Clue data processing method and device, equipment and medium

Abstract

The invention belongs to the field of big data, and relates to a clue data processing method, which comprises the following steps of: acquiring a plurality of clue data in a historical time period from a constructed full-amount clue library; dividing the multiple pieces of clue data based on a preset clue strategy, and determining clue type information of each piece of clue data; based on a preset priority strategy and clue type information, judging a clue priority level of each clue data; and sending each piece of clue data and the clue priority level to a processing platform, so that the processing platform reaches a plurality of user terminals based on each piece of clue data and the clue priority level. The invention further provides a clue data processing device and equipment and a medium. In addition, the invention also relates to a block chain technology, and multiple pieces of clue data, preset clue strategies, clue type information and clue priorities in the total clue library can be stored in a block chain. The method can improve the efficiency of touching the user.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a clue data processing method, device, equipment and medium. Background Art

[0002] With the vigorous development of modern network technology, online apps have become an indispensable part of people's daily lives. They provide a variety of services including browsing, searching, non-car content browsing and smart shopping guides, which greatly enrich people's lives. However, with the frequent occurrence of users' online behaviors, a large amount of clue information is generated every moment, which is both an opportunity and a challenge for enterprises.

[0003] In order to improve the activity of online customers and the conversion rate of online premiums, enterprises need to make full use of these lead information. However, when processing these lead information, the existing system often adopts a full-dimensional inventory method, which lacks pertinence, resulting in a lack of focus in the processing process, making it difficult to effectively identify and utilize high-quality leads, which in turn causes a huge waste of resources. It is urgent to develop a method that can achieve accurate analysis of user behavior, improve the utilization efficiency of lead information, and improve the efficiency of reaching users. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a clue data processing method, device, equipment and medium to solve the existing problem of being unable to accurately analyze user behavior, improve the utilization efficiency of clue information, and improve the efficiency of reaching users.

[0005] In order to solve the above technical problems, the present application embodiment provides a clue data processing method, which adopts the following technical solutions:

[0006] Acquire multiple clue data within a historical time period from the constructed full clue library, where the clue data in the full clue library consists of historical behavior data of multiple user terminals; divide the multiple clue data based on a preset clue strategy, and determine the clue type information of each clue data; determine the clue priority level of each clue data based on a preset priority strategy and clue type information; send each clue data and clue priority level to a processing platform, so that the processing platform can reach multiple user terminals based on each clue data and clue priority level.

[0007] Furthermore, before the step of obtaining a plurality of clue data in a historical time period from the constructed full clue library, the step further includes:

[0008] Obtain historical behavior data of multiple user terminals within a preset time period; extract user identification information from the historical behavior data according to preset user identification rules; group the historical behavior data according to the user identification information to obtain a behavior data group corresponding to each user terminal; and construct a full clue library based on the behavior data group corresponding to each user terminal.

[0009] Furthermore, based on the behavior data group corresponding to each user terminal, a full clue library is constructed, including:

[0010] The behavior data group corresponding to each user terminal is structured according to a predetermined format to form initial clue data of each user terminal;

[0011] A clustering algorithm is used to classify the initial clue data to obtain multiple categories of initial clue data; an association rule mining algorithm is used to perform association mining on each category of initial clue data to determine the correlation information and logical connection information between the initial clue data, where the correlation information indicates the correlation between the initial clue data, and the logical connection information indicates the logical connection between the initial clue data; a network topology diagram of the initial clue data is constructed based on the correlation information and the logical connection information to form a thinking chain of the initial clue data; the marked initial clue data and the thinking chain are imported into the clue database to form a full clue library.

[0012] Furthermore, the steps of obtaining multiple clue data within a historical time period from the constructed full clue library specifically include:

[0013] Acquire multiple initial clue data within a historical time period from the constructed full clue database; pre-process the multiple clue data to obtain multiple clue data;

[0014] The steps of dividing the plurality of clue data based on the preset clue strategy and determining the clue type information of each clue data specifically include:

[0015] A clustering algorithm is used to divide multiple clue data to obtain multiple clue data sets; based on a preset clue strategy, each clue data set is analyzed to determine the clue type information of each clue data set; if the clue type information meets the preset clue conditions, the clue data set is marked as a target clue data set; a classification algorithm is used to classify each clue data of the target clue data set, determine the clue type of each clue data, and obtain the clue type information of each clue data.

[0016] Further, a classification algorithm is used to classify each clue data of the target clue data set, determine the clue type of each clue data, and obtain the clue type information of each clue data, which specifically includes:

[0017] Extract the behavioral feature information of each clue data in the target clue data set; use the classification prediction model to predict the type of the behavioral feature information and obtain the type prediction result; based on the type prediction result, determine the clue type of each clue data and obtain the clue type information of each clue data.

[0018] Furthermore, based on the preset priority strategy and clue type information, the step of determining the clue priority level of each clue data specifically includes:

[0019] Perform key feature extraction on each clue data to obtain key feature information; match the key feature information with the preset priority strategy to determine the clue score of the clue data; based on the clue score and clue type information, use the preset level prediction model to predict the priority level of the clue data to obtain the priority level prediction result; based on the priority level prediction result, determine the clue priority of each clue data.

[0020] Furthermore, the step of matching the key feature information with the preset priority strategy to determine the clue score of the clue data specifically includes:

[0021] Match key feature information with preset priority strategies to determine the importance level and urgency level of the clue data; obtain the importance score and importance weight value corresponding to the importance level, and obtain the urgency score and urgency weight value corresponding to the urgency level; perform weighted processing on the importance score, importance weight value, urgency score and urgency weight value to obtain the clue score of the clue data.

[0022] In order to solve the above technical problems, the embodiment of the present application further provides a clue data processing device, which adopts the following technical solution:

[0023] An acquisition module is used to acquire multiple clue data within a historical time period from the constructed full clue library, where the clue data in the full clue library consists of historical behavior data of multiple user terminals;

[0024] A division module, used to divide multiple clue data based on a preset clue strategy and determine clue type information of each clue data;

[0025] A determination module, used to determine the clue priority level of each clue data based on a preset priority strategy and clue type information;

[0026] The sending module is used to send each clue data and clue priority level to the processing platform, so that the processing platform can reach multiple user terminals based on each clue data and clue priority level.

[0027] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the above-mentioned clue data processing method are implemented.

[0028] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-readable instructions. The computer-readable instructions can be executed by at least one processor to enable at least one processor to perform the steps of the above-mentioned clue data processing method.

[0029] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: by obtaining multiple clue data within a historical time period from the constructed full clue library, the comprehensive integration and utilization of user behavior data is achieved. Based on the preset clue strategy, the clue data is accurately divided, and the type information of each clue is determined, which helps the company to have a deeper understanding of user needs and preferences. At the same time, combined with the preset priority strategy, this solution can scientifically and reasonably determine the priority level of each clue, ensuring that high-value clues are processed in a timely manner, thereby effectively improving the efficiency and accuracy of clue processing. By sending the clue data and clue priority level to the processing platform, the processing platform can accurately reach the user terminal based on this information, improve the efficiency of reaching users, and realize personalized marketing and service push. This not only helps to improve the user experience, but also significantly improves the company's marketing conversion rate and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0032] Figure 2 It is a flowchart of a clue data processing method provided by the present application;

[0033] Figure 3 It is a structural schematic diagram of a clue data processing device provided by the present application;

[0034] Figure 4 It is a structural schematic diagram of a computer device provided by this application. DETAILED DESCRIPTION

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0036] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0038] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0039] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0040] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0041] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0042] It should be noted that the clue data processing method provided in the embodiment of the present application is generally executed by a server, and accordingly, the clue data processing device is generally set in the server.

[0043] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0044] Continue to refer Figure 2 , shows a flow chart of an embodiment of a clue data processing method according to the present application. The clue data processing method comprises the following steps:

[0045] Step S201, obtaining a plurality of clue data within a historical time period from a constructed full clue library, where the clue data in the full clue library is composed of historical behavior data of a plurality of user terminals.

[0046] In this embodiment, the clue data processing method is executed on the electronic device (eg Figure 1 The server shown in the figure) can obtain multiple clue data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0047] Among them, the full clue library refers to a comprehensive database of all user behavior data collected from various channels. These data cover all historical behavior records of users on various user terminals (such as mobile apps, web pages, etc.), including but not limited to browsing records, search records, click records, purchase records, etc. The full clue library is equivalent to a huge data warehouse that stores massive and diverse user behavior data for subsequent data mining and analysis.

[0048] The historical time period refers to a specific time range, which is used to filter out clue data generated within this time period from the full clue library. This time range can be the past day, week, month or longer, depending on the analysis requirements.

[0049] Among them, clue data refers to data points collected from user terminals that can reflect the user's potential needs and interests. These data points can be a user's click, search, browse or purchase behavior, etc. For example, in the insurance industry, clue data may include the number of times a user browses insurance products, the length of stay, the type of insurance clicked, etc., which can be used to evaluate the user's purchase intention.

[0050] Among them, user terminal refers to the device used by users to access network services, such as smart phones, tablets, computers, etc.

[0051] Among them, historical behavior data refers to all the behavior records generated by users through user terminals in the past period of time, including browsing records, search records, click records, purchase records, etc. These data reflect the interests, preferences and behavior patterns of users. For example, in the insurance industry, historical behavior data can help companies understand users' purchase history and preferences, so as to formulate more accurate marketing strategies.

[0052] Step S202: based on a preset clue strategy, multiple clue data are divided to determine clue type information of each clue data.

[0053] Among them, lead strategies refer to the rules and methods used to classify and filter lead data based on business needs and user behavior characteristics. These strategies can be built based on big data analysis and machine learning algorithms. For example, based on user browsing history, purchase history, interest preferences and other information, lead strategies can be used to classify lead data into different types.

[0054] Among them, segmentation refers to the process of classifying and grouping clue data according to clue strategies.

[0055] The clue type information refers to the information obtained after the clue data is divided and reflects the characteristics and attributes of the clue data. The clue type information can be used to describe the category of the clue data.

[0056] Step S203: determining the clue priority level of each clue data based on the preset priority strategy and clue type information.

[0057] Priority strategy refers to the method of sorting and grading the lead data according to its characteristics and attributes. High-quality leads can be identified and utilized based on priority strategy. For example, in the insurance industry, priority strategy can be used to sort and grade lead data based on user purchase intention, purchase history, insurance type and other information, so as to give priority to high-value leads.

[0058] Among them, the lead priority level refers to the result obtained by sorting and grading the lead data according to the priority strategy. These lead priorities reflect the potential value and importance of the lead data and can be used to guide subsequent processing and outreach.

[0059] Step S204, sending each clue data and clue priority level to the processing platform, so that the processing platform reaches multiple user terminals based on each clue data and clue priority level.

[0060] The processing platform refers to a comprehensive system that integrates data processing, analysis and access functions. This comprehensive system can be built based on big data technology and artificial intelligence technology to process, analyze and utilize clue data.

[0061] Reach refers to the process of sending information or providing services to users of user terminals through specific channels and methods. For example, in the insurance industry, reach refers to sending product information, promotional activities and other content to users through APP push, SMS, email and other methods.

[0062] The embodiment of the present application can achieve comprehensive integration and utilization of user behavior data by obtaining multiple clue data within a historical time period from the constructed full clue library. Based on the preset clue strategy, the clue data is accurately divided and the type information of each clue is determined, which helps the company to have a deeper understanding of user needs and preferences. At the same time, combined with the preset priority strategy, this solution can scientifically and reasonably determine the priority level of each clue to ensure that high-value clues are processed in a timely manner, thereby effectively improving the efficiency and accuracy of clue processing. By sending the clue data and clue priority level to the processing platform, the processing platform can accurately reach the user terminal based on this information, improve the efficiency of reaching users, and realize personalized marketing and service push. This not only helps to improve the user experience, but also significantly improves the company's marketing conversion rate and user satisfaction.

[0063] In some optional implementations of this embodiment, before the step of acquiring a plurality of clue data within a historical time period from the constructed full clue library in step 201, the following steps may also be included:

[0064] Obtain historical behavior data of multiple user terminals within a preset time period; extract user identification information from the historical behavior data according to preset user identification rules; group the historical behavior data according to the user identification information to obtain a behavior data group corresponding to each user terminal; and construct a full clue library based on the behavior data group corresponding to each user terminal.

[0065] In one example, historical behavior data such as browsing, clicking, purchasing, consulting, etc. of all user terminals in the past time period (for example, in the past year) can be collected from various channels such as websites, apps, and social media platforms. Then, through regular expression matching, hash algorithms and other technical means, information that uniquely identifies the user, such as user ID, mobile phone number, and email address, is extracted from the above historical behavior data. Based on the extracted user identification information, the historical behavior data is grouped by user terminal to ensure that each user terminal corresponds to an independent behavior data group. Based on each user's behavior data group, a full clue library containing all user information is constructed.

