtained audio data is recorded, video data and audio data are associated by corresponding objective time, and then is carried out comprehensive
Conjunction processing, has achieved the effect that comprehensively to handle data, and then achieve the purpose that the service quality of comprehensive assessment waiter,
Human intervention is not needed, and avoids by manually spot-check, determined according only to monitor video content, according only to audio content
To the incomplete problem of the service quality assessment of waiter caused by the service quality of waiter, comprehensive determining service is reached
The effect of the service quality of member.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
Embodiment 3
The embodiment of the invention also provides a kind of data processing equipments.It should be noted that the data processing of the embodiment
Device can be used for executing the data processing method of the embodiment of the present invention.
Fig. 3 is a kind of schematic diagram of data processing equipment according to an embodiment of the present invention.As shown in figure 3, the device can be with
It include: first acquisition unit 10, second acquisition unit 20 and processing unit 30.
First acquisition unit 10, for obtaining target video data, wherein target video data is by image capture module pair
The service behavior of target object in the target time period is shot to obtain.
Second acquisition unit 20, for obtaining target audio data, wherein target audio data are by voice acquisition module pair
The service voice of target object in the target time period is recorded to obtain.
Processing unit 30, for determining multiple object times from target time section, and to the mesh on each object time
Target audio data on mark video data and each object time are handled, and obtain target process outcome, wherein at target
Reason result is used to indicate the service quality of target object in the target time period.
Optionally, processing unit 30 includes: first processing module, for the target video data on each object time
It is handled, obtains the first processing result on each object time, wherein the first processing result on each object time is used
In the service behavior quality of service behavior of the instruction target object on each object time；Second processing module, for every
Target audio data on a object time are handled, and the second processing result on each object time is obtained, wherein each
Second processing result on object time is used to indicate the service voice of service voice of the target object on each object time
Quality；Determining module, for passing through the second processing in the first processing result and each object time on each object time
As a result target process outcome is determined.
Optionally, first processing module includes: the first processing submodule, for by the target video on each object time
Goal behavior on service behavior and object time indicated by data is compared, and obtains the first comparison result, and by first
Comparison result is determined as the first processing result；Second processing module includes: second processing submodule, is used for each object time
On target audio data indicated by target voice on service voice and object time be compared, obtain second and compare knot
Fruit, and the second comparison result is determined as second processing result.
Optionally it is determined that module includes: transform subblock, for converting the first value for the first comparison result, and by
Two comparison results are converted into second value；Submodule is determined, for being determined as target processing for the first value and second value sum of the two
As a result.
Optionally, device further include: synchronization unit for obtaining target video data, and obtains target sound frequency
According to before, the local zone time of local zone time and voice acquisition module to image capture module is synchronized, wherein Image Acquisition
The local zone time of module is used for when being shot by service behavior of the image capture module to target object, indicates service rows
For the time occurred, the local zone time of voice acquisition module is used in the service language by voice acquisition module to target object
When sound is recorded, the time that service voice is occurred is indicated.
Optionally, synchronization unit includes: the first synchronization module, for the sheet by time server to image capture module
The local zone time of ground time and voice acquisition module synchronizes.
Optionally, synchronization unit includes: the second synchronization module, for timing to the local zone time and language of image capture module
The local zone time of sound acquisition module synchronizes.
Optionally, the image capture module of the embodiment and voice acquisition module are disposed on the target device, and image is adopted
The local zone time of the local zone time and voice acquisition module that collect module is the local zone time of target device, image capture module
Local zone time is used for when being shot by service behavior of the image capture module to target object, and instruction service behavior is sent out
Raw time, the local zone time of voice acquisition module are used to carry out by service voice of the voice acquisition module to target object
When recording, the time that service voice is occurred is indicated.
The embodiment obtains target video data by first acquisition unit 10, wherein target video data is adopted by image
Collection module is shot to obtain to the service behavior of target object in the target time period, by second acquisition unit 20 in acquisition
Target audio data, wherein service language of the target audio data by voice acquisition module to target object in the target time period
Sound is recorded to obtain, and through the processing unit 30, for determining multiple object times from target time section, and to each target
When the target video data and each object time that engrave on target audio data handled, obtain target process outcome,
Wherein, target process outcome is used to indicate the service quality of target object in the target time period.That is, to same target
When the video data that engraves and audio data handled, reached the comprehensive mesh being determined to the service quality of target object
, the service quality that object is determined by manually spot-check, according only to monitor video content, according only to audio content is avoided,
The technical effect handled comprehensively data is reached, has solved and data are carried out to handle incomplete technical problem.
Embodiment 4
The embodiment of the invention also provides a kind of storage mediums.The storage medium includes the program of storage, wherein in program
Equipment executes the data processing method of any one of embodiment of the present invention where controlling storage medium when operation.
Embodiment 5
The embodiment of the invention also provides a kind of processors.The processor is for running program, wherein program is held when running
The data processing method of any one of the row right embodiment of the present invention.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific
Hardware and software combines.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (11)
1. a kind of data processing method characterized by comprising
Obtain target video data, wherein the target video data is by image capture module to target object in the object time
Service behavior in section is shot to obtain；
Obtain target audio data, wherein the target audio data are by voice acquisition module to the target object described
Service voice in target time section is recorded to obtain；
Multiple object times are determined from the target time section, and to the target video number on each object time
It is handled according to the target audio data on each object time, obtains target process outcome, wherein the mesh
Mark processing result is used to indicate service quality of the target object in the target time section.
2. the method according to claim 1, wherein to the target video number on each object time
It is handled according to the target audio data on each object time, obtaining target process outcome includes:
The target video data on each object time is handled, on each object time is obtained
One processing result, wherein first processing result on each object time is used to indicate the target object every
The service behavior quality of service behavior on a object time；
The target audio data on each object time are handled, on each object time is obtained
Two processing results, wherein the second processing result on each object time is used to indicate the target object in each institute
State the service voice quality of the service voice on object time；
At described second in first processing result and each object time on each object time
Reason result determines the target process outcome.
3. according to the method described in claim 2, it is characterized in that,
The target video data on each object time is handled, on each object time is obtained
One processing result includes: by service behavior indicated by the target video data on each object time and the mesh
The goal behavior engraved when mark is compared, and obtains the first comparison result, and first comparison result is determined as described
One processing result；
The target audio data on each object time are handled, on each object time is obtained
Two processing results include: by service voice and the mesh indicated by the target audio data on each object time
The target voice engraved when mark is compared, and obtains the second comparison result, and second comparison result is determined as described
Two processing results.
4. according to the method described in claim 3, it is characterized in that, passing through first processing on each object time
As a result determine that the target process outcome includes: with the second processing result on each object time
The first value is converted by first comparison result, and converts second value for second comparison result；
By first value and the second value sum of the two, it is determined as the target process outcome.
5. method as claimed in any of claims 1 to 4, which is characterized in that obtaining target video data, and obtaining
Before taking target audio data, the method also includes:
The local zone time of local zone time and voice acquisition module to described image acquisition module synchronizes, wherein the figure
As the local zone time of acquisition module be used for by described image acquisition module to the service behavior of the target object into
When row shooting, the time that the service behavior is occurred is indicated, the local zone time of the voice acquisition module is used for passing through
When stating voice acquisition module and recording to the service voice of the target object, indicate what the service voice was occurred
Time.
6. according to the method described in claim 5, it is characterized in that, local zone time and voice collecting mould to image capture module
The local zone time of block, which synchronizes, includes:
By time server to the local zone time of the local zone time of described image acquisition module and the voice acquisition module into
Row synchronizes.
7. according to the method described in claim 5, it is characterized in that, local zone time and voice collecting mould to image capture module
The local zone time of block, which synchronizes, includes:
Timing synchronizes the local zone time of described image acquisition module and the local zone time of the voice acquisition module.
8. method as claimed in any of claims 1 to 4, which is characterized in that described image acquisition module and described
Voice acquisition module is disposed on the target device, the local zone time of described image acquisition module and the voice acquisition module
Local zone time is the local zone time of the target device, and the local zone time of described image acquisition module is used to pass through the figure
When being shot as the service behavior of the acquisition module to the target object, indicate that the service behavior occurred when
Between, the local zone time of the voice acquisition module is used in the clothes by the voice acquisition module to the target object
When business voice is recorded, the time that the service voice is occurred is indicated.
9. a kind of data processing equipment characterized by comprising
First acquisition unit, for obtaining target video data, wherein the target video data is by image capture module to mesh
The service behavior of mark object in the target time period is shot to obtain；
Second acquisition unit, for obtaining target audio data, wherein the target audio data are by voice acquisition module to institute
Service voice of the target object in the target time section is stated to be recorded to obtain；
Processing unit, for determining multiple object times from the target time section, and on each object time
The target audio data in the target video data and each object time are handled, and target processing knot is obtained
Fruit, wherein the target process outcome is used to indicate service quality of the target object in the target time section.
10. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require any one of 1 to 8 described in method.
11. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 8 described in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811604135.3A CN109740020A (en) | 2018-12-26 | 2018-12-26 | Data processing method, device, storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811604135.3A CN109740020A (en) | 2018-12-26 | 2018-12-26 | Data processing method, device, storage medium and processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109740020A true CN109740020A (en) | 2019-05-10 |
Family
ID=66361297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811604135.3A Pending CN109740020A (en) | 2018-12-26 | 2018-12-26 | Data processing method, device, storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740020A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532988A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Behavior monitoring method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN110909613A (en) * | 2019-10-28 | 2020-03-24 | Oppo广东移动通信有限公司 | Video character recognition method and device, storage medium and electronic equipment |
| CN111883247A (en) * | 2020-07-29 | 2020-11-03 | 复旦大学 | Analysis system for correlation between behavior data and medical outcome |
| CN112633037A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Object monitoring method and device, storage medium and electronic equipment |
| CN110909613B (en) * | 2019-10-28 | 2024-05-31 | Oppo广东移动通信有限公司 | Video character recognition method and device, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310373A (en) * | 2013-03-13 | 2013-09-18 | 四川天翼网络服务有限公司 | Bank counter service evaluation system based on audio and video recognition and method thereof |
| CN107018372A (en) * | 2017-04-20 | 2017-08-04 | 深圳声联网科技有限公司 | Voice recognition monitoring record method and device |
| CN107978344A (en) * | 2017-11-20 | 2018-05-01 | 广州市健全家源信息科技有限公司 | A kind of behavior monitoring and managing method, device and electronic equipment |
-
2018
- 2018-12-26 CN CN201811604135.3A patent/CN109740020A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310373A (en) * | 2013-03-13 | 2013-09-18 | 四川天翼网络服务有限公司 | Bank counter service evaluation system based on audio and video recognition and method thereof |
| CN107018372A (en) * | 2017-04-20 | 2017-08-04 | 深圳声联网科技有限公司 | Voice recognition monitoring record method and device |
| CN107978344A (en) * | 2017-11-20 | 2018-05-01 | 广州市健全家源信息科技有限公司 | A kind of behavior monitoring and managing method, device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 鲁业频: "《数字电视原理与应用技术》", 30 June 2009, 国防工业出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532988A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Behavior monitoring method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN112633037A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Object monitoring method and device, storage medium and electronic equipment |
| CN110909613A (en) * | 2019-10-28 | 2020-03-24 | Oppo广东移动通信有限公司 | Video character recognition method and device, storage medium and electronic equipment |
| CN110909613B (en) * | 2019-10-28 | 2024-05-31 | Oppo广东移动通信有限公司 | Video character recognition method and device, storage medium and electronic equipment |
| CN111883247A (en) * | 2020-07-29 | 2020-11-03 | 复旦大学 | Analysis system for correlation between behavior data and medical outcome |
| CN111883247B (en) * | 2020-07-29 | 2022-03-15 | 复旦大学 | Analysis system for correlation between behavior data and medical outcome |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740020A (en) | Data processing method, device, storage medium and processor | |
| CN105160318B (en) | Lie detecting method based on facial expression and system | |
| CN107918755A (en) | A kind of real-time focus analysis method and system based on face recognition technology | |
| US8354579B2 (en) | Music linked photocasting service system and method | |
| CN105934753A (en) | Sharing video in a cloud video service | |
| CN110458591A (en) | Advertising information detection method, device and computer equipment | |
| CN108132952A (en) | A kind of active searching method and device based on speech recognition | |
| CN109189544A (en) | Method and apparatus for generating dial plate | |
| CN108010526A (en) | Method of speech processing and device | |
| CN108983966B (en) | Criminal reconstruction assessment system and method based on virtual reality and eye movement technology | |
| CN108388889A (en) | Method and apparatus for analyzing facial image | |
| US20180165622A1 (en) | Action analysis device, acton analysis method, and analysis program | |
| CN110059624A (en) | Method and apparatus for detecting living body | |
| GB2575388A (en) | Method, apparatus and system for discovering and displaying information related to video content | |
| EP3979133A1 (en) | Systems, methods, and storage media for selecting video portions for a video synopsis of streaming video content | |
| CN111063455A (en) | Human-computer interaction method and device for telemedicine | |
| CN111210818B (en) | Word acquisition method and device matched with emotion polarity and electronic equipment | |
| CN110392271A (en) | The method and apparatus that live video examines | |
| CN111368737A (en) | System and method for automatically analyzing working behaviors of staff | |
| CN107783856A (en) | A kind of method of testing and system of image processor parameter | |
| CN114661928A (en) | Retrieval method, device and equipment of violation image and storage medium | |
| JP2019191718A (en) | Serving operation analysis and evaluation system | |
| CN115499677A (en) | Audio and video synchronization detection method and device based on live broadcast | |
| CN111770300B (en) | Conference information processing method and virtual reality head-mounted equipment | |
| CN112235517B (en) | Method for adding white-matter, device for adding white-matter, and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |