Method and device for processing a buried point, computer device and storage medium

Abstract

The embodiment of the application belongs to the field of artificial intelligence and the field of financial technology, and relates to a method for processing a buried point, comprising the following steps: obtaining identity information of each customer service personnel; obtaining feature information of each customer service personnel based on the identity information and a feature type; performing analysis on the feature information based on a clustering algorithm to perform grouping processing on each customer service personnel, and obtaining a plurality of target groups; performing random selection on the customer service personnel in each target group based on a random selection rule to obtain target customer service personnel; and performing buried point processing on behavior data of the target customer service personnel in a business system. The application also provides a device for processing a buried point, computer equipment and a storage medium. In addition, the application also relates to blockchain technology, and the feature information can be stored in a blockchain. The application can be applied to a scene of processing a buried point of customer service behavior data in the financial field, and can effectively reduce the sample quantity of buried point sampling and improve the processing efficiency of processing a buried point of the customer service personnel.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence development and the field of financial technology, and in particular relates to a method and device for processing a point, a computer device and a storage medium. BACKGROUND

[0002] In the business management of a financial technology company, it is often necessary to analyze the state of the use of an operation business system by the agents within the financial technology company, and the current method is to use a point embedding method on the browser end of the agents to obtain the corresponding point embedding data. The existing point embedding strategy for agents usually uses a full point embedding method to perform point embedding processing, that is, all links of all agents are embedded. However, this full point embedding method requires a large amount of storage resources, has low processing efficiency, and will also result in a large amount of storage costs. SUMMARY

[0003] The embodiments of the present application aim to provide a point embedding processing method, device, computer device and storage medium to solve the technical problem that the existing full point embedding method requires a large amount of storage resources, has low processing efficiency, and will also result in a large amount of storage costs.

[0004] To solve the above technical problems, the embodiments of the present application provide a point embedding processing method, which adopts the following technical solutions:

[0005] Obtain identity information of each agent in all agents;

[0006] Obtain feature information of each agent based on the identity information and a preset feature type;

[0007] Analyze the feature information based on a preset clustering algorithm, and perform grouping processing on each agent according to the obtained analysis result to obtain a plurality of target groups corresponding thereto;

[0008] Randomly select agents in each target group based on a preset random selection rule to obtain target agents corresponding thereto; wherein the target agents include at least one agent in each target group;

[0009] Perform point embedding processing on behavior data of the target agents in the business system.

[0010] Further, the step of randomly selecting agents in each target group based on a preset random selection rule to obtain target agents corresponding thereto specifically includes:

[0011] obtaining a specified classification result of a specified group; wherein the specified group is any one of all the target groups;

[0012] obtaining the agent information of each agent included in the specified group;

[0013] constructing a mapping relationship between the agent information of each agent included in the specified group and the specified classification result;

[0014] storing the mapping relationship in a preset classification mapping table;

[0015] selecting at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table based on a preset random strategy;

[0016] selecting at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table based on a preset random strategy;

[0017] Further, the step of selecting at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table based on a preset random strategy specifically comprises:

[0018] obtaining a plurality of preset random algorithms;

[0019] determining a target random algorithm from all the random algorithms;

[0020] selecting at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table based on the target random algorithm.

[0021] Further, after the step of selecting at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table based on a preset random strategy, it further comprises:

[0022] obtaining the specified agent information of the specified agent;

[0023] obtaining a preset initial data table;

[0024] storing the specified agent information in the initial data table to obtain a hit mapping table;

[0025] storing the hit mapping table.

[0026] Further, after the step of storing the hit mapping table, it further comprises:

[0027] obtaining the current time;

[0028] determining whether the current time meets a preset timeout condition.

[0029] If so, the classification mapping table is processed by the target random algorithm to filter the seats and obtain the corresponding specific seat information;

[0030] The hit mapping table is updated based on the specific agent information.

[0031] Furthermore, the step of obtaining the feature information of each of the agents based on the identity information and the preset feature types specifically includes:

[0032] Call the preset information database;

[0033] Based on the identity information, the personnel information of each of the seated personnel is obtained from the information database;

[0034] Based on the feature type, feature information corresponding to the feature type is filtered out from the personnel information of each of the seated personnel.

[0035] Furthermore, after the step of embedding data on the target agent's behavior data in the business system, the method further includes:

[0036] Obtain the target business links accessed by each of the target agents in the business system;

[0037] Determine the storage method for the target service link;

[0038] The target business link is stored based on the storage method described above.

[0039] To address the aforementioned technical problems, this application also provides a data embedding processing device, which employs the following technical solution:

[0040] The first acquisition module is used to acquire the identity information of each agent among all the agents;

[0041] The second acquisition module is used to acquire the feature information of each of the agents based on the identity information and the preset feature types.

[0042] The analysis module is used to analyze the feature information based on a preset clustering algorithm, and to group each of the agents according to the analysis results to obtain multiple target groups.

[0043] The selection module is used to randomly select agents from each of the target groups based on a preset random selection rule to obtain corresponding target agents; wherein, the target agents include at least one agent from each of the target groups;

[0044] A processing module is configured to perform a behavior data burying point processing on the target agent in a business system.

[0045] To solve the above technical problems, the embodiment of the application further provides a computer device, which adopts the technical scheme as follows:

[0046] Obtain identity information of each agent in all agents;

[0047] Obtain feature information of each agent based on the identity information and a preset feature type;

[0048] Perform an analysis on the feature information based on a preset clustering algorithm, and perform a grouping processing on each agent according to an analysis result obtained, to obtain a plurality of target groups corresponding thereto;

[0049] Randomly select agents in each target group based on a preset random selection rule, to obtain a target agent corresponding thereto; wherein the target agent includes at least one agent in each target group;

[0050] Perform a behavior data burying point processing on the target agent in a business system.

[0051] To solve the above technical problems, the embodiment of the application further provides a computer readable storage medium, which adopts the technical scheme as follows:

[0052] Obtain identity information of each agent in all agents;

[0053] Obtain feature information of each agent based on the identity information and a preset feature type;

[0054] Perform an analysis on the feature information based on a preset clustering algorithm, and perform a grouping processing on each agent according to an analysis result obtained, to obtain a plurality of target groups corresponding thereto;

[0055] Randomly select agents in each target group based on a preset random selection rule, to obtain a target agent corresponding thereto; wherein the target agent includes at least one agent in each target group;

[0056] Perform a behavior data burying point processing on the target agent in a business system.

[0057] Compared with the prior art, the embodiment of the application has the following beneficial effects:

[0058] This application first obtains the identity information of each agent among all agents; then, based on the identity information and preset feature types, it obtains the feature information of each agent; next, it analyzes the feature information based on a preset clustering algorithm, and groups the agents according to the analysis results to obtain multiple target groups; subsequently, it randomly selects agents from each target group based on preset random selection rules to obtain the corresponding target agents; finally, it performs data tracking on the behavioral data of the target agents in the business system. This application uses a clustering algorithm to perform cluster analysis on the feature information of agents, thereby quickly completing the grouping of all agents. Then, it randomly selects agents from the groups based on random selection rules to determine the target agents. Therefore, subsequent data tracking only needs to be performed on the behavioral data of the target agents in the business system to meet the requirements for data tracking analysis of the business system. This application effectively reduces the number of samples for data tracking, thus avoiding the unreasonable production and efficiency problems caused by excessive storage of data tracking, and improving the processing efficiency and intelligence of data tracking for agents. In addition, the use of random strategies helps to avoid survivor bias in the selection of agents and allows the selected agent data to reflect the overall situation of agents, effectively improving the intelligence of target agent determination and the randomness of selection. Attached Figure Description

[0059] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0061] Figure 2 A flowchart of an embodiment of the embedding point processing method according to this application;

[0062] Figure 3 This is a schematic diagram of a structure of an embodiment of the embedding point processing device according to this application;

[0063] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application; the use herein of terms such as "comprise", "comprising", "comprises", "including", "includes" or "have" or "has" are to be construed in an open, non-exclusive way, in the sense that they do not exclude further elements or steps; the use herein of terms such as "first", "second" and the like do not denote any order, quantity, combination or arrangement, but are used to distinguish one element from another.

[0065] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiments, or alternative or alternative embodiments.

[0066] In order to make the technical personnel in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings.

[0067] As shown in Figure 1 The system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a communication link medium between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0068] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0069] The terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, and desktop computers, etc.

[0070] The server 105 can be a server providing various services, for example, a background server providing support for a page displayed on the terminal device 101, 102, 103.

[0071] It should be noted that the method for processing a buried point provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the device for processing a buried point is generally arranged in a server / terminal device.

[0072] It should be understood that Figure 1 The number of terminal devices, networks and servers in

[0073] With reference to Figure 2 , a flow chart of one embodiment of the method for processing a buried point according to the present application is shown. The order of the steps in the flow chart can be changed, and some steps can be omitted, according to different requirements. The method for processing a buried point provided in the embodiments of the present application can be applied to any scenario requiring processing of a buried point, and thus the method can be applied to products in these scenarios, for example, a scenario of processing of data of behavior of a seat in the financial field. The method for processing a buried point includes the following steps:

[0074] Step S201: identity information of each seat in all seats is acquired.

[0075] In the present embodiment, the electronic device (for example, the server / terminal device shown in Figure 1 The identity information of the seat can be acquired by a wired connection or a wireless connection. It should be noted that the wireless connection can include, but is not limited to, 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other now known or future developed wireless connection methods. The identity information can refer to name information or UM information of the seat.

[0076] Step S202: feature information of each seat is acquired based on the identity information and a preset feature type.

[0077] In the embodiment, the identity information can include name information or UM information. The feature types include at least area of the agent, center of the agent, organization of the agent, team of the agent, position of the agent, role of the agent, hardware device information (computer, mobile phone) used by the agent, date of employment, performance profile information, and the like. The specific implementation process of obtaining the feature information of each agent based on the identity information and the preset feature types will be further described in detail in subsequent specific embodiments, and will not be described in detail here.

[0078] In step S203, the feature information is analyzed based on a preset clustering algorithm, and each agent is grouped based on the analysis result to obtain a plurality of target groups.

[0079] In the embodiment, the clustering algorithm can specifically be a K-MEANS clustering algorithm, also known as a k-means clustering algorithm. The k-means clustering algorithm is an iterative solution clustering analysis algorithm. The steps are as follows: the data is divided into K groups, K objects are randomly selected as initial cluster centers, the distance between each object and each seed cluster center is calculated, and each object is assigned to the cluster center closest to it. The cluster centers and the objects assigned to them represent a cluster. The cluster centers of the cluster are recalculated according to the existing objects in the cluster after each sample is assigned. This process will be repeated until a certain termination condition is met. The termination condition can be that no (or a minimum number of) objects are reassigned to different clusters, no (or a minimum number of) cluster centers change, the error sum of squares is locally minimized. By using unsupervised learning to automatically classify agents, it is beneficial to subsequently select representative agents from all agents more efficiently.

[0080] In step S204, the agents in each target group are randomly selected based on a preset random selection rule to obtain corresponding target agents. The target agents include at least one agent in each target group.

[0081] In the embodiment, the target agent corresponding to the to-be-analyzed data can represent the state and experience of the agent using the business. The specific implementation process of randomly selecting the agents in each target group based on the preset random selection rule to obtain the target agents will be further described in detail in subsequent specific embodiments, and will not be described in detail here.

[0082] In step S205, the behavior data of the target agent in the business system is subjected to a point embedding process.

[0083] In the embodiment, the behavior data of the target agent in the business system can be tracked based on the preset use of the tracking function component, i.e., tracking all business links of the target agent in the business system.

[0084] The application first acquires the identity information of each agent in all agents; then acquires the feature information of each agent based on the identity information and a preset feature type; then analyzes the feature information based on a preset clustering algorithm and groups each agent according to the analysis result to obtain a plurality of target groups; subsequently randomly selects an agent in each target group based on a preset random selection rule to obtain a target agent; and finally tracks the behavior data of the target agent in the business system. The application can quickly group all agents by using the clustering algorithm to analyze the feature information of the agents, and then randomly selects an agent in the group based on the random selection rule to determine the target agent, so that subsequent tracking of the behavior data of the target agent in the business system can meet the demand for tracking analysis of the business system. The application can effectively reduce the sample size of tracking sampling, thereby avoiding the problem of unreasonable production caused by excessive storage of tracking data, and improving the processing efficiency and intelligence of tracking of agents. In addition, the use of the random strategy can help avoid survivor bias in agent selection and enable the selected part of the agent data to reflect the overall agent situation, effectively improving the determination intelligence and selection randomness of the target agent.

[0085] In some optional implementations, step S204 includes the following steps:

[0086] Acquire a specified classification result of a specified group.

[0087] In the embodiment, the specified group is any one of all the target groups.

[0088] Acquire agent information of each agent included in the specified group.

[0089] In the embodiment, the agent information can include the name information or UM information of the agent.

[0090] Construct a mapping relationship between the agent information of each agent included in the specified group and the specified classification result.

[0091] Store the mapping relationship in a preset classification mapping table.

[0092] In the embodiment, storing the mapping relationship into the preset classification mapping table means storing the agent information of each agent and the specified classification result corresponding to the agent information into the classification mapping table based on the mapping relationship. The storage can be performed in a key-value storage mode. The key is a classification, and the value is a set of agent information.