[0066] The embodiments of the present application can make full use of big data resources and avoid data idleness or waste by systematically collecting and analyzing user behavior data within a preset time period. This comprehensive and detailed data processing strategy ensures that every piece of data can contribute value to the construction of a full clue library. By grouping historical behavior data based on user identification information, each user terminal corresponds to an independent and complete behavior data group, which can accurately capture the user's personalized needs and preferences.

[0067] In some optional implementations of this embodiment, the step of “building a full clue library based on the behavior data group corresponding to each user terminal” specifically includes the following steps:

[0068] The behavior data group corresponding to each user terminal is structured in a predetermined format to form the initial clue data of each user terminal; the initial clue data is classified by a clustering algorithm to obtain multiple categories of initial clue data; the association rule mining algorithm is used to perform association mining on the initial clue data of each category to determine the association information and logical connection information between the initial clue data, the association information indicates the association between the initial clue data, and the logical connection information indicates the logical connection between the initial clue data; based on the association information and the logical connection information, a network topology diagram of the initial clue data is constructed to form a thinking chain of the initial clue data; the marked initial clue data and the thinking chain are imported into the clue database to form a full clue library.

[0069] In one example, the behavior data group of each user terminal can be structured in a predetermined format, such as JSON format (i.e., JavaScript Object Notation format, which is a lightweight data exchange format), to form initial clue data containing key fields such as user basic information, browsing history, and purchase history. Next, the initial clue data can be classified using the K-means clustering algorithm (K-means) to obtain multiple customer categories with similar characteristics. For example, users who frequently purchase health insurance can be classified into one category, and users who frequently browse travel insurance pages can be classified into another category. In order to deeply explore the correlation within and between these categories, an association rule mining algorithm can be used, such as the Apriori association rule mining algorithm (i.e., the Apriori AssociationRule Mining Algorithm association rule mining algorithm). By performing association mining on the initial clue data of each category, the correlation information and logical connection information between user behaviors can be determined. For example, it is found that users who purchase health insurance often also pay attention to medical insurance and serious illness insurance, while users who browse travel insurance pages are more inclined to purchase short-term accident insurance. Based on this correlation information and logical connection information, a network topology diagram of the initial clue data can be constructed to form a clear chain of thought. These chains of thought not only show the direct connection between user behaviors, but also reveal potential user needs and preferences. Finally, these initial clue data and chains of thought can be imported into the clue database to form a full clue library.

[0070] The embodiment of the present application forms standardized initial clue data by structured processing of the behavior data group of each user terminal, which greatly improves the readability and processability of the data. By using a clustering algorithm to classify the initial clue data, multiple user categories with similar characteristics can be obtained. Through the association rule mining algorithm, the correlation information and logical connection information between each category of initial clue data can be deeply mined. This information reveals the inherent connection and potential laws between user behaviors, which helps to better understand user needs and preferences and improve user satisfaction.

[0071] In some optional implementations of this embodiment, step S201, obtaining a plurality of clue data within a historical time period from the constructed full clue library, specifically includes the following steps:

[0072] A plurality of initial clue data within a historical time period is obtained from the constructed full clue library; the plurality of clue data are preprocessed to obtain a plurality of clue data.

[0073] In one example, a database query technology can be used to filter out multiple initial clue data within a historical period from the full clue database. Next, these initial clue data can be preprocessed, such as data cleaning can be performed on these initial clue data to remove duplicate data, invalid data and abnormal data to obtain multiple clue data.

[0074] The embodiment of the present application can remove duplicate, invalid and abnormal data and ensure the accuracy of data through preprocessing steps including data cleaning, data conversion and data standardization. The quality of clue data after preprocessing is higher, which provides a solid foundation for subsequent data analysis and mining.

[0075] In some optional implementations of this embodiment, step S202, based on a preset clue strategy, divides the plurality of clue data and determines clue type information of each clue data, specifically including the following steps:

[0076] A clustering algorithm is used to divide multiple clue data to obtain multiple clue data sets; based on a preset clue strategy, each clue data set is analyzed to determine the clue type information of each clue data set; if the clue type information meets the preset clue conditions, the clue data set is marked as a target clue data set; a classification algorithm is used to classify each clue data of the target clue data set, determine the clue type of each clue data, and obtain the clue type information of each clue data.

