CN111504300A - Service quality evaluation method and device of perception robot and storage medium - Google Patents
Service quality evaluation method and device of perception robot and storage medium Download PDFInfo
- Publication number
- CN111504300A CN111504300A CN202010285954.7A CN202010285954A CN111504300A CN 111504300 A CN111504300 A CN 111504300A CN 202010285954 A CN202010285954 A CN 202010285954A CN 111504300 A CN111504300 A CN 111504300A
- Authority
- CN
- China
- Prior art keywords
- robot
- area
- service quality
- service
- acquiring
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Abstract
The application discloses a service quality evaluation method, a service quality evaluation device and a storage medium of a perception robot, which can acquire client distribution information and robot position information in a service area, divide the service area into a concentrated area and a sparse area according to the client distribution information, set the central point of the concentrated area as a target point, enable the perception robot to move towards areas with more clients and acquire more service quality evaluations as much as possible; meanwhile, a reachable area is obtained according to the robot position information and the target point, a potential moving range is obtained according to the client distribution information, an unreachable area is obtained, a moving path is calculated according to the reachable area and the unreachable area, and the perception that the robot collides with the client in the moving process is effectively avoided; and the service quality evaluation is obtained according to the obtained face image and the trained multi-color channel sequencing network, so that the service quality evaluation can be accurately and quickly obtained.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a service quality evaluation method and device of a perception robot and a storage medium.
Background
At present, the service industry and government service organizations pay more and more attention to the service quality, the evaluation of customers is the most intuitive embodiment of the service quality, in order to obtain the evaluation of the customers, the traditional method mainly depends on questionnaires, not only a large amount of manpower is consumed, but also more time is occupied by the customers, and the participation enthusiasm of the customers is low.
With the development of image recognition technology, facial images of users can be acquired through a camera, corresponding expressions are recognized, some perception robots are available on the market for reducing manual operation and improving automation degree, image processing equipment is mounted in the robots, facial images of the customers in a service area are acquired through movement of the perception robots, and therefore the expressions of the customers are recognized, and service quality evaluation is calculated on the basis of the expressions. However, the client does not stay at a fixed place, but may move in a service area, if the perception robot moves only according to a fixed route, collision accidents are easily caused with the client, although some perception robots can also carry the existing obstacle avoidance algorithm, the client is not uniformly distributed in the service area, and the perception robot is easily operated in an area where the client is rare by adopting the obstacle avoidance algorithm, so that data required by service quality evaluation cannot be normally collected.
Disclosure of Invention
In order to overcome the defects of the prior art, the application aims to provide a service quality evaluation method, a service quality evaluation device and a storage medium for a perception robot, which can reasonably plan a path and improve the efficiency of acquiring service quality evaluation data.
The technical scheme adopted by the application for solving the problems is as follows: in a first aspect, the present application provides a service quality evaluation method for a perception robot, including the following steps:
acquiring customer distribution information and robot position information in a service area, dividing the service area into a concentrated area and a sparse area according to the customer distribution information, and setting a central point of the concentrated area as a target point;
acquiring a reachable area according to the robot position information and the target point;
obtaining a potential moving range according to the client distribution information, and obtaining an unreachable area according to the potential moving range;
calculating a moving path according to the reachable area and the unreachable area, and acquiring a face image of the client in the moving path;
and obtaining service quality evaluation according to the facial image and the trained multi-color channel sequencing network.
One or more technical schemes provided in the embodiment of the application have at least the following beneficial effects: the service quality evaluation method of the perception robot is applied to the perception robot, can acquire client distribution information and robot position information in a service area, divides the service area into a concentrated area and a sparse area according to the client distribution information, sets a central point of the concentrated area as a target point, can enable the perception robot to move towards areas with more clients, and collects more service quality evaluations as much as possible; meanwhile, a reachable area is obtained according to the robot position information and the target point, a potential moving range is obtained according to the client distribution information, an unreachable area is further obtained, a moving path is calculated according to the reachable area and the unreachable area, and the perception that the robot collides with the client in the moving process is effectively avoided; and the service quality evaluation is obtained according to the obtained face image and the trained multi-color channel sequencing network, so that the service quality evaluation can be accurately and rapidly obtained.