[0093] Filtering, based on a preset random strategy, at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table.

[0094] In the embodiment, the specific implementation process of filtering, based on a preset random strategy, at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table will be further described in detail in subsequent embodiments, and will not be described here in detail. The application associates and stores the target group based on the classification mapping table, and then randomly selects the stored data in the classification mapping table based on the use of the random strategy. The specified agent information of the specified agent corresponding to each classification result can be quickly and accurately selected, so as to determine the target agent. The use of the random strategy is beneficial to avoid survivor bias in agent selection, and can make the selected part of the agent data reflect the overall agent situation, effectively improving the determination intelligence and selection randomness of the target agent.

[0095] The specified agent corresponding to the specified agent information is taken as the target agent.

[0096] The application obtains the specified classification result of the specified group and the agent information of each agent included in the specified group. Then, a mapping relationship between the agent information of each agent included in the specified group and the specified classification result is constructed, and the mapping relationship is stored in a preset classification mapping table. Then, at least one specified agent information of a specified agent corresponding to each classification result is filtered from the classification mapping table based on a preset random strategy. Subsequently, the specified agent corresponding to the specified agent information is taken as the target agent.

[0097] In some optional implementations of the embodiment, filtering, based on a preset random strategy, at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table comprises the following steps:

[0098] Obtaining a plurality of preset random algorithms.

[0099] In the embodiment, the random algorithm can include a numerical probability algorithm, a Monte Carlo algorithm, a Las Vegas algorithm, a Shewood algorithm, etc.

[0100] A target random algorithm is determined from all the random algorithms.

[0101] In the embodiment, the determination manner of the target random algorithm is not limited, for example, one algorithm can be randomly selected from all the random algorithms as the target random algorithm, or an algorithm with the highest processing evaluation value can be selected from all the random algorithms as the target random algorithm. The processing evaluation value is obtained by weighted summation of processing efficiency, processing accuracy and processing satisfaction of the random algorithm.

[0102] Based on the target random algorithm, at least one designated seat information of a designated seat personnel corresponding to each classification result is selected from the classification mapping table.

[0103] The application obtains a plurality of preset random algorithms, determines a target random algorithm from all the random algorithms, and subsequently selects at least one designated seat information of a designated seat personnel corresponding to each classification result from the classification mapping table based on the target random algorithm. Based on the use of the target random algorithm, the designated seat information of the designated seat personnel corresponding to each classification result can be quickly and intelligently selected from the classification mapping table, which helps to avoid survivor bias in seat selection and enables the selected part of the seat data to reflect the overall situation of the seats, thereby effectively improving the intelligence and data randomness of the designated seat information.

[0104] In some optional implementations, after the step of selecting at least one designated seat information of a designated seat personnel corresponding to each classification result from the classification mapping table based on the preset random strategy, the electronic device can further perform the following steps:

[0105] Obtaining the designated seat information of the designated seat.

[0106] Obtaining a preset initial data table.

[0107] In the embodiment, the initial data table can be a data table for storing seat information constructed in advance.

[0108] Storing the designated seat information into the initial data table to obtain a hit mapping table.

[0109] In the embodiment, the specified agent information and the corresponding classification result can be stored in the initial data table in the storage mode of key-value to generate the hit mapping table. The key is the classification, and the value is the agent information.

[0110] The hit mapping table is stored.

[0111] In the embodiment, the storage mode of the hit mapping table is not limited, for example, the local database storage, cloud storage, blockchain storage and the like can be used.

[0112] The application obtains the specified agent information of the specified agent, then obtains a preset initial data table, then stores the specified agent information in the initial data table to obtain a hit mapping table, and then stores the hit mapping table. The application generates a hit mapping table based on the obtained specified agent information of the specified agent, which is beneficial to subsequent point embedding processing of the agent corresponding to the agent information stored in the hit mapping table, thereby effectively reducing the number of point embedding agents, avoiding the problem of unreasonable production caused by the occupation of too much storage of point embedding data, and improving the intelligence of point embedding processing of the agent personnel.

[0113] In some optional implementation manners, after the step of storing the hit mapping table, the electronic device can further perform the following steps:

[0114] Obtain the current time.

[0115] Determine whether the current time meets a preset timeout condition.

[0116] In the embodiment, the timeout condition refers to that the difference between the current time and the last update time of the hit mapping table is less than a preset threshold, and the value of the preset threshold is not limited and can be set according to actual use requirements.

[0117] If yes, perform agent screening processing on the classification mapping table based on the target random algorithm to obtain corresponding specific agent information.

[0118] In the embodiment, the processing process of performing agent screening processing on the classification mapping table based on the target random algorithm can refer to the processing process of screening at least one specified agent information of a specified agent corresponding to various classification results from the classification mapping table based on the target random algorithm, which will not be described in detail here.

[0119] Update the hit mapping table based on the specific agent information.

[0120] In the embodiment, the data in the hit mapping table can be deleted first, and then the specific agent information is filled into the hit mapping table to complete the data update of the hit mapping table.

[0121] The application obtains the current time, and then judges whether the current time meets the preset timeout time condition. If yes, the target random algorithm is used to perform agent screening processing on the classification mapping table to obtain corresponding specific agent information. Subsequently, the hit mapping table is updated based on the specific agent information. The application analyzes the current time based on the use of the timeout time condition to intelligently update the hit mapping table, ensuring the randomness and timeliness of the data in the hit mapping table, and facilitating the improvement of the intelligence of the agent personnel burying point processing.

[0122] In some optional implementation manners of the embodiment, step S202 includes the following steps:

[0123] A preset information database is called.

[0124] In the embodiment, the information database is a database pre-constructed to store personnel information of each agent.

[0125] Based on the identity information, personnel information of each agent is obtained from the information database.

[0126] In the embodiment, the personnel information of each agent corresponding to the identity information can be queried from the information database.

[0127] Based on the feature type, feature information corresponding to the feature type is screened from the personnel information of each agent.

[0128] In the embodiment, the feature type at least includes the region of the agent, the center of the agent, the organization of the agent, the team of the agent, the position of the agent, the role of the agent, the hardware device information (computer, mobile phone) used by the agent, the date of employment, the performance portrait information, and the like.

[0129] The application calls a preset information database, and then obtains personnel information of each agent from the information database based on the identity information. Subsequently, feature information corresponding to the feature type is screened from the personnel information of each agent based on the feature type. The application queries the information database based on the identity information and the feature type, and can quickly and accurately query the required feature information from the information database, thereby improving the efficiency of obtaining the feature information of the agent.

[0130] In some optional implementations of this embodiment, after step S205, the electronic device may further perform the following steps:

[0131] Obtain the target business links accessed by each of the target agents in the business system.

[0132] In this embodiment, the target business links accessed by each target agent in the business system can be extracted from the data obtained by acquiring the data generated by each target agent in the business system.

[0133] Determine the storage method for the target service link.

[0134] In this embodiment, no specific limitation is made to the above storage method. For example, local database storage, cloud storage, blockchain storage, etc. can be used.

[0135] The target business link is stored based on the storage method described above.

[0136] This application obtains the target business links accessed by each target agent in the business system; then determines the storage method of the target business links; and subsequently stores the target business links based on the storage method. By obtaining and storing the target business links accessed by each target agent in the business system, this application facilitates intelligent analysis and processing of agent usage status and experience based on the target business links, thereby improving the processing efficiency of agent data analysis.

[0137] It should be emphasized that, to further ensure the privacy and security of the aforementioned feature information, this feature information can also be stored in a blockchain node.

[0138] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0139] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0140] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric identification technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0141] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by computer readable instructions instructing related hardware, and the computer readable instructions can be stored in a computer readable storage medium. When the program is executed, the processes of the above-mentioned embodiments of each method can be included. The storage medium can be a non-volatile storage medium such as a magnetic disc, an optical disc, a read-only memory (ROM), or a random access memory (RAM).

[0142] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0143] Further referring to Figure 3 , as an implementation of the method shown in the above Figure 2 , the present application provides an embodiment of a device for handling a buried point. The device embodiment corresponds to the method embodiment shown in Figure 2 , and the device can be specifically applied to various electronic devices.

[0144] As shown in Figure 3 , the device for handling a buried point 300 described in the present embodiment includes a first obtaining module 301, a second obtaining module 302, an analyzing module 303, a selecting module 304, and a processing module 305. Among them:

[0145] The first obtaining module 301 is configured to obtain identity information of each of all the seat personnel;

[0146] The second obtaining module 302 is configured to obtain feature information of each of the seat personnel based on the identity information and a preset feature type.

[0147] The analysis module 303 is configured to analyze the feature information based on a preset clustering algorithm, and group each of the agents according to an analysis result obtained, to obtain a plurality of target groups corresponding thereto.

[0148] The selection module 304 is configured to randomly select an agent in each of the target groups based on a preset random selection rule, to obtain a target agent corresponding thereto; wherein the target agent includes at least one agent in each of the target groups.

[0149] The processing module 305 is configured to perform a tracking point processing on behavior data of the target agent in a business system.

[0150] In the embodiment, the modules or units are respectively used for performing operations corresponding to the steps of the tracking point processing method of the foregoing embodiments, and thus will not be described herein.

[0151] In some optional implementations of the embodiment, the selection module 304 includes:

[0152] The first obtaining sub-module is configured to obtain a specified classification result of a specified group; wherein the specified group is any one of all the target groups.

[0153] The second obtaining sub-module is configured to obtain agent information of each agent included in the specified group.

[0154] The constructing sub-module is configured to construct a mapping relationship between the agent information of each agent included in the specified group and the specified classification result.

[0155] The first storing sub-module is configured to store the mapping relationship in a preset classification mapping table.

[0156] The first screening sub-module is configured to screen, based on a preset random strategy, at least one specified agent information of a specified agent corresponding to each classification result from the classification mapping table.

[0157] The determining sub-module is configured to determine the specified agent corresponding to the specified agent information as the target agent.

[0158] In the embodiment, the modules or units are respectively used for performing operations corresponding to the steps of the tracking point processing method of the foregoing embodiments, and thus will not be described herein.

[0159] In some optional implementations of the embodiment, the first screening sub-module includes:

[0160] The obtaining unit is configured to obtain a plurality of preset random algorithms.

[0161] determining unit configured to determine a target random algorithm from all the random algorithms;

[0162] screening unit configured to screen designated agent information of at least one designated agent corresponding to various classification results respectively from the classification mapping table based on the target random algorithm.

[0163] In the embodiment, the operations performed by the above modules or units correspond to the steps of the point embedding processing method of the foregoing embodiments one by one, and will not be described here again.

[0164] In some optional implementations of the embodiment, the selecting module 304 further includes:

[0165] a third obtaining sub-module configured to obtain designated agent information of the designated agent;

[0166] a fourth obtaining sub-module configured to obtain a preset initial data table;

[0167] a second storing sub-module configured to store the designated agent information into the initial data table to obtain a hit mapping table;

[0168] a third storing sub-module configured to store the hit mapping table.

[0169] In the embodiment, the operations performed by the above modules or units correspond to the steps of the point embedding processing method of the foregoing embodiments one by one, and will not be described here again.

[0170] In some optional implementations of the embodiment, the selecting module 304 further includes:

[0171] a fifth obtaining sub-module configured to obtain a current time;

[0172] a judging sub-module configured to judge whether the current time meets a preset timeout condition;

[0173] a second screening sub-module configured to, if yes, perform agent screening processing on the classification mapping table based on the target random algorithm to obtain specific agent information corresponding to the target random algorithm;

[0174] an updating sub-module configured to perform data updating on the hit mapping table based on the specific agent information.

[0175] In the embodiment, the operations performed by the above modules or units correspond to the steps of the point embedding processing method of the foregoing embodiments one by one, and will not be described here again.

[0176] In some optional implementations of the embodiment, the second obtaining module 302 includes:

[0177] Call a submodule for calling a preset information database;

[0178] A sixth acquisition submodule is configured to acquire personnel information of each of the service personnel from the information database based on the identity information.

[0179] A third screening submodule is configured to screen feature information corresponding to the feature type from the personnel information of each of the service personnel based on the feature type.

[0180] In the embodiment, the modules or units are respectively used for performing operations corresponding to steps of the aforementioned point embedding processing method, and thus no further description is given herein.

[0181] In some optional implementation forms of the embodiment, the point embedding processing apparatus further includes:

[0182] A third acquisition module is configured to acquire a target service link accessed by each of the target service personnel in the service system.

[0183] A determination module is configured to determine a storage mode of the target service link.

[0184] A storage module is configured to store the target service link based on the storage mode.

[0185] In the embodiment, the modules or units are respectively used for performing operations corresponding to steps of the aforementioned point embedding processing method, and thus no further description is given herein.

[0186] To solve the above technical problems, the embodiment of the present application further provides a computer device. For details, please refer to Figure 4 , Figure 4 The basic structure block diagram of the computer device in the embodiment is shown in FIG. 4.

[0187] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 which are connected to each other through a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0188] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The computer device can interact with a user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, or the like.

[0189] The memory 41 can include at least one type of readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, or the like), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, or the like. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, or the like. Of course, the memory 41 can include both an internal storage unit and an external storage device of the computer device 4. In this embodiment, the memory 41 is generally used to store an operating system and various application software installed in the computer device 4, such as computer readable instructions of the embedding point processing method, or the like. In addition, the memory 41 can also be used to temporarily store various data that has been output or will be output.

[0190] The processor 42 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer readable instructions or process data stored in the memory 41, such as computer readable instructions of the embedding point processing method.

[0191] The network interface 43 can include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0192] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0193] In the embodiments of the present application, first, identity information of each of all the agent personnel is acquired; then, feature information of each of the agent personnel is acquired based on the identity information and a preset feature type; subsequently, the feature information is analyzed based on a preset clustering algorithm, and each of the agent personnel is grouped according to an analysis result obtained, to obtain a plurality of target groups corresponding thereto; subsequently, agent personnel in each of the target groups is randomly selected based on a preset random selection rule, to obtain target agent personnel corresponding thereto; finally, behavior data of the target agent personnel in a business system is subjected to a burying point processing. By using the clustering algorithm to perform clustering analysis on the feature information of the agent personnel, the grouping of all the agent personnel can be quickly completed, and then the agent personnel in the groups is randomly selected based on the random selection rule to determine the target agent personnel, so that only the behavior data of the target agent personnel in the business system needs to be subjected to the burying point processing, and the demand for the burying point analysis of the business system can be met. By the embodiments of the present application, the sample quantity of the burying point sampling can be effectively reduced, and then the unreasonable problem of the production caused by the burying point data occupying too large storage can be avoided, and the processing efficiency and the intelligence of the burying point processing of the agent personnel are improved. In addition, the use of the random strategy is beneficial to avoiding the survivor bias in the selection of the agent personnel, and the selected part of the agent data can reflect the situation of the whole agent personnel, and the determination intelligence and the selection randomness of the target agent are effectively improved.

[0194] The present application also provides another embodiment, that is, a computer readable storage medium storing computer readable instructions, the computer readable instructions being executable by at least one processor to cause the at least one processor to perform the steps of the burying point processing method as described above.

[0195] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0196] In the embodiments of the present application, first, the identity information of each agent in all agent personnel is acquired; then, based on the identity information and a preset feature type, the feature information of each agent is acquired; thereafter, the feature information is analyzed based on a preset clustering algorithm, and each agent is grouped according to the obtained analysis result, to obtain a plurality of target groups corresponding thereto; subsequently, the agents in each target group are randomly selected based on a preset random selection rule, to obtain a target agent corresponding thereto; finally, the behavior data of the target agent in the business system is subjected to a burying point processing. The present application uses a clustering algorithm to perform clustering analysis on the feature information of the agent personnel, so that the grouping of all agent personnel can be quickly completed, and then the agents in the group are randomly selected based on a random selection rule to determine the target agent, so that only the behavior data of the target agent in the business system needs to be subjected to a burying point processing, and the demand for burying point analysis of the business system can be met. The embodiments of the present application can effectively reduce the sample quantity of the burying point sampling, and thus avoid the unreasonable problem of production caused by the large storage occupied by the burying point data, and improve the processing efficiency and intelligence of the burying point processing of the agent personnel. In addition, the use of the random strategy is beneficial to avoiding survivor bias in the selection of the agent personnel, and can make the selected part of the agent data reflect the overall situation of the agent personnel, effectively improving the determination intelligence and selection randomness of the target agent.

[0197] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and a necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk), and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0198] Obviously, the above-described embodiments are only some embodiments but not all the embodiments of the present application, the preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent replacements to some technical features therein. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the present application.

Claims

1. A method for processing embedded points, characterized in that, Includes the following steps: Obtain the identity information of each agent among all agents; Based on the identity information and the preset feature types, the feature information of each of the seated personnel is obtained; The feature information is analyzed based on a preset clustering algorithm, and the various agents are grouped according to the analysis results to obtain multiple target groups. Based on a preset random selection rule, the agents in each of the target groups are randomly selected to obtain the corresponding target agents; wherein, the target agents include at least one agent in each of the target groups; The behavioral data of the target agent in the business system is processed by embedding data points; The step of randomly selecting agents from each target group based on a preset random selection rule to obtain the corresponding target agents specifically includes: Obtain the specified classification result for a specified group; wherein, the specified group is any one of all the target groups; Obtain the seating information of each agent contained in the specified group; Construct a mapping relationship between the seat information of each agent in the specified group and the specified classification result; The mapping relationship is stored in a preset classification mapping table; Based on a preset random strategy, select the designated seat information of at least one designated agent corresponding to each of the various classification results from the classification mapping table. The designated agent corresponding to the designated agent information is taken as the target agent. Storing the mapping relationship into a preset classification mapping table means storing the seat information of each agent and the specified classification result in the classification mapping table based on the mapping relationship. The step of obtaining the feature information of each of the agents based on the identity information and the preset feature types specifically includes: Call the preset information database; Based on the identity information, the personnel information of each of the seated personnel is obtained from the information database; Based on the feature type, feature information corresponding to the feature type is filtered out from the personnel information of each of the seated personnel; Among them, the above-mentioned feature types include at least the area of ​​the seats, the center of the seats, the organization of the seats, the team of the seats, the position of the seats, the role of the seats, the hardware equipment information used by the seats, the date of employment, and the performance profile information. Among them, based on the use of the preset data tracking function components, data tracking is performed on the behavioral data of the target agent in the business system, that is, data tracking is performed on all business links corresponding to the target agent in the business system.

2. The embedding point processing method according to claim 1, characterized in that, The step of selecting the designated seat information of at least one designated agent corresponding to each of the various classification results from the classification mapping table based on a preset random strategy specifically includes: Obtain multiple preset random algorithms; The target random algorithm is determined from all the aforementioned random algorithms; Based on the target random algorithm, at least one designated seat information of a designated agent corresponding to each of the various classification results is selected from the classification mapping table.

3. The embedding point processing method according to claim 1, characterized in that, After the step of selecting the designated seat information of at least one designated agent corresponding to each of the various classification results from the classification mapping table based on a preset random strategy, the method further includes: Obtain the specified seat information of the specified agent; Retrieve the preset initial data table; The specified agent information is stored in the initial data table to obtain the hit mapping table; Store the hit mapping table.

4. The embedding point processing method according to claim 3, characterized in that, Following the step of storing the hit mapping table, the method further includes: Get the current time; Determine whether the current time meets the preset timeout condition; If so, the classification mapping table is processed by a target random algorithm to filter the seats and obtain the corresponding specific seat information; The hit mapping table is updated based on the specific agent information.

5. The embedding point processing method according to claim 1, characterized in that, After the step of embedding data on the target agent's behavior in the business system, the method further includes: Obtain the target business links accessed by each of the target agents in the business system; Determine the storage method for the target service link; The target business link is stored based on the storage method described above.

6. A device for processing embedded points, characterized in that, include: The first acquisition module is used to acquire the identity information of each agent among all the agents; The second acquisition module is used to acquire the feature information of each of the agents based on the identity information and the preset feature types. The analysis module is used to analyze the feature information based on a preset clustering algorithm, and to group each of the agents according to the analysis results to obtain multiple target groups. The selection module is used to randomly select agents from each of the target groups based on a preset random selection rule to obtain corresponding target agents; wherein, the target agents include at least one agent from each of the target groups; The processing module is used to perform data tracking on the behavioral data of the target agent in the business system. The selected modules include: The first acquisition submodule is used to acquire a specified classification result for a specified group; wherein, the specified group is any one of all the target groups; The second acquisition submodule is used to acquire the seat information of each agent contained in the specified group; A submodule is used to construct a mapping relationship between the seat information of each agent in the specified group and the specified classification result; The first storage submodule is used to store the mapping relationship into a preset classification mapping table; The first filtering submodule is used to filter the specified seat information of at least one specified agent corresponding to each of the various classification results from the classification mapping table based on a preset random strategy. The determination submodule is used to identify the designated agent corresponding to the designated agent information as the target agent. Storing the mapping relationship into a preset classification mapping table means storing the seat information of each agent and the specified classification result in the classification mapping table based on the mapping relationship. The second acquisition module includes: Calling submodules is used to call preset information databases; The sixth acquisition submodule is used to acquire personnel information of each of the agents from the information database based on the identity information; The third filtering submodule is used to filter out feature information corresponding to the feature type from the personnel information of each of the seat personnel based on the feature type; Among them, the above-mentioned feature types include at least the area of ​​the seats, the center of the seats, the organization of the seats, the team of the seats, the position of the seats, the role of the seats, the hardware equipment information used by the seats, the date of employment, and the performance profile information. Among them, based on the use of the preset data tracking function components, data tracking is performed on the behavioral data of the target agent in the business system, that is, data tracking is performed on all business links corresponding to the target agent in the business system.

7. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor, when executing the computer-readable instructions, implements the steps of the data embedding processing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the data embedding processing method as described in any one of claims 1 to 5.

Images