Network service supervision method and system

Abstract

The present application provides a method and system for supervising network point services, which relates to the field of intelligent recognition and can be applied to the financial field and other fields. The method includes: determining a plurality of detection areas according to the network point attributes of the current network point, and determining a supervision evaluation scope according to the detection areas and the identity information of the object to be supervised; collecting face data of network point users entering and leaving each of the detection areas to generate a vector data set; analyzing the vector data set through a preset expression recognition model to obtain the occurrence frequency of the predetermined expression information of the user, and comparing the occurrence frequency with a preset threshold to obtain a first comparison result; and obtaining the service evaluation result of the object to be supervised in the corresponding detection area according to the first comparison result and the vector data set.

Description

Technical Field

[0001] This application relates to the field of intelligent recognition and can be applied to the financial field and other fields, especially a method and system for supervising network service. Background Art

[0002] At present, with the continuous development of human science and technology, face recognition technology has become more and more popular in people's daily lives. Whether in the research of artificial intelligence or in public security applications, face recognition technology has always been a cutting-edge and popular technology, playing a crucial role. Among them, smile recognition in face recognition technology is a very important part in the field of computer vision technology. With the growth of application requirements such as face payment, emotion analysis, and medical monitoring, face recognition, as an important part of completing human-computer interaction, has received more and more attention, which has prompted global researchers to intensify their efforts in smile recognition technology. The existing network service supervision mainly determines the service quality of network service personnel by means of personnel spot checks and evaluations. This method has certain defects. For example, the workload of evaluators is relatively large, and there are also large errors in the spot check method. Moreover, the time of customers cannot be accurately predicted. Therefore, the existing network service supervision problem has always been a major problem that needs to be solved in the industry. Summary of the Invention

[0003] The purpose of this application is to provide a method and system for supervising network service, which analyzes customers based on face recognition technology to determine the satisfaction of customers, and judges the service quality of the network based on this satisfaction, so as to complete the reverse supervision of network service.

[0004] To achieve the above object, a method for supervising network service provided by this application includes: determining a plurality of detection areas according to the network attributes of the current network, and determining the supervision and evaluation scope according to the detection areas and the identity information of the object to be supervised; collecting face data of network users entering and leaving each of the detection areas to generate a vector data set; analyzing the vector data set through a preset expression recognition model to obtain the occurrence frequency of the user's preset expression information, and comparing the occurrence frequency with a preset threshold to obtain a first comparison result; obtaining the service evaluation result of the object to be supervised in the corresponding detection area according to the first comparison result and the vector data set.

[0005] In the above method for supervising network service, optionally, determining a plurality of detection areas according to the network attributes of the current network includes: partitioning the public area and a plurality of detection areas according to the position information of each service device and the public area information in the predetermined network by the principle of proximity in position, and respectively numbering the public area and the detection areas.

[0006] In the above-mentioned network point service supervision method, optionally, the generation of the vector data set by collecting the face data of network point users entering and leaving each of the detection areas includes: sorting the numbers of the detection areas according to the collection time of the face data collected by the network point users in each detection area to generate one-dimensional vector data; and merging the face data into the one-dimensional vector data to obtain the vector data set.

[0007] In the above-mentioned network point service supervision method, optionally, the generation of the vector data set by collecting the face data of network point users entering and leaving each of the detection areas includes: collecting the monitoring video data of network point users through face tracking technology; analyzing multiple frame image data in the monitoring video data to obtain the full body orientation, viewing direction and position data of the users; obtaining the residence time of the network point users in each detection area according to the position data of the users in the multiple frame image data; and generating the vector data set according to the full body orientation, the viewing direction, the position data and the residence time.

[0008] In the above-mentioned network point service supervision method, optionally, obtaining the service evaluation result of the object to be supervised in the corresponding detection area according to the first comparison result and the vector data set includes: analyzing the service category handled by the network point users according to the vector data set, and obtaining the service handling time through the residence time and the service category; comparing the service handling time with a preset service handling threshold to obtain a second comparison result, and obtaining the service evaluation result of the object to be supervised according to the second comparison result.

[0009] In the above-mentioned network point service supervision method, optionally, obtaining the service evaluation result of the object to be supervised according to the second comparison result further includes: collecting the residence time of each object to be supervised in the corresponding detection area, and comparing the residence times of each object to be supervised to obtain a third comparison result; and obtaining the service evaluation result of the object to be supervised according to the second comparison result and the third comparison result.

[0010] The present application also provides a network point service supervision system, which includes a definition module, a collection module, a comparison module and an analysis module; the definition module is used to determine a plurality of detection areas according to the network point attributes of the current network point, and determine the supervision evaluation scope according to the detection areas and the identity information of the objects to be supervised; the collection module is used to collect the face data of network point users entering and leaving each of the detection areas to generate a vector data set; the comparison module is used to analyze the occurrence frequency of the predetermined expression information of the users according to the vector data set through a preset expression recognition model, and compare the occurrence frequency with a preset threshold to obtain a first comparison result; the analysis module is used to obtain the service evaluation result of the object to be supervised in the corresponding detection area according to the first comparison result and the vector data set.

[0011] In the above-mentioned network point service supervision system, optionally, the definition module includes a partitioning unit, which is configured to partition, according to the location information and public area information of each service device within a predetermined network point, to obtain a public area and a plurality of detection areas by the principle of proximity in location, and number the public area and the detection areas respectively.

[0012] In the above-mentioned network point service supervision system, optionally, the acquisition module includes a tracking unit, which is configured to collect monitoring video data of network point users through face tracking technology; analyze multi-frame image data in the monitoring video data to obtain the full-body orientation, viewing direction and position data of the users; obtain the residence time of network point users in each detection area according to the position data of the users in the multi-frame image data; and generate a vector data set according to the full-body orientation, the viewing direction, the position data and the residence time.

[0013] In the above-mentioned network point service supervision system, optionally, the analysis module further includes: analyzing the vector data set to obtain the types of services handled by network point users, and obtaining the service handling time through the residence time and the types of services; comparing the service handling time with a preset service handling threshold to obtain a second comparison result, and obtaining a service evaluation result of the object to be supervised according to the second comparison result.

[0014] This application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the above method when executing the computer program.

[0015] This application also provides a computer-readable storage medium, which stores a computer program for executing the above method.

[0016] The beneficial technical effects of this application are as follows: It can be used as an evaluation basis for refined service quality management of network segments, complete network point service supervision, effectively save manpower while improving the accuracy of supervision results, and complete efficient network point service supervision. Description of the Drawings

[0017] The drawings described herein are used to provide a further understanding of this application, form a part of this application, and do not limit this application. In the drawings:

[0018] Figure 1 It is a schematic flowchart of the network point service supervision method provided by an embodiment of this application;

[0019] Figure 2 It is a schematic flowchart of the generation process of the vector data set provided by an embodiment of this application;

[0020] Figure 3Schematic diagram of the generation process of the vector data set provided by an embodiment of the present application;

[0021] Figure 4 Schematic diagram of the service evaluation generation process of the object to be supervised provided by an embodiment of the present application;

[0022] Figure 5 Schematic diagram of the service evaluation generation process of the object to be supervised provided by an embodiment of the present application;

[0023] Figure 6 Schematic diagram of the structure of the network service supervision system provided by an embodiment of the present application;

[0024] Figure 7 Schematic diagram of the structure of the electronic device provided by an embodiment of the present application. Detailed implementation manners

[0025] The following will describe in detail the implementation manners of the present application in combination with the accompanying drawings and embodiments, so as to fully understand how the present application uses technical means to solve technical problems and the implementation process of achieving technical effects and implement accordingly. It should be noted that as long as there is no conflict, the various embodiments in the present application and the various features in each embodiment can be combined with each other, and the formed technical solutions are all within the protection scope of the present application.

[0026] In addition, the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0027] Please refer to Figure 1 As shown, a network service supervision method provided by the present application includes:

[0028] S101 Determine a plurality of detection areas according to the network attributes of the current network, and determine the supervision evaluation range according to the detection areas and the identity information of the object to be supervised;

[0029] S102 Collect face data of network users entering and leaving each of the detection areas to generate a vector data set;

[0030] S103 Analyze through a preset expression recognition model according to the vector data set to obtain the occurrence frequency of the user's predetermined expression information, and compare the occurrence frequency with a preset threshold to obtain a first comparison result;

[0031] S104 Obtain the service evaluation result of the object to be supervised in the corresponding detection area according to the first comparison result and the vector data set.

[0032] In actual work, the face capture technology has matured. The existing face detection and attribute analysis modules can be used to track faces, dynamically locate faces, perform live detection, obtain the outlines of eyes, mouths, and noses, and identify various face attributes such as gender, age, and expression. Therefore, this application uses user expressions to judge the service situation of the object to be supervised. For example, if the number of times a user smiles is higher than the preset number, it means that the user is in a good mood at present, indicating that the service quality is good. Thus, the service evaluation result of the object to be supervised in the corresponding detection area is determined.

[0033] In an embodiment of this application, determining multiple detection areas according to the network point attributes of the current network point may include: based on the position information and public area information of each service device in the predetermined network point, partitioning through the principle of proximity to obtain a public area and multiple detection areas, and numbering the public area and the detection areas respectively. In actual work, each device in the network point hall can be partitioned and numbered according to the principle of proximity. When a customer enters the equipment area, a fixed number is displayed. The number of the hall public area is 0, and the consecutive numbers of the positions where people enter the network point form a one-dimensional vector, which is merged into the one-dimensional vector dataset of the person; the last equipment position before the customer leaves is the destination position of the customer, and the probability of the customer entering the network point is the number of types of equipment. Specifically, please refer to Figure 2 As shown, in another embodiment of this application, collecting the face data of network point users entering and leaving each of the detection areas to generate a vector dataset may include:

[0034] S201 According to the collection time of the face data collected by the network point users in each detection area, sort the numbers of each detection area to generate a one-dimensional vector data;

[0035] S202 Merge the face data into the one-dimensional vector data to obtain a vector dataset.

[0036] Thus, this vector dataset contains task attributes. For a person entering the range of the lobby monitor and successfully reaching near the network point equipment, it forms a closed loop. This closed loop is a one-dimensional vector group that contains the parameter values extracted for anomalies.

[0037] Please refer to Figure 3 As shown, in an embodiment of this application, collecting the face data of network point users entering and leaving each of the detection areas to generate a vector dataset includes:

[0038] S301 Collect the monitoring video data of network point users through face tracking technology;

[0039] S302 Analyze the multi-frame image data in the monitoring video data to obtain the full-body orientation, observation direction, and position data of the user;

[0040] S303 obtains the residence time of the network point user in each detection area according to the position data of the user in the multi-frame image data;

[0041] S304 generates a vector data set according to the whole body orientation, the observation direction, the position data and the residence time.

[0042] In actual work, the analysis of the characteristics of network point users may include the following parts: the whole body orientation of pedestrians (the angle of the pedestrian movement direction), the attention direction / head pose estimation of pedestrians (the pedestrian observation direction), the distance and size of pedestrians (height and width) and the regional position in the monitoring range, the recognition of the presence of pedestrians, the gender recognition of pedestrians (male or female); to further improve the accuracy of the analysis results, the current network point attributes can also be supplemented, such as: 1: near the commercial street, 2: near the residential area, 3: in the suburbs, 4: in the villages and towns, 5: transportation hub, 6: government agencies, etc. Information, and the purposes of network point users are assisted in analysis by these network point attributes. Of course, in actual work, those skilled in the relevant art can select and set according to actual needs, and this application does not make further limitations in this regard.

[0043] Please refer to Figure 4 As shown, in an embodiment of the present application, obtaining the service evaluation result of the supervised object in the corresponding detection area according to the first comparison result and the vector data set may include:

[0044] S401 analyzes and obtains the business category handled by the network point user according to the vector data set, and obtains the business handling time through the residence time and the business category;

[0045] S402 compares the business handling time with a preset business handling threshold to obtain a second comparison result, and obtains the service evaluation result of the supervised object according to the second comparison result.

[0046] In this way, it is determined whether the supervised object efficiently completes the business guidance under the condition of user satisfaction according to the business handling time of each network point user; further, when there are multiple supervised objects in a certain detection area, it can be as Figure 5 As shown, obtaining the service evaluation result of the supervised object according to the second comparison result may further include:

[0047] S501 collects the residence time of each supervised object in the corresponding detection area, and compares the residence time of each supervised object to obtain a third comparison result;

[0048] S502 obtains the service evaluation result of the supervised object according to the second comparison result and the third comparison result.

[0049] Thus, by comparing the residence time of each object to be supervised, its interaction and service with the user can be confirmed. To further determine which object to be supervised has more effective communication with the network users, the facial expression changes during the interaction between the user and the object to be supervised, such as the frequency of smiling, can also be analyzed in practical applications.

[0050] Taking the bank branch employees as the objects to be supervised as an example, the network service supervision method provided by this application can include the following processes when applied:

[0051] I. Using the face capture mechanism, during the face-to-face business handling process between employees and customers, such as capturing the customer before entering the branch door (perceiving the urgency), capturing the customer when stepping into the branch (perceiving the target location and predicting whether it is a high counter or a low counter), the facial expressions of the customer during the waiting process for the lobby manager and during the conversation with the lobby manager (perceiving the nervousness and urgency), capturing the customer when handling business, when ending the business, and when leaving the branch (perceiving the customer satisfaction) to capture the faces of the customer and employees; if the number of times the customer smiles reaches the threshold, the excellent points of each receiving employee will be evaluated once.

[0052] II. Extracting features from the captured face images: Establishing a customer model ID before capture, extracting customer information according to artificial intelligence, pre-classifying according to the judgment of artificial intelligence to improve the prediction accuracy. According to the preset smiling face recognition model and the extracted face features, for example, when the customer approaches the branch, extracting human body features such as the customer's height, weight, gender, clothing, whether carrying a briefcase, whether wearing glasses, etc., and excluding customers with low importance; determining the number of times the employee smiles, and extracting the on-site sound. If there is a smile plus sound, it is a higher degree of smile and the satisfaction is higher. If the number of times the customer smiles reaches the threshold, the excellent points of each receiving employee will be evaluated once.

[0053] III. Improving the service rating of employees with a higher number of smiling faces: (For example: Marking customers such as ordinary children, the elderly, those with crutches, eye diseases, and those with improper clothing as low-level customers, who need to be served by ordinary lobby managers, and high-level users need to be served by star-level lobby managers immediately to optimize human resources).

[0054] Furthermore, the face capture technology can also be used to capture the people entering the hall, check the captured faces, and give early warnings to those without masks, and ask the lobby manager to provide help in a timely manner to improve the epidemic prevention ability of the branch.

[0055] In this embodiment, the method for evaluating the excellent points of each receiving employee can be adopted as follows:

[0056] Since the vector data set is a column vector, which contains 1. the dimension information of the network point location, 2. the dimension information of the customers entering the network point area, and 3. the information collected from the customers entering the equipment area of each network point (including smile, behavior, and the number of the network point equipment area where the face is facing), a scoring function formula is constructed to calculate and evaluate the vector. The function formula 1 is as follows:

[0057] f(x,W)=Wx(+h);

[0058] The score value of this one-dimensional vector is calculated, where x is a column vector before the customer enters the network point to handle business. W is a row (random) vector, which is the weight corresponding to each value in the data set of the customer entering the network point. b is a column vector of the number of purposes of a customer entering the network segment, which is used as a bias parameter (our initial value is 1) and is fine-tuned according to the result as the weight.

[0059] The equipment number when the customer enters the network point and finally leaves the network point is the target value we need to obtain. According to the target value, the loss value of this scoring function is calculated, that is, the wrong score obtained by the scoring function minus the correct score. The value greater than zero is the loss value, and the value less than or equal to zero has no loss, thus obtaining the loss function.

[0060] Loss function:

[0061]

[0062] The loss function is defined as calculating the scoring function for all data sets of customers entering the network point and leaving after handling business, and then performing operations according to the loss function. The scoring function of formula 1 is operated, the wrong value is subtracted from the correct value, and then 1 (variable parameter, tolerance level) is added for summation. The smaller this value is, the better. The values less than zero are discarded, and then the sum of all data sets is calculated and the average value is taken.

[0063] Among them, f(x i ;W)i is the wrong score, f(x i ;W)y i is the correct score. Then, the max function is used to set the values less than zero to zero, and then the sum of all scores is calculated and the average value is taken, which is the final loss score.

[0064] Perform regularization transformation on it:

[0065]

[0066] Use the data set of customers entering the network point and the weight parameter to calculate using the scoring function, and then calculate the loss based on the correct value using the score value, and then add the regularization penalty term to obtain a loss value with distinguishable meaning.

[0067] Among them, the penalty term is expressed as the sum of squares of the W weight parameters used for each implement score value of k groups of scores, and then multiplied by the penalty parameter λ, where λ is an adjustable penalty parameter. Δ is the tolerable parameter, which is adjusted according to the final value range.

[0068] Finally, a softmax classifier is used for classification, and the formula is as follows:

[0069]

[0070] After calculating the score values for classifying the implements, all the score categories are classified. The method is to perform the e-power calculation on the score values. That is, s is the score value. After calculation, the classification is clearer. Then, all are normalized. That is, the sum of the implement scores is used as the denominator, and the implement score value is used as the numerator to calculate the probability value of each value (since the probability value is positive, a negative sign is added in front of the value). The loss value is used to optimize each group of W weight parameters. The chain derivative is performed on each W weight parameter to obtain the change trend of the W weight parameter. To obtain the minimum loss, it can be based on each optimization equation as follows:

[0071]

[0072] According to the trend calculated from the W weight parameters, the W weight parameters are optimized. When the dataset is large enough, the W weight parameters will form a fixed range value. The more the dataset, the smaller the range of the W weight value. Then, substituting the value of x, which is a column vector before the customer enters the network to handle business, into the score function formula, the probability of the customer specifically doing a certain business and possibly doing a certain business can be predicted. Then, the prediction is used to score the participation of the lobby manager and the employees in the high and low counters of the network in the processing process.

[0073] In actual work, the above integral calculation process can be used as a way to quantitatively measure the service levels of various objects to be supervised in the network. Those skilled in the relevant art can also use other methods for evaluation. This application only provides an implementation method here and does not make further limitations.

[0074] Please refer to Figure 6As shown in the figure, the present application also provides a network point service supervision system, which includes a definition module, a collection module, a comparison module, and an analysis module. The definition module is used to determine multiple detection areas according to the network point attributes of the current network point, and determine the supervision evaluation scope according to the detection areas and the identity information of the object to be supervised. The collection module is used to collect the face data of network point users entering and leaving each of the detection areas to generate a vector data set. The comparison module is used to analyze the occurrence frequency of the predetermined expression information of the user through a preset expression recognition model according to the vector data set, and compare the occurrence frequency with a preset threshold to obtain a first comparison result. The analysis module is used to obtain the service evaluation result of the object to be supervised in the corresponding detection area according to the first comparison result and the vector data set.

[0075] In the above embodiment, the definition module may include a partitioning unit, which is used to partition the public area and multiple detection areas according to the position information of each service device and the public area information in the predetermined network point by the principle of proximity in position, and number the public area and the detection areas respectively. The collection module may include a tracking unit, which is used to collect the monitoring video data of network point users through face tracking technology; analyze the multi-frame image data in the monitoring video data to obtain the overall orientation, observation direction, and position data of the user; obtain the residence time of the network point user in each detection area according to the position data of the user in the multi-frame image data; generate a vector data set according to the overall orientation, the observation direction, the position data, and the residence time. In another embodiment, the analysis module may further include: analyzing the business type handled by the network point user according to the vector data set, and obtaining the business handling time through the residence time and the business type; comparing the business handling time with a preset business handling threshold to obtain a second comparison result, and obtaining the service evaluation result of the object to be supervised according to the second comparison result.

[0076] Based on the above embodiment, the network point service supervision system provided by the present application mainly includes the following three implementation methods in actual application:

[0077] First, use the customers when they enter the network point gate to predict the business handled by the customers. Whether the lobby manager guides in time and whether the average time for the customers to handle business is within a reasonable range (the average value of handling business, that is, the average time for each type of business from the customer entering the network point to leaving the network point). If the lobby manager accesses in time and the customers handle business successfully and in time, then an excellent score is given once. Divide the number of scored times by the number of receptions to obtain the employee service effect score table, and the service quality stability ranking of the employees can be obtained; sort the time for each type of handled business to obtain the service effect ranking.

[0078] II. Use the customer portrait when the customer enters the branch door to predict whether the customer urgently needs the reception of the lobby manager (judge that the lobby manager and key customers are in the same area). For example, elderly people such as senior uncles and aunts need the lobby manager to receive them as soon as possible, or young children without adult supervision, and blind people, etc.; if the lobby manager accesses in time, an excellent score will be evaluated once.

[0079] III. Use the time when the customer stays in each area of the branch. When the stay time in an area exceeds the threshold, confirm whether the lobby manager follows up (judge that the lobby manager and key customers are in the same area). If the lobby manager accesses in time, an excellent score will be evaluated once.

[0080] The beneficial technical effects of this application are as follows: It can be used as an evaluation basis for the refined service quality management of the network segment, complete the service supervision of the branch, improve the accuracy of the supervision results while effectively saving manpower, and complete the efficient service supervision of the branch.

[0081] This application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above method is implemented.

[0082] This application also provides a computer-readable storage medium, which stores a computer program for executing the above method.

[0083] As Figure 7 shown, the electronic device 600 may further include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It should be noted that the electronic device 600 does not necessarily have to include Figure 7 all the components shown in Figure 7 ; in addition, the electronic device 600 may further include

[0084] components not shown in Figure 7 ; reference may be made to the prior art.

[0085] Among them, the memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices. The above information related to failures can be stored, and in addition, programs for executing relevant information can also be stored. And the central processing unit 100 can execute the program stored in the memory 140 to implement information storage or processing, etc.

[0086] The input unit 120 provides input to the central processing unit 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to supply power to the electronic device 600. The display 160 is used to display display objects such as images and texts. The display can be, for example, an LCD display, but is not limited thereto.

[0087] The memory 140 can be a solid-state memory, for example, a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that stores information even when power is off, can be selectively erased and has more data, and an example of this memory is sometimes referred to as an EPROM, etc. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 can include an application / function storage unit 142, and the application / function storage unit 142 is used to store application programs and function programs or the processes for operating the electronic device 600 through the central processing unit 100.

[0088] The memory 140 can also include a data storage unit 143, and the data storage unit 143 is used to store data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 can include various drivers of the electronic device for communication functions and / or for performing other functions of the electronic device (such as a messaging application, an address book application, etc.).

[0089] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via the antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0090] Based on different communication technologies, multiple communication modules 110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc. The communication module (transmitter / receiver) 110 is also coupled to the speaker 131 and the microphone 132 via the audio processor 130 to provide an audio output via the speaker 131 and receive an audio input from the microphone 132, so as to implement normal telecommunication functions. The audio processor 130 can include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 130 is also coupled to the central processing unit 100, so that recording can be performed on the local machine through the microphone 132, and the sound stored on the local machine can be played through the speaker 131.

[0091] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0092] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0093] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0095] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present application. It should be understood that the above description is only for the specific embodiments of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for supervising network point services, characterized in that, The method includes: Determining a plurality of detection regions according to the branch attributes of the current branch, and determining a supervision evaluation scope according to the detection regions and the identity information of the object to be supervised; wherein, the branch attributes include: Near commercial streets, near residential areas, outskirts, villages and towns, transportation hubs, government agencies; Collecting face data of branch users entering and leaving each of the detection regions to generate a vector data set; Analyzing the vector data set through a preset expression recognition model to obtain the occurrence frequency of the predetermined expression information of the user, comparing the occurrence frequency with a preset threshold to obtain a first comparison result; obtaining a service evaluation result of the object to be supervised in the corresponding detection region according to the first comparison result and the vector data set; Among them, collecting face data of branch users entering and leaving each of the detection regions to generate a vector data set includes: collecting monitoring video data of branch users through face tracking technology; analyzing multi-frame image data in the monitoring video data to obtain the whole body orientation, observation direction and position data of the user; obtaining the residence time of the branch user in each detection region according to the position data of the user in the multi-frame image data; generating a vector data set according to the whole body orientation, the observation direction, the position data and the residence time.

2. The network point service supervision method according to claim 1, characterized in that, Determining a plurality of detection regions according to the branch attributes of the current branch includes: partitioning to obtain a public area and a plurality of detection regions according to the position information of each service device and the public area information in the predetermined branch by the principle of proximity in position, and numbering the public area and the detection regions respectively.

3. The network point service supervision method according to claim 2, characterized in that Collecting face data of branch users entering and leaving each of the detection regions to generate a vector data set includes: Sorting the numbers of each detection region according to the collection time of the face data collected by the branch user in each detection region to generate one-dimensional vector data; Merging the face data into the one-dimensional vector data to obtain a vector data set.

4. The network service supervision method according to claim 1, characterized in that Obtaining a service evaluation result of the object to be supervised in the corresponding detection region according to the first comparison result and the vector data set includes: Analyzing the vector data set to obtain the business category handled by the branch user, and obtaining the business handling time through the residence time and the business category; Comparing the business handling time with a preset business handling threshold to obtain a second comparison result, and obtaining a service evaluation result of the object to be supervised according to the second comparison result.

5. The network service supervision method according to claim 4, wherein Obtaining a service evaluation result of the object to be supervised according to the second comparison result further includes: Collecting the residence time of each object to be supervised in the corresponding detection region, and comparing the residence time of each object to be supervised to obtain a third comparison result; Obtaining a service evaluation result of the object to be supervised according to the second comparison result and the third comparison result.

6. A network service supervision system, characterized in that, The system includes a definition module, a collection module, a comparison module and an analysis module; The definition module is used to determine a plurality of detection regions according to the branch attributes of the current branch, and determine a supervision evaluation scope according to the detection regions and the identity information of the object to be supervised; wherein, the branch attributes include: near commercial streets, near residential areas, outskirts, villages and towns, transportation hubs, government agencies; The acquisition module is used to acquire face data of network point users entering and leaving each of the detection areas to generate a vector data set; The comparison module is used to analyze the occurrence frequency of the user's predetermined expression information according to the vector data set through a preset expression recognition model, and compare the occurrence frequency with a preset threshold to obtain a first comparison result; The analysis module is used to obtain the service evaluation result of the supervised object corresponding to the detection area according to the first comparison result and the vector data set; Among them, the acquisition module includes a tracking unit, and the tracking unit is used to collect monitoring video data of network point users through face tracking technology; analyze multiple frame image data in the monitoring video data to obtain the full body orientation, observation direction and position data of the user; obtain the residence time of the network point user in each detection area according to the position data of the user in the multiple frame image data; generate a vector data set according to the full body orientation, the observation direction, the position data and the residence time.

7. The network service supervision system according to claim 6, wherein The definition module includes a partitioning unit, and the partitioning unit is used to partition the public area and multiple detection areas according to the position information of each service device and the public area information in the predetermined network point by the principle of proximity in position, and number the public area and the detection areas respectively.

8. The network service supervision system according to claim 7, characterized in that The analysis module further includes: analyzing the service type handled by the network point user according to the vector data set, and obtaining the service handling time through the residence time and the service type; comparing the service handling time with a preset service handling threshold to obtain a second comparison result, and obtaining the service evaluation result of the supervised object according to the second comparison result.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for the computer to execute the method according to any one of claims 1 to 5.

Images