Optionally, in an embodiment of the present application, before acquiring the customer distribution information and the robot location information in the service area, the method further includes: and establishing a rectangular coordinate system by taking the vertex of the service area as the origin of coordinates.
Optionally, in an embodiment of the present application, the obtaining of the customer distribution information further includes: and reading the acquisition time interval, and acquiring the primary client distribution information according to the acquisition time interval.
Optionally, in an embodiment of the present application, the acquiring of the acquisition time interval specifically includes the following steps:
acquiring position information of each client in the client distribution information acquired at the current time, and acquiring corresponding client coordinates in the rectangular coordinate system according to the position information;
acquiring a customer distance between the customer coordinate and the coordinate origin;
and calculating the arithmetic mean value of all the customer distances, reading the arithmetic mean value of the customer distances acquired last time and a preset adjusting threshold, if the absolute value of the difference value of the arithmetic mean values of the customer distances acquired two times is smaller than the adjusting threshold, increasing the acquisition time interval, and if the absolute value is larger than the adjusting threshold, decreasing the acquisition time interval.
Optionally, in an embodiment of the present application, the calculating a reachable area according to the robot position information and the target point specifically includes the following steps:
acquiring a robot coordinate corresponding to the robot position information in the rectangular coordinate system, and acquiring a target point coordinate corresponding to the target point in the rectangular coordinate system;
and acquiring the number of customers in the service area, acquiring a target point weight according to the number of customers, and acquiring the reachable area according to the target point weight, the robot coordinate and the target point coordinate.
Optionally, in an embodiment of the present application, the deriving a potential moving range according to the customer distribution information specifically includes:
acquiring speed information of a client in the service area;
deriving the potential movement range according to the speed information and the customer distribution information;
and obtaining distance information between the robot and the client according to the robot position information and the client distribution information, and obtaining the inaccessible area according to the distance information and the potential moving range.
Optionally, in an embodiment of the present application, the deriving the service quality evaluation according to the facial image and the trained multi-color channel ranking network specifically includes the following steps:
converting the facial image into a color space image;
splitting the color space image into color images of a plurality of colors;
coding the color image through a convolutional neural network to obtain channel space characteristics, and performing dimension reduction sequencing on the channel space characteristics;
and inputting the sequenced channel space characteristics into a recurrent neural network to obtain a service quality evaluation result.
Optionally, in an embodiment of the present application, if the number of the service areas is at least greater than 2, the method further includes performing weighted summation on the service quality evaluation of each service area to obtain an overall service quality evaluation.
In a second aspect, the present application provides a service quality evaluation apparatus for a perception robot, including at least one control processor and a memory for communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform a method of perception of quality of service assessment of a robot as described above.
In a third aspect, the present application provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the service quality evaluation method for a perception robot as described above.
In a fourth aspect, the present application also provides a computer program product comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the method for quality of service assessment of a perception robot as described above.
Drawings
The present application is further described below with reference to the following figures and examples.
Fig. 1 is a flowchart of a service quality evaluation method for a perception robot according to an embodiment of the present application;
fig. 2 is a flowchart of a service quality evaluation method for a perception robot according to another embodiment of the present application;
fig. 3 is a flowchart of a method for evaluating service quality of a perception robot according to another embodiment of the present application;
fig. 4 is a flowchart of a service quality evaluation method for a perception robot according to another embodiment of the present application;
fig. 5 is a flowchart of a method for evaluating service quality of a perception robot according to another embodiment of the present application;
fig. 6 is a flowchart of a method for evaluating service quality of a perception robot according to another embodiment of the present application;
fig. 7 is a flowchart of a method for evaluating service quality of a perception robot according to another embodiment of the present application;
fig. 8 is a schematic device diagram for performing a service quality evaluation method of a perception robot according to another embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that, if not conflicted, the various features of the embodiments of the present application may be combined with each other within the scope of protection of the present application. Additionally, while functional block divisions are performed in apparatus schematics, with logical sequences shown in flowcharts, in some cases, steps shown or described may be performed in sequences other than block divisions in apparatus or flowcharts.
Referring to fig. 1, a first embodiment of the present application provides a service quality evaluation method for a perception robot, including the following steps S110 to S150:
step S110, acquiring customer distribution information and robot position information in a service area, dividing the service area into a concentrated area and a sparse area according to the customer distribution information, and setting a central point of the concentrated area as a target point;
step S120, acquiring a reachable area according to the position information and the target point of the robot;
step S130, obtaining a potential moving range according to the client distribution information, and obtaining an unreachable area according to the potential moving range;
step S140, calculating a moving path according to the reachable area and the unreachable area, and acquiring a face image of the client in the moving path;
and S150, obtaining service quality evaluation according to the facial image and the trained multi-color channel sequencing network.
It should be noted that, the perception robot in the embodiment of the present application may be any common perception robot in the prior art, and path planning, facial image acquisition, and data transmission may be performed only.
It should be noted that, the number of sensing robots in the embodiment of the present application may be any, and the following description is exemplified in a usage scenario in which a service area is large, for example, a main sensing robot and a plurality of sub-sensing robots may be provided, where each sensing robot is configured to obtain a service quality evaluation of one service sub-area, the main sensing robot performs data processing and path planning, sends a planned moving path to each sub-sensing robot, the plurality of sub-sensing robots perform face image acquisition in response to the moving path sent by the main sensing robot, and sends the acquired face image to the main sensing robot, and the main sensing robot calculates the service quality evaluation of each service sub-area, and obtains the service quality evaluation of the entire service area by a weighted summation method. The number and primary and secondary distribution modes of the specific perception robots are adjusted according to actual requirements.
It should be noted that the facial images in the embodiment of the present application may be acquired by any type of camera, for example, a common multi-directional camera may acquire facial images of multiple users at multiple angles at the same time, so as to improve the efficiency of image acquisition.
In an embodiment, the client distribution information may be a location corresponding to each client in the service area, and since the number of clients in the actual usage scenario is usually greater than 2, acquiring the client distribution information can provide a data base for the client location in the service area.
In an embodiment, the concentrated region and the sparse region may adjust a specific determination manner according to an actual requirement, for example, the service region is divided into a plurality of sub-regions, if the number of customers in the sub-region meets a preset number threshold, the sub-regions are concentrated sub-regions, all the concentrated sub-regions are added to obtain the concentrated region, the sparse region is a region of the service region excluding the concentrated region, and distinguishing between the concentrated region and the sparse region enables the sensing direction of the robot to be biased to the concentrated region, so that more service quality evaluations are obtained through more customers.
In an embodiment, the moving path may be any route from the position of the robot to the position of the target point in the reachable area, for example, the route may be a straight line, or may pass through as many customers as possible according to the customer distribution information, and the specific manner may be selected according to actual needs.
Another embodiment of the present application further provides a service quality evaluation method for a perception robot, as shown in fig. 2, fig. 2 is a schematic diagram of another embodiment of a detailed flow of step S110 in fig. 1, where the step S110 includes, but is not limited to:
step S210, a rectangular coordinate system is established with the vertex of the service area as the origin of coordinates.
In one embodiment, to facilitate path planning, the service area may take the form of a square area. It can be understood that the origin of coordinates may adopt any vertex of the square region, and a rectangular coordinate system may be constructed, and the position of the client may be represented by coordinates, which is not described herein again.
Another embodiment of the present application further provides a service quality evaluation method for a perception robot, as shown in fig. 3, fig. 3 is a schematic diagram of another embodiment of a detailed flow of step S110 in fig. 1, where the step S110 includes, but is not limited to:
and step S310, reading the acquisition time interval, and acquiring the client distribution information once according to the acquisition time interval.
In an embodiment, the collection time interval may be a constant value or a value that changes adaptively, if a constant value is used, that is, the collection is performed at equal time intervals, when the time interval is set to be large, the client distribution changes greatly, which causes the perception robot to move back and forth near the original location, and it is difficult to collect facial expressions of the client, which causes a decrease in accuracy of service quality evaluation acquisition, and when the time interval is set to be small, the perception robot operates too frequently under the condition of slow client distribution change, which wastes a large amount of system resources.
Another embodiment of the present application further provides a service quality evaluation method for a perception robot, as shown in fig. 4, fig. 4 is a schematic diagram of another embodiment of a detailed flow of step S310 in fig. 3, where the step S310 includes, but is not limited to:
step S410, acquiring the position information of each client in the client distribution information acquired at the current time, and acquiring corresponding client coordinates in a rectangular coordinate system according to the position information;
step S420, obtaining a client distance between the client coordinate and the coordinate origin;
step S430, calculating an arithmetic mean of all the customer distances, and reading the arithmetic mean of the customer distances obtained last time and a preset adjustment threshold, if the absolute value of the difference between the arithmetic mean of the customer distances obtained two times is smaller than the adjustment threshold, increasing the acquisition time interval, and if the absolute value is larger than the adjustment threshold, decreasing the acquisition time interval.
Based on the above embodiments, the present application adopts a distance-based adaptive algorithm to adjust the acquisition time interval, and based on an embodiment of establishing a rectangular coordinate system in the service area, the following distance description is performed by taking a specific example:
generating corresponding client coordinates in a rectangular coordinate system, e.g., (x) at the location of the service area based on the location information of each client1,y1)、(x2,y2)...(xk,yk) (ii) a Obtaining the client distance between each current client coordinate and the coordinate origin, wherein the specific calculation formula is as follows:
then according to the distance diCalculate the average of the current customer distance:
then calculating the arithmetic mean value of the customer distances acquired by two adjacent timesThe absolute value of the difference of (a) is:
wherein
Is the arithmetic mean of the currently collected customer distances,
is the arithmetic mean of the last collected customer distances.
Based on the above embodiment, the adjustment threshold may be any value or may be a value interval, for example, 0.4,0.6, where s ∈ [0.4,0.6] calculated in the above embodiment is appropriate for the acquisition time interval, where s <0.4 is smaller for the acquisition time interval, and needs to be increased for the acquisition time interval, and where s >0.6 is larger for the acquisition time interval, and needs to be decreased for the acquisition time interval.
Based on the above embodiment, the acquisition time interval can be calculated by the following formula:
wherein t is the current acquisition time interval, and the initialized sampling time interval t0 is 0.5 s; a is a scale factor and takes the value of (0, 1)]D is the customer distribution ratio, and its value is in the range of (1,2), and the value of D is determined by the following formula:
is the arithmetic mean of the currently collected customer distances,
is the arithmetic mean of the last collected customer distances,
is composed of
The arithmetic mean value of the last acquired customer distance can be used for adjusting the acquisition time interval by utilizing the ratio of the poor distribution of the customers, so that a better self-adaptive effect is achieved.
Another embodiment of the present application further provides a service quality evaluation method for a perception robot, as shown in fig. 5, fig. 5 is a schematic diagram of another embodiment of a detailed flow of step S120 in fig. 1, where the step S120 includes, but is not limited to:
step S510, acquiring a robot coordinate corresponding to the robot position information in a rectangular coordinate system, and acquiring a target point coordinate corresponding to a target point in the rectangular coordinate system;
step S520, the number of customers in the service area is obtained, the weight of the target point is obtained according to the number of the customers, and the reachable area is obtained according to the weight of the target point, the coordinates of the robot and the coordinates of the target point.
Based on the above embodiment of establishing the rectangular coordinate system, the following is illustrated as a specific example:
in a rectangular coordinate system, (x, y) is the coordinate of the perception robot, (p)x,py) Is the customer coordinates. v is the walking speed of the client, and the calculation formula of the walking speed of the client is as follows:
wherein (p)x1,py1)、(px0,py0) The coordinates of the client at the current time and the last time, respectively, and t1 and t0 are the times of the current time and the last time, respectively. Based on this, the reachable domain of the target point can be determined:
wherein (g)x,gy) Is the coordinates of the target point, and g _ w is the target point weight, depending on the number of customers in the service area,
e.g. of concentrated areaThe specific target point weight can be adjusted and selected according to the actual requirement. Determining the tendency of the perception robot to move according to the inaccessible domain and the accessible domain of the perception robot: s ═ Sn+Sy，
gradS is the moving coordinate of the perception robot at the current time.
Another embodiment of the present application further provides a service quality evaluation method for a perception robot, as shown in fig. 6, fig. 6 is a schematic diagram of another embodiment of a detailed flow of step S130 in fig. 1, where the step S130 includes, but is not limited to:
step S610, acquiring speed information of a client in a service area;
step S620, obtaining a potential moving range according to the speed information and the client distribution information;
and step S630, obtaining distance information between the robot and the client according to the robot position information and the client distribution information, and obtaining the unreachable area according to the distance information and the potential moving range.
Based on the above embodiment of establishing the rectangular coordinate system, the following is illustrated as a specific example: firstly, modeling the clients according to the positions and the speeds of the clients, wherein the potential moving range of each client is as follows:
where c and b are constants and may be arbitrary values, for example, 135 and 1 are taken, r is a client area r which is L v, L may be arbitrary values, for example, 15 is taken, v is a speed of client walking, and the calculation method may refer to the above embodiment and is not described herein again, and θ is a polar angle:
and x and y are coordinates of the perception robot in the service area. γ is the central angle:
the unreachable domain of the perception robot is then determined according to the potential movement range of each customer:
wherein
d is the distance between the perception robot and the customer. Mu-1 (0, 1)]As a contraction factor, when d>When 1, mu is set to be reduced; when d is<When 1, μ ═ 1. The setting of mu can lead the perception robot to bypass the client and simultaneously can collect the facial expression of the client in a close distance.
Another embodiment of the present application further provides a service quality evaluation method for a perception robot, as shown in fig. 7, fig. 7 is a schematic diagram of another embodiment of a detailed flow of step S150 in fig. 1, where the step S150 includes, but is not limited to:
step S710 of converting the face image into a color space image;
step S720, splitting the color space image into color images of a plurality of colors;
step S730, coding the color image through a convolutional neural network to obtain channel space characteristics, and performing dimensionality reduction sequencing on the channel space characteristics;
and step S740, inputting the sorted channel space characteristics into a recurrent neural network to obtain a service quality evaluation result.
The following is illustrated with one specific example:
the perception robot processes the collected face image, for example, by performing rectification, removing duplicate face images, and segmenting the face image from the background. The perception robot converts the processed face image into images of 5 different color spaces: RGB, YCbCr, xyz, RGB and YIQ images. Splitting the channels of the 5 different color space images into 15 color images: r, G, B, Y, Cb, Cr, x, Y, z, R, G, B, Y, I, and Q images. The 15 color images are coded by adopting a convolutional neural network to obtain channel space characteristics, the convolutional neural network can adopt any existing network, for example, the convolutional neural network comprises an input layer with 64x64 pixels and three convolutional layers with convolutional kernel sizes of 3x3, the number of channels of the three convolutional layers is 32, 32 and 64 respectively, a maximum pooling layer with kernel sizes of 3x3 and step length of 2 is connected behind each convolutional layer, and finally two 1024-node full-connection layers are connected.
After the channel space features are obtained, using T-SNE (T-Distribution storage probabilistic neighbor embedding, T-Distribution random neighbor embedding) to perform dimension reduction ordering on the obtained 15 channel space features, for example, using the following steps: input channel feature set I ═ I1,i2，…，i15Determining the iteration time T as 10000, learning rate lr as 0.0001, momentum α as 0.5, and calculating the channel space feature dimension reduction set O as tSNE (I, T, lr, α) as { O }1，o2，…，o15}; calculating the space characteristic length of each channel after dimension reduction
Wherein u is the characteristic dimension of each channel after dimension reduction.
The method comprises the steps of utilizing the obtained length dw of each channel space feature after dimensionality reduction to sort the channel space features before dimensionality reduction, inputting the sorted channel space features into a recurrent neural network, wherein the recurrent neural network comprises two layers of L STMs, each layer of L STM comprises 512 hidden nodes, and finally connecting a full connecting layer of 1024 nodes to synthesize the two layers of L STMs and output a result Eb of facial expression of a client, wherein the value of b is 0 or 1, 0 represents that the client is open, and 1 represents that the client is not open.
In another embodiment of the present application, if the number of service areas is at least greater than 2, the method further includes performing weighted summation on the service quality assessment of each service area to obtain an overall service quality assessment.
Based on the above embodiment, if the number of service areas is greater than 2,obtaining the number of the clients in each service area by utilizing a multi-color channel sorting network, comparing the number of the clients in each service area with the total number of the clients in the service area to obtain the service quality of each service area, and then weighting and summing the service quality of each service area to obtain the overall service quality:
n is the number of service areas,ithe weight of each service area is defined by the total number of people in each service areaiAnd the larger Ni is, the larger the weight is, and the total weight is 1. HiThe number of happy people in each service area.
In an embodiment, the service quality evaluation may be set according to an actual requirement, for example, in the above embodiment, when Z <0.5, it may indicate that the current overall service quality is poor; when 0.6< Z <0.7, it may indicate that the current overall quality of service is general; when 0.7< Z <0.8, it may indicate that the current overall quality of service is good; when 0.8< Z <0.9, it may indicate that the current overall quality of service is superior; when 0.9< Z <1, it may indicate that the current overall quality of service is excellent.
Referring to fig. 8, another embodiment of the present application further provides a service quality evaluation apparatus 5000 for a perception robot, including: memory 8100, control processor 8200 and a computer program stored in memory 8200 and executable on control processor 8100, the control processor implementing the method for quality of service evaluation of a perception robot as in any of the embodiments above, e.g. performing method steps S110 to S150 in fig. 1, method step S210 in fig. 2, method step S310 in fig. 3, method steps S410 to S430 in fig. 4, method steps S510 to S520 in fig. 5, method steps S610 to S630 in fig. 6, method steps S710 to S740 in fig. 7 as described above.
The control processor 8200 and the memory 8100 may be connected by a bus or other means, and fig. 8 illustrates the connection by the bus.
The memory 8100 serves as a non-transitory computer readable storage medium that may be used to store non-transitory software programs as well as non-transitory computer executable programs. Additionally, memory 8100 may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 8100 may optionally include a memory remotely located from the control processor 8200, which may be connected to the perception robot quality of service evaluation device 8000 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Optionally, the service quality evaluation device 8000 of the perception robot may further include a short-range wireless communication module, a temperature sensor, a humidity sensor, a clock module, a display screen, a control button, and the like. The short-distance wireless communication module can be a WIFI module or a Bluetooth module; in addition, when the display screen is a touch display screen, the control key may be a key function of the touch display screen.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Furthermore, another embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, which are executed by one or more control processors, for example, by one control processor 8200 in fig. 8, and may cause the one or more control processors 8200 to execute the method for service quality evaluation of the perception robot in the above method embodiment, for example, execute the above-described method steps S110 to S150 in fig. 1, the method step S210 in fig. 2, the method step S310 in fig. 3, the method steps S410 to S430 in fig. 4, the method steps S510 to S520 in fig. 5, the method steps S610 to S630 in fig. 6, and the method steps S710 to S740 in fig. 7.
It should be noted that, since the apparatus for executing the service quality evaluation method of the perception robot in the embodiment is based on the same inventive concept as the service quality evaluation method of the perception robot, the corresponding contents in the method embodiment are also applicable to the embodiment of the apparatus, and are not described in detail here.
Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by software plus a general hardware platform. Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the preferred embodiments of the present invention have been described, the present invention is not limited to the above embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and such equivalent modifications or substitutions are included in the scope of the present invention defined by the claims.
Claims (10)
1. A service quality evaluation method of a perception robot is used for the perception robot and is characterized by comprising the following steps:
acquiring customer distribution information and robot position information in a service area, dividing the service area into a concentrated area and a sparse area according to the customer distribution information, and setting a central point of the concentrated area as a target point;
acquiring a reachable area according to the robot position information and the target point;
obtaining a potential moving range according to the client distribution information, and obtaining an unreachable area according to the potential moving range;
calculating a moving path according to the reachable area and the unreachable area, and acquiring a face image of the client in the moving path;
and obtaining service quality evaluation according to the facial image and the trained multi-color channel sequencing network.
2. The method of claim 1, wherein before obtaining the customer distribution information and the robot location information in the service area, the method further comprises: and establishing a rectangular coordinate system by taking the vertex of the service area as the origin of coordinates.
3. The method of claim 2, wherein the obtaining of the customer distribution information further comprises: and reading the acquisition time interval, and acquiring the primary client distribution information according to the acquisition time interval.
4. The method for evaluating the service quality of the perception robot according to claim 3, wherein the acquiring of the collection time interval specifically comprises the following steps:
acquiring position information of each client in the client distribution information acquired at the current time, and acquiring corresponding client coordinates in the rectangular coordinate system according to the position information;
acquiring a customer distance between the customer coordinate and the coordinate origin;
and calculating the arithmetic mean value of all the customer distances, reading the arithmetic mean value of the customer distances acquired last time and a preset adjusting threshold, if the absolute value of the difference value of the arithmetic mean values of the customer distances acquired two times is smaller than the adjusting threshold, increasing the acquisition time interval, and if the absolute value is larger than the adjusting threshold, decreasing the acquisition time interval.
5. The method for evaluating the service quality of the perception robot according to claim 2, wherein the step of calculating the reachable area according to the robot position information and the target point specifically comprises the steps of:
acquiring a robot coordinate corresponding to the robot position information in the rectangular coordinate system, and acquiring a target point coordinate corresponding to the target point in the rectangular coordinate system;
and acquiring the number of customers in the service area, acquiring a target point weight according to the number of customers, and acquiring the reachable area according to the target point weight, the robot coordinate and the target point coordinate.
6. The method as claimed in claim 1, wherein the deriving a potential movement range according to the customer distribution information, and the deriving an unreachable area according to the potential movement range specifically includes:
acquiring speed information of a client in the service area;
deriving the potential movement range according to the speed information and the customer distribution information;
and obtaining distance information between the robot and the client according to the robot position information and the client distribution information, and obtaining the inaccessible area according to the distance information and the potential moving range.
7. The method as claimed in claim 1, wherein the deriving the service quality assessment according to the facial image and the trained multi-color channel ranking network specifically comprises:
converting the facial image into a color space image;
splitting the color space image into color images of a plurality of colors;
coding the color image through a convolutional neural network to obtain channel space characteristics, and performing dimension reduction sequencing on the channel space characteristics;
and inputting the sequenced channel space characteristics into a recurrent neural network to obtain a service quality evaluation result.
8. The service quality evaluation method of the perception robot as claimed in claim 1, wherein: and if the number of the service areas is at least more than 2, carrying out weighted summation on the service quality evaluation of each service area to obtain the overall service quality evaluation.
9. A service quality evaluation device of a perception robot is applied to the perception robot and is characterized by comprising at least one control processor and a memory which is in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform a method of quality of service assessment of a perception robot as claimed in any one of claims 1 to 8.
10. A computer-readable storage medium characterized by: the computer-readable storage medium stores computer-executable instructions for causing a computer to perform the method for perception-robot service quality assessment according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010285954.7A CN111504300B (en) | 2020-04-13 | 2020-04-13 | Service quality evaluation method and device of perception robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010285954.7A CN111504300B (en) | 2020-04-13 | 2020-04-13 | Service quality evaluation method and device of perception robot and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111504300A true CN111504300A (en) | 2020-08-07 |
| CN111504300B CN111504300B (en) | 2022-04-08 |
Family
ID=71870937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010285954.7A Active CN111504300B (en) | 2020-04-13 | 2020-04-13 | Service quality evaluation method and device of perception robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111504300B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106970630A (en) * | 2017-05-23 | 2017-07-21 | 上海棠棣信息科技股份有限公司 | A kind of robot actively provides method and device, the robot of service |
| CN107065863A (en) * | 2017-03-13 | 2017-08-18 | 山东大学 | A kind of guide to visitors based on face recognition technology explains robot and method |