[0077] In one example, a clustering algorithm, such as a K-means clustering algorithm, can be used to divide the obtained multiple clue data. By calculating the Euclidean distance between each clue data, the number of clusters is set to N, and N clue data sets are obtained. Then, for each clue data set, based on the preset clue strategy, by analyzing the attribute characteristics of the clues in the set, such as the product type, user profile, behavior trajectory, etc. of the clues, the clue type information of the data set is determined using a decision tree algorithm. If the clue type information is a valuable clue, the clue data set is marked as a valid clue, otherwise it is marked as an invalid clue. According to the clue type information marking result, the clue data is filtered using a logistic regression algorithm to obtain multiple target clue data sets. Then, a classification algorithm, such as a classification prediction model, is used to subdivide the target clue data set, and by analyzing the key attributes of the clues, the specific type of each clue data is determined, such as high-value timely clues, high-willing timely clues, high-quality clues, medium-low willingness clues, etc.

[0078] The embodiment of the present application can divide a large amount of clue data into multiple clue data sets through a clustering algorithm, which can significantly reduce the workload of subsequent analysis and make the processing process more efficient. By analyzing each clue data set based on a preset clue strategy, the clue type information of each set can be accurately determined. By screening the clue type information through preset clue conditions, the target clue data set that meets specific conditions can be quickly marked, reducing the interference of invalid clues. By classifying each clue data in the target clue data set, the clue type can be further refined to provide more detailed information for subsequent clue processing.

[0079] In some optional implementations of this embodiment, the step of "using a classification algorithm to classify each clue data of the target clue data set, determining the clue type of each clue data, and obtaining clue type information of each clue data" may specifically include the following steps:

[0080] Extract the behavioral feature information of each clue data in the target clue data set; use the classification prediction model to predict the type of the behavioral feature information and obtain the type prediction result; based on the type prediction result, determine the clue type of each clue data and obtain the clue type information of each clue data.

[0081] In one example, after extracting the behavior feature information of each clue data of the target clue data set, the extracted behavior feature information can be converted into a vector form and input into a trained classification prediction model, such as a naive Bayes model, to output the posterior probability of each clue type of the behavior feature information. The clue type corresponding to the maximum posterior probability can be selected as the prediction category of the behavior feature information to obtain a type prediction result, and then the clue type of each clue data and the clue type information of each clue data can be determined.

[0082] The embodiment of the present application can quickly obtain the key information points of each clue data by extracting the behavioral feature information of each clue data in the target clue data set. A classification prediction model is used to predict the type of the behavioral feature information, and a relatively accurate type prediction result can be obtained. Compared with manual classification, this model-based prediction method not only improves the accuracy of classification, but also greatly reduces labor costs. After determining the clue type of each clue data based on the type prediction result, the clue type information of each clue data can be obtained. This information is crucial for subsequent processing and decision-making. For example, different processing strategies or priorities can be adopted for different types of clues, so as to more effectively solve related problems.

[0083] In some optional implementations of this embodiment, step S203, based on the preset priority strategy and clue type information, determines the clue priority level of each clue data, which may specifically include the following steps:

[0084] Perform key feature extraction on each clue data to obtain key feature information; match the key feature information with the preset priority strategy to determine the clue score of the clue data; based on the clue score and clue type information, use the preset level prediction model to predict the priority level of the clue data to obtain the priority level prediction result; based on the priority level prediction result, determine the clue priority of each clue data.

[0085] In one example, a preset priority strategy can be obtained first. The priority strategy includes clue importance scoring rules and urgency scoring rules, and also defines thresholds for different priority levels. After extracting the key feature information of each clue data, the key feature information can be matched with the preset priority strategy, and the clue score of the clue can be obtained by weighted calculation. A preset level prediction model, such as the XGBoost algorithm (i.e., the eXtremeGradient Boosting algorithm, which is an optimized gradient boosting algorithm), is used to classify and predict the priority of the clues, using the clue score and clue type information as input features, and outputting the priority prediction results. Based on the priority prediction results, the clue priority of each clue data is determined.

[0086] The embodiments of the present application can quickly identify the core information in the data by extracting key features from the clue data, reducing the time for processing a large amount of non-critical data, thereby improving the overall processing efficiency. By matching the key feature information with the preset priority strategy, the potential value or importance of each clue can be more accurately evaluated. Based on the clue score and clue type information, the priority level of the clue data is predicted using a preset level prediction model, so that resources can be reasonably allocated according to the priority of the clue.

[0087] In some optional implementations of this embodiment, the step of “matching the key feature information with the preset priority strategy to determine the clue score of the clue data” may specifically include the following steps:

[0088] Match key feature information with preset priority strategies to determine the importance level and urgency level of the clue data; obtain the importance score and importance weight value corresponding to the importance level, and obtain the urgency score and urgency weight value corresponding to the urgency level; perform weighted processing on the importance score, importance weight value, urgency score and urgency weight value to obtain the clue score of the clue data.

[0089] In one example, a preset priority strategy may be obtained first, which includes clue importance scoring rules and urgency scoring rules, and also defines thresholds for different priority levels. Based on the priority strategy, the scoring dimensions of the extracted key feature information are divided into importance dimension and urgency dimension, each dimension has multiple levels, and different scores are assigned to each dimension. At the same time, importance weight A and urgency weight B may be assigned to these two dimensions. Obtain the importance score C of the key feature information on the importance dimension, and obtain the urgency score D of the key feature information on the urgency dimension. The clue score of the clue data can be: importance score C × importance weight A + urgency score D × urgency weight B.

[0090] The embodiment of the present application can ensure the objectivity of the evaluation process by matching using a preset priority strategy. At the same time, by obtaining the corresponding scores and weight values, the characteristics and value of the clues can be further quantified to improve the accuracy of the evaluation. According to the clue scores, processing resources can be allocated more scientifically. Clues with high scores will be given priority to ensure that key tasks are responded to and processed in a timely manner.

[0091] It should be emphasized that in order to further ensure the privacy and security of the multiple clue data, preset clue strategies, clue type information, and clue priority levels in the above-mentioned full clue library, the multiple clue data, preset clue strategies, clue type information, and clue priority levels in the above-mentioned full clue library can also be stored in a node of a blockchain.

[0092] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0093] The embodiment of the present application can acquire and process multiple clue data, preset clue strategies, clue type information, and clue priority levels in the full clue library based on the relevant algorithms of natural language processing technology (NLP) under artificial intelligence. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0094] Natural language processing technology is a key branch in the field of artificial intelligence. It focuses on giving computers the ability to understand and process human language, so that they can parse, understand and generate natural language text like humans. By simulating some core mechanisms of human language processing, NLP technology can deeply process, analyze and interpret text data, extract key information from it, understand semantic content, and perform complex tasks or generate natural language responses based on it. Natural language processing technology can be used to parse candidate data to obtain graph structure data that will be imported into the graph database.

[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0096] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0097] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a clue data processing device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0098] like Figure 3 As shown, the clue data processing device 400 of this embodiment includes: an acquisition module 401, a division module 402, a determination module 403 and a sending module 404. Among them:

[0099] The acquisition module 401 is used to acquire multiple clue data within a historical time period from the constructed full clue library, where the clue data in the full clue library is composed of historical behavior data of multiple user terminals;

[0100] A division module 402 is used to divide the plurality of clue data based on a preset clue strategy and determine clue type information of each clue data;

[0101] The determination module 403 is used to determine the clue priority level of each clue data based on the preset priority strategy and clue type information;

[0102] The sending module 404 is used to send each clue data and clue priority level to the processing platform, so that the processing platform can reach multiple user terminals based on each clue data and clue priority level.

[0103] The embodiment of the present application can achieve comprehensive integration and utilization of user behavior data by obtaining multiple clue data within a historical time period from the constructed full clue library. Based on the preset clue strategy, the clue data is accurately divided and the type information of each clue is determined, which helps the company to have a deeper understanding of user needs and preferences. At the same time, combined with the preset priority strategy, this solution can scientifically and reasonably determine the priority level of each clue to ensure that high-value clues are processed in a timely manner, thereby effectively improving the efficiency and accuracy of clue processing. By sending the clue data and clue priority level to the processing platform, the processing platform can accurately reach the user terminal based on this information, improve the efficiency of reaching users, and realize personalized marketing and service push. This not only helps to improve the user experience, but also significantly improves the company's marketing conversion rate and user satisfaction.

[0104] In one embodiment, the clue data processing device 400 further includes:

[0105] A data acquisition module, used to acquire historical behavior data of multiple user terminals within a preset time period;

[0106] An extraction module, used to extract user identification information from historical behavior data according to preset user identification rules;

[0107] A grouping module, used to group the historical behavior data according to the user identification information to obtain a behavior data group corresponding to each user terminal;

[0108] The construction module is used to build a full clue library based on the behavior data group corresponding to each user terminal.

[0109] The embodiments of the present application can make full use of big data resources and avoid data idleness or waste by systematically collecting and analyzing user behