Online resource sorting method, device, electronic device and storage medium

Abstract

The present invention relates to the field of intelligent decision-making, and discloses an online resource sorting method, including: obtaining the online behavior data of online users in business outlets, and calculating the first user anxiety weight value of the online users according to the online behavior data; collecting the offline behavior data of offline users in business outlets, identifying the face images corresponding to the offline behavior data, using a pre-trained face feature recognition model to extract features from the face images to obtain face feature information, and calculating the second user anxiety weight value of the offline users according to the face feature information; sorting the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list; using a skip list algorithm to determine the sorting position of the online users in the user anxiety list. In addition, the present invention also relates to blockchain technology, and the offline behavior data can be stored in the blockchain. The present invention can determine the waiting position of users and improve the efficiency of business handling.

Description

Technical Field

[0001] The present invention relates to the field of intelligent decision-making, and particularly to an online resource sorting method, device, electronic device and computer-readable storage medium. Background Art

[0002] With the continuous development of the Internet, handling business online not only facilitates everyone but also has become a relatively mainstream trend today, such as card application, number reservation, cross-border remittance, and foreign exchange trading, etc. However, for some complex businesses, for the sake of safety and insurance, most users still choose to handle them at business outlets. Currently, at almost all business outlets, one can only get a number in the business hall and wait in line until the number is called by the number calling machine before handling the business. When users handle business at business outlets, due to the inability to accurately grasp the waiting time, it causes a serious waste of users' time. At the same time, it is also impossible to prioritize different user groups according to the actual situation of the business outlet itself and users, resulting in low efficiency of business handling. Summary of the Invention

[0003] The present invention provides an online resource sorting method, device, electronic device and computer-readable storage medium, and its main purpose is to determine the reasonable waiting position of users and improve the efficiency of business handling.

[0004] To achieve the above object, an online resource sorting method provided by the present invention includes:

[0005] Obtain the online behavior data of online users in a business outlet, and calculate the first user anxiety weight value of the online users according to the online behavior data;

[0006] Collect the offline behavior data of offline users in the business outlet, and identify the face image corresponding to the offline behavior data. Use the pre-trained face feature recognition model to extract features from the face image to obtain face feature information, and calculate the second user anxiety weight value of the offline users according to the face feature information;

[0007] Perform weight value sorting on the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list;

[0008] Adopt a skip list algorithm to determine the sorting position of the online users in the user anxiety list.

[0009] Optionally, the obtaining the online behavior data of online users in a business outlet includes:

[0010] Query the name of the business outlet closest to the online user, and based on the name of the business outlet and the terminal device of the online user, collect the online behavior data of the online user in the business outlet.

[0011] Optionally, calculating the first user anxiety weight value of the online user according to the online behavior data includes:

[0012] Calculating the first user anxiety weight value of the online user by using the following method:

[0013]

[0014] where C i represents the first user anxiety weight value, E i represents the characteristic data of the online behavior data, represents the characteristic vector covariance of the characteristic data, and trace() represents the spatial filtering function.

[0015] Optionally, calculating the second user anxiety weight value of the offline user according to the offline behavior data includes:

[0016] Identifying the face image corresponding to the offline behavior data;

[0017] Extracting features from the face image by using a pre-trained face feature recognition model to obtain face feature information;

[0018] Calculating the second user anxiety weight value of the offline user according to the face feature information.

[0019] Optionally, the extracting features from the face image by using a pre-trained face feature recognition model to obtain face feature information includes:

[0020] Calculating the state value of the face image by using the input gate in the face feature recognition model;

[0021] Calculating the activation value of the face image by using the forget gate in the face feature recognition model;

[0022] Calculating the state update value of the face image according to the state value and the activation value;

[0023] Calculating the feature information sequence of the state update value by using the output gate in the face feature recognition model;

[0024] Calculating the loss value between the feature information sequence and the corresponding face image label by using the loss function in the face feature recognition model, and selecting the feature information sequence with the loss value less than the preset threshold to obtain the face feature information.

[0025] Optionally, the calculating the state value of the face image by using the input gate in the face feature recognition model includes:

[0026] Calculate the status value of the face image using the following method:

[0027] i t = θ(w i ·[h t-1 ,x t ) + b i

[0028] where i t represents the status value, θ represents the bias of the cell unit in the input gate, w i represents the activation factor of the input gate, h t-1 represents the peak value of the face image at the input gate at time t-1, x t represents the face image at time t, and b i represents the weight of the cell unit in the input gate.

[0029] Optionally, the skiplist algorithm is used to determine the sorting position of the online user in the user anxiety list, including:

[0030] Use the skiplist algorithm to query the time waiting value corresponding to the second anxiety weight value in the user anxiety list;

[0031] Filter out the second anxiety weight values whose time waiting values are less than the preset time to obtain the range of offline users waiting to jump the queue;

[0032] Determine the sorting position of the online user within the range of offline users waiting to jump the queue.

[0033] To solve the above problems, the present invention also provides an online resource sorting device, which includes:

[0034] A calculation module for obtaining the online behavior data of the online user in the business outlet and calculating the first user anxiety weight value of the online user according to the online behavior data;

[0035] The calculation module is further configured to collect the offline behavior data of the offline user in the business outlet, identify the face image corresponding to the offline behavior data, extract the features of the face image using a pre-trained face feature recognition model to obtain face feature information, and calculate the second user anxiety weight value of the offline user according to the face feature information;

[0036] A sorting module for sorting the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list;

[0037] A determination module for using the skiplist algorithm to determine the sorting position of the online user in the user anxiety list.

[0038] To solve the above problems, the present invention also provides an electronic device, which includes:

[0039] at least one processor; and,

[0040] a memory communicatively connected to the at least one processor; wherein,

[0041] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to implement the above-mentioned online resource sorting method.

[0042] To solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the above-mentioned online resource sorting method.

[0043] In the embodiment of the present invention, first, online behavior data of online users in business outlets is obtained, and according to the online behavior data, a first user anxiety weight value of the online users is calculated. Offline behavior data of offline users in the business outlets is collected, and a face image corresponding to the offline behavior data is identified. A pre-trained face feature recognition model is used to extract features from the face image to obtain face feature information. According to the face feature information, a second user anxiety weight value of the offline users is calculated, and the weight values of the anxiety levels of all online and offline appointment users can be analyzed. Secondly, the embodiment of the present invention sorts the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list, which ensures the rationality of the subsequent user queuing positions. The skip list algorithm is used to determine the sorting position of the online users in the user anxiety list, and the reasonable waiting positions of the users are determined, improving the efficiency of business handling. Therefore, an online resource sorting method, device, electronic device, and storage medium proposed by the present invention can determine the reasonable waiting positions of users and improve the efficiency of business handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flowchart of an online resource sorting method provided by an embodiment of the present invention;

[0045] Figure 2 In the first embodiment of the present invention Figure 1 is a detailed flowchart of one step of the online resource sorting method provided;

[0046] Figure 3 is a module diagram of an online resource sorting device provided by an embodiment of the present invention;

[0047] Figure 4Schematic diagram of the internal structure of an electronic device for implementing an online resource sorting method provided by an embodiment of the present invention;

[0048] The realization, functional features and advantages of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. Detailed implementation manners

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] An embodiment of the present application provides an online resource sorting method. The execution subject of the online resource sorting method includes but is not limited to at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the online resource sorting method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0051] Refer to Figure 1 As shown, it is a flowchart of an online resource sorting method provided by an embodiment of the present invention. In the embodiment of the present invention, the online resource sorting method includes:

[0052] S1. Obtain the online behavior data of an online user in a business outlet, and calculate the first user anxiety weight value of the online user according to the online behavior data.

[0053] In the embodiment of the present invention, the business outlet includes a bank outlet. The online behavior data refers to the click data of the user in the app of the business outlet, including: the number of views, the queuing number information, and the browsing time, etc.

[0054] Specifically, in the embodiment of the present invention, the obtaining of the online behavior data of the online user in the business outlet includes: querying the name of the business outlet closest to the online user, and based on the name of the business outlet, collecting the online behavior data of the online user in the business outlet on the terminal device of the online user.

[0055] In an alternative embodiment, the name of the business outlet closest to the online user is queried through a currently known map software, and the terminal device includes: a mobile phone or a tablet.

[0056] Exemplarily, online user A needs to handle a loan business at Ping An Bank. The name of the business outlet of Ping An Bank closest to online user A is queried as the Luohu Branch of Ping An Bank. Then, through the mobile phone of online user A, the online behavior data is collected by selecting the Luohu Branch of Ping An Bank on the app of Ping An Bank.

[0057] Further, since the anxiety levels of different users during business processing are inconsistent, in order to better assist users in business processing, the embodiments of the present invention calculate the first user anxiety weight value of the online users based on the online behavior data to identify the anxiety level of the users' business processing, so as to provide better service to the users.

[0058] In one optional embodiment of the present invention, the following method is used to calculate the first user anxiety weight value of the online users:

[0059]

[0060] Wherein, C i represents the first user anxiety weight value, E i represents the characteristic data of the online behavior data, represents the characteristic vector covariance of the characteristic data, and trace() represents the spatial filtering function.

[0061] Further, the characteristic data is determined based on the online users. For example, in the application scenario of online number taking, after the online users perform the online number taking operation, a pop-up window is used to prompt the users to select the anxiety weight value for business processing, and the selected anxiety weight value by the users is the characteristic data. Among them, the anxiety weight value can be represented by the numbers 1-10 (there are five stars, and each star represents 2). The smaller the number, the lower the anxiety level; on the contrary, the higher the anxiety level of the users' business processing.

[0062] S2. Collect the offline behavior data of the offline users in the business outlet, identify the face image corresponding to the offline behavior data, use the pre-trained face feature recognition model to extract features from the face image to obtain face feature information, and calculate the second user anxiety weight value of the offline users according to the face feature information.

[0063] In a preferred embodiment of the present invention, the offline behavior data includes: expression data and body data. Optionally, the offline behavior data is captured by the camera in the business outlet. Further, the embodiments of the present invention screen out the face image from the offline behavior data captured by the camera, and use the pre-trained face feature recognition model to extract features from the face image to obtain face feature information.

[0064] Further, in the embodiments of the present invention, before performing feature extraction on the face image, it further includes: performing a preprocessing operation on the face image to improve the quality of the face image, eliminate noise, and unify the image grayscale value and size. Specifically, the preprocessing operation includes: performing a grayscale conversion operation on the face image through various ratio methods to obtain a grayscale face image; using Gaussian filtering to denoise the grayscale face image; using median filtering to eliminate isolated noise points from the denoised grayscale face image, and using a contrast enhancement method to enhance the contrast of the grayscale face image after eliminating isolated noise points; performing a thresholding operation on the contrast-enhanced grayscale face image according to the OTSU algorithm.

[0065] Further, the face feature recognition model includes: a Long Short-Term Memory (LSTM) model. The face feature recognition model is a type of time-recurrent neural network and includes: an input gate, a forget gate, and an output gate.

[0066] Among them, in the present invention, the face feature recognition model is used to identify the face feature sequence of the face image to identify face feature information, so as to help the user better judge the distribution of feature information in the face image.

[0067] Specifically, using the pre-trained face feature recognition model to perform feature extraction on the face image to obtain face feature information includes: using the input gate to calculate the state value of the face image; using the forget gate to calculate the activation value of the face image; calculating the state update value of the face image according to the state value and the activation value; using the output gate to calculate the feature information sequence of the state update value; using the loss function in the face feature recognition model to calculate the loss value between the feature information sequence and the corresponding face image label, and selecting the feature information sequence with a loss value less than a preset threshold to obtain face feature information.

[0068] In an alternative embodiment, the calculation method of the state value includes:

[0069] i t = θ(w i ·[h t-1 , x t ) + b i

[0070] where i t represents the state value, θ represents the bias of the cell unit in the input gate, w i represents the activation factor of the input gate, h t-1 represents the peak value of the face image at the (t - 1)th moment of the input gate, x t represents the face image at the tth moment, bi Represents the weight of the cell unit in the input gate.

[0071] In an optional embodiment, the calculation method of the activation value includes:

[0072]

[0073] where f t represents the activation value, θ represents the bias of the cell unit in the forget gate, w f represents the activation factor of the forget gate, represents the peak value of the face image at the (t - 1)th moment in the forget gate, x t represents the face image input at the tth moment, b f represents the weight of the cell unit in the forget gate.

[0074] In an optional embodiment, the calculation method of the state update value includes:

[0075]

[0076] where c t represents the state update value, h t-1 represents the peak value of the face image at the (t - 1)th moment in the input gate, represents the peak value of the face image at the (t - 1)th moment in the forget gate.

[0077] In an optional embodiment, the calculation method of the feature information sequence includes:

[0078] o t = tanh(c t )

[0079] where o t represents the feature information sequence, tanh represents the activation function of the output gate, c t represents the state update value.

[0080] In an optional embodiment of the present invention, the loss function is the softmax function, where the face image label refers to the feature information sequence marked by the user in the face image in advance. Further, in the present invention, the feature information sequence with a loss value less than a preset threshold is selected as the feature information sequence to screen out the feature information in the face image.

[0081] Further, the embodiment of the present invention calculates the second user anxiety weight value of the offline user according to the face feature information to identify the anxiety degree of the user's business handling.

[0082] In one optional embodiment of the present invention, the second user anxiety weight value of the offline user is calculated by the following method:

[0083]

[0084] Among them, C t represents the anxiety weight value of the second user, and E t represents the face feature information. represents the feature vector covariance of the face feature information, and trace() represents the spatial filtering function.

[0085] Exemplarily, when the offline user handles business at the business outlet, the behavior data of the offline user queuing in the number-taking and waiting areas is captured through the camera of the business outlet, and the corresponding face image is identified. The face feature recognition model is used to identify the feature information of the face image. For example, the user keeps looking up at the call display, keeps consulting the staff, has a relatively anxious expression, and plays with the mobile phone with the head down many times. According to the feature information, the corresponding user anxiety weight value is calculated.

[0086] Further, to ensure the reusability of the offline behavior data, the offline behavior data can also be stored in a blockchain node.

[0087] S3. Sort the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list.

[0088] Since the first user anxiety weight value and the second user anxiety weight value represent the anxiety levels of the corresponding users when handling business, in order to more intuitively understand the anxiety levels of users in handling business, in the embodiments of the present invention, the small top heap algorithm is used to sort the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list.

[0089] The idea of the small top heap algorithm is to traverse from the first child node, compare it with its parent node, and if it is larger than the parent node, float up to the parent node. At this time, the parent node continues to float until the root node. In the present invention, the first user anxiety weight value is used as the first child node, and traversal starts from the second user anxiety weight value. If the first user anxiety weight value is larger than the traversed second user anxiety weight value, the first user anxiety weight value is ranked before the second user anxiety weight value until the traversal of the second user anxiety weight value ends.

[0090] S4. Use the skip list algorithm to determine the sorting position of the online user in the user anxiety list.

[0091] In the embodiments of the present invention, if the waiting position of an online user is directly arranged before the corresponding offline user position according to the sorting order in the user anxiety list, it is very easy to cause chaos in business handling. For example, during the waiting process for business handling after taking a number at the bank, the initial number of an online user is 26, the anxiety weight value of this online user is calculated to be 9.2, and the anxiety weight values of offline waiting users are all less than 9.2. If the waiting position of this online user is directly arranged in the first place, it is very easy to cause dissatisfaction among other offline waiting users, resulting in business chaos. Therefore, in the embodiments of the present invention, by adopting the skip list algorithm, the sorting position of the online user in the user anxiety list is determined, which not only realizes business rationality but also well meets the needs of anxious users.

[0092] Specifically, referring to Figure 2 as shown, the method of adopting the skip list algorithm to determine the sorting position of the online user in the user anxiety list includes:

[0093] S20. Use the skip list algorithm to query the time waiting value corresponding to the second anxiety weight value in the user anxiety list;

[0094] S21. Screen out the second anxiety weight values whose time waiting values are less than the preset time to obtain the range of offline users to be cut in line;

[0095] S22. Determine the sorting position of the online user within the range of offline users to be cut in line.

[0096] Among them, the time waiting value is queried through the select query statement in the skip list algorithm, and the preset time is half an hour.

[0097] The step S22 includes: obtaining the first anxiety weight value of the online user and the second anxiety weight values of the offline users within the range of offline users, and arranging the sorting positions of the online users whose first anxiety weight values are greater than the second anxiety weight values before the corresponding offline users.

[0098] Furthermore, it should be stated that the present invention does not insert the sorting position of the online user before the top three offline users in the user anxiety list to avoid dissatisfaction among users in the front positions in the actual business scenario.

[0099] In an embodiment of the present invention, first, online behavior data of an online user in a business outlet is obtained. According to the online behavior data, a first user anxiety weight value of the online user is calculated. Offline behavior data of an offline user in the business outlet is collected, and a face image corresponding to the offline behavior data is identified. A pre-trained face feature recognition model is used to extract features from the face image to obtain face feature information. According to the face feature information, a second user anxiety weight value of the offline user is calculated, and the weight values of the anxiety levels of all users with online and offline appointments can be analyzed. Secondly, in the embodiment of the present invention, the first user anxiety weight value and the second user anxiety weight value are sorted by weight value to obtain a user anxiety ranking list, which ensures the rationality of the subsequent user queuing positions. The skip list algorithm is used to determine the sorting position of the online user in the user anxiety list, determining the reasonable waiting position of the user and improving the efficiency of business processing. Therefore, the present invention can determine the reasonable waiting position of the user and improve the efficiency of business processing.

[0100] As Figure 3 shown, it is a functional module diagram of the online resource sorting device of the present invention.

[0101] The online resource sorting device 100 of the present invention can be installed in an electronic device. According to the functions achieved, the online resource sorting device may include a calculation module 101, a sorting module 102, and a determination module 103. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0102] In this embodiment, the functions of each module / unit are as follows:

[0103] The calculation module 101 is configured to obtain online behavior data of an online user in a business outlet, and calculate a first user anxiety weight value of the online user according to the online behavior data;

[0104] The calculation module 101 is further configured to collect offline behavior data of an offline user in the business outlet, identify a face image corresponding to the offline behavior data, use a pre-trained face feature recognition model to extract features from the face image to obtain face feature information, and calculate a second user anxiety weight value of the offline user according to the face feature information;

[0105] The sorting module 102 is configured to sort the first user anxiety weight value and the second user anxiety weight value by weight value to obtain a user anxiety ranking list;

[0106] The determining module 103 is configured to determine the sorting position of the online user in the user anxiety list by using a skip list algorithm.

[0107] Specifically, each module in the online resource sorting device 100 in the embodiments of the present invention uses the same technical means as the Figure 1 and Figure 2 online resource sorting method described in, and can produce the same technical effects, which will not be elaborated here.

[0108] As Figure 4 shown, it is a schematic structural diagram of an electronic device for implementing the online resource sorting method of the present invention.

[0109] The electronic device 1 may include a processor 10, a memory 11, and a bus, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as an online resource sorting program 12.

[0110] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used not only to store application software installed in the electronic device 1 and various types of data, such as the code of the online resource sorting program, but also to temporarily store data that has been output or will be output.

[0111] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and circuits. By running or executing programs or modules stored in the memory 11 (such as executing an online resource sorting program, etc.), and by calling data stored in the memory 11, it performs various functions of the electronic device 1 and processes data.

[0112] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable connection and communication between the memory 11 and at least one processor 10, etc.

[0113] Figure 4 Only the electronic device with components is shown. Those skilled in the art can understand that, Figure 4 The shown structure does not constitute a limitation on the electronic device 1. It may include fewer or more components than shown, or combine certain components, or have a different component layout.

[0114] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0115] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0116] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0117] It should be understood that the above embodiments are only for illustration purposes and are not limited by this structure in the scope of the patent application.

[0118] The online resource sorting program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can implement:

[0119] Obtain the online behavior data of online users in business outlets, and calculate the first user anxiety weight value of the online users according to the online behavior data;

[0120] Collect the offline behavior data of offline users in the business outlets, identify the face image corresponding to the offline behavior data, extract features from the face image using a pre-trained face feature recognition model to obtain face feature information, and calculate the second user anxiety weight value of the offline users according to the face feature information;

[0121] Sort the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorted list;

[0122] Use the skip list algorithm to determine the sorting position of the online users in the user anxiety list.

[0123] Specifically, the specific implementation method of the above instructions by the processor 10 can refer to Figure 1 the description of the relevant steps in the corresponding embodiments, which will not be elaborated here.

[0124] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0125] The present invention also provides a computer-readable storage medium storing a computer program, which when executed by a processor of an electronic device, can implement:

[0126] Obtain the online behavior data of online users in a business outlet, and calculate the first user anxiety weight value of the online users according to the online behavior data;

[0127] Collect the offline behavior data of offline users in the business outlet, identify the face image corresponding to the offline behavior data, extract features from the face image using a pre-trained face feature recognition model to obtain face feature information, and calculate the second user anxiety weight value of the offline users according to the face feature information;

[0128] Sort the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorted list;

[0129] Use the skip list algorithm to determine the sorting position of the online users in the user anxiety list.

[0130] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation.

[0131] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, in each embodiment of the present invention, each functional module can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0133] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0134] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be construed as limiting the claimed invention.

[0135] The blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms. Blockchain, essentially a decentralized database, is a string of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, an application service layer, etc.

[0136] In addition, obviously, the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. Words such as "second" are used to denote names and do not denote any particular order.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An online resource sorting method, characterized in that, The method includes: Obtain the online behavior data of online users in business outlets, and calculate the first user anxiety weight value of the online users according to the online behavior data; Collect the offline behavior data of offline users in the business outlets, identify the face images corresponding to the offline behavior data, extract features from the face images using a pre-trained face feature recognition model to obtain face feature information, and calculate the second user anxiety weight value of the offline users according to the face feature information; Sort the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorted list; Use the skip list algorithm to query the time waiting value corresponding to the second anxiety weight value in the user anxiety list, filter out the second anxiety weight value whose time waiting value is less than the preset time to obtain the range of offline users to be cut in line, obtain the first anxiety weight value of the online users and the second anxiety weight values of the offline users in the range of offline users to be cut in line, and arrange the sorting positions of the online users whose first anxiety weight value is greater than the second anxiety weight value in front of the corresponding offline users.

2. The online resource sorting method according to claim 1, wherein The obtaining of the online behavior data of online users in business outlets includes: Query the name of the business outlet closest to the online user, and based on the name of the business outlet and the terminal device of the online user, collect the online behavior data of the online user in the business outlet.

3. The online resource sorting method according to claim 1, characterized in that The calculating of the first user anxiety weight value of the online users according to the online behavior data includes: Calculate the first user anxiety weight value of the online users using the following method: Among them, C i represents the anxiety weight value of the first user, and E i represents the characteristic data of the online behavior data, represents the covariance of the eigenvectors of the characteristic data, and trace() represents the spatial filtering function.

4. The online resource sorting method according to claim 1, wherein, Before extracting features from the face image using the pre-trained face feature recognition model, it further includes: Perform a grayscale conversion operation on the face image to obtain a grayscale face image; Denoise the grayscale face image, eliminate isolated noise points from the denoised grayscale face image, and enhance the contrast of the grayscale face image after eliminating isolated noise points; Perform a thresholding operation on the grayscale face image after contrast enhancement.

5. The online resource sorting method according to claim 4, wherein The extracting of features from the face image using the pre-trained face feature recognition model to obtain face feature information includes: Calculate the state value of the face image using the input gate in the face feature recognition model; Calculate the activation value of the face image using the forget gate in the face feature recognition model; Calculate the state update value of the face image according to the state value and the activation value; Calculate the feature information sequence of the state update value using the output gate in the face feature recognition model; Calculate the loss value between the feature information sequence and the corresponding face image label using the loss function in the face feature recognition model, and select the feature information sequence whose loss value is less than the preset threshold to obtain face feature information.

6. The online resource sorting method according to claim 5, wherein The calculating of the state value of the face image using the input gate in the face feature recognition model includes: Calculate the state value of the face image using the following method: where, i t represents the state value, represents the bias of the cell unit in the input gate, w i represents the activation factor of the input gate, h t-1 represents the peak value of the face image at the (t - 1)th moment of the input gate, x t represents the face image at the tth moment, b i represents the weight of the cell unit in the input gate.

7. An online resource sorting device, characterized in that, The device includes: A calculation module, configured to obtain online behavior data of an online user in a business outlet, and calculate a first user anxiety weight value of the online user according to the online behavior data; The calculation module is further configured to collect offline behavior data of an offline user in the business outlet, identify a face image corresponding to the offline behavior data, perform feature extraction on the face image by using a pre-trained face feature recognition model to obtain face feature information, and calculate a second user anxiety weight value of the offline user according to the face feature information; A sorting module, configured to perform weight value sorting on the first user anxiety weight value and the second user anxiety weight value to obtain a user anxiety sorting list; A determination module, configured to use a skip list algorithm to query a time waiting value corresponding to a second anxiety weight value in the user anxiety list, filter out the second anxiety weight value whose time waiting value is less than a preset time to obtain a range of offline users to be jump-cut, obtain the first anxiety weight value of the online user and the second anxiety weight values of the offline users in the range of offline users to be jump-cut, and arrange the sorting position of the online user whose first anxiety weight value is greater than the second anxiety weight value before the corresponding offline user.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the online resource sorting method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the online resource sorting method according to any one of claims 1 to 6.

Images