| CN107168334A (en) * | 2017-06-26 | 2017-09-15 | 上海与德通讯技术有限公司 | A kind of paths planning method and robot |
| US20180189581A1 (en) * | 2010-06-07 | 2018-07-05 | Affectiva, Inc. | Vehicle manipulation using convolutional image processing |
| CN108614562A (en) * | 2018-06-05 | 2018-10-02 | 北京智行者科技有限公司 | A kind of cleaning method for optimizing route |
| CN109048934A (en) * | 2018-08-20 | 2018-12-21 | 深圳威琳懋生物科技有限公司 | A kind of intelligent shopping guide robot system |
| CN110263681A (en) * | 2019-06-03 | 2019-09-20 | 腾讯科技（深圳）有限公司 | The recognition methods of facial expression and device, storage medium, electronic device |
| CN110328662A (en) * | 2019-06-24 | 2019-10-15 | 北京理工华汇智能科技有限公司 | Paths planning method and device based on image recognition |
-
2020
- 2020-04-13 CN CN202010285954.7A patent/CN111504300B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180189581A1 (en) * | 2010-06-07 | 2018-07-05 | Affectiva, Inc. | Vehicle manipulation using convolutional image processing |
| CN107065863A (en) * | 2017-03-13 | 2017-08-18 | 山东大学 | A kind of guide to visitors based on face recognition technology explains robot and method |
| CN106970630A (en) * | 2017-05-23 | 2017-07-21 | 上海棠棣信息科技股份有限公司 | A kind of robot actively provides method and device, the robot of service |
| CN107168334A (en) * | 2017-06-26 | 2017-09-15 | 上海与德通讯技术有限公司 | A kind of paths planning method and robot |
| CN108614562A (en) * | 2018-06-05 | 2018-10-02 | 北京智行者科技有限公司 | A kind of cleaning method for optimizing route |
| CN109048934A (en) * | 2018-08-20 | 2018-12-21 | 深圳威琳懋生物科技有限公司 | A kind of intelligent shopping guide robot system |
| CN110263681A (en) * | 2019-06-03 | 2019-09-20 | 腾讯科技（深圳）有限公司 | The recognition methods of facial expression and device, storage medium, electronic device |
| CN110328662A (en) * | 2019-06-24 | 2019-10-15 | 北京理工华汇智能科技有限公司 | Paths planning method and device based on image recognition |
Non-Patent Citations (2)
| Title |
|---|
| YIKUI ZHAI 等: "BeautyNet: Joint Multiscale CNN and Transfer Learning Method for Unconstrained Facial Beauty Prediction", 《COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE》 * |
| 宋康: "《基于卷积神经网络的人体行为识别》", 《中国优秀硕士学位论文全文数据库》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111504300B (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598610B (en) | Target significance detection method based on neural selection attention | |
| CN108648161B (en) | Binocular vision obstacle detection system and method of asymmetric kernel convolution neural network | |
| CN110941999B (en) | Method for adaptively calculating size of Gaussian kernel in crowd counting system | |
| CN111126399A (en) | Image detection method, device and equipment and readable storage medium | |
| CN103514432A (en) | Method, device and computer program product for extracting facial features | |
| US20150227817A1 (en) | Category Histogram Image Representation | |
| CN104715251A (en) | Salient object detection method based on histogram linear fitting | |
| Laupheimer et al. | The importance of radiometric feature quality for semantic mesh segmentation | |
| CN109523015B (en) | Image processing method in neural network | |
| Shen et al. | Smart lighting control system based on fusion of monocular depth estimation and multi-object detection | |
| CN113901911A (en) | Image recognition method, image recognition device, model training method, model training device, electronic equipment and storage medium | |
| CN111504300B (en) | Service quality evaluation method and device of perception robot and storage medium | |
| CN113065379B (en) | Image detection method and device integrating image quality and electronic equipment | |
| CN112738725A (en) | Real-time identification method, device, equipment and medium for target crowd in semi-closed area | |
| CN111914809A (en) | Target object positioning method, image processing method, device and computer equipment | |
| Lu et al. | Environment-aware multiscene image enhancement for internet of things enabled edge cameras | |
| CN112036268B (en) | Component identification method and related device | |
| JP2019174910A (en) | Information acquisition device and information aggregation system and information aggregation device | |
| CN115272450A (en) | Target positioning method based on panoramic segmentation | |
| CN114419096A (en) | Multi-target tracking method for aerial video based on trapezoid frame | |
| KR101326644B1 (en) | Full-body joint image tracking method using evolutionary exemplar-based particle filter | |
| CN114764902A (en) | Behavior recognition method and device and storage medium | |
| CN103399893B (en) | Method for retrieving objects on basis of hierarchical perception | |
| CN113115072A (en) | Video target detection tracking scheduling method and system based on end cloud cooperation | |
| WO2021038840A1 (en) | Object number estimation device, control method, and program |
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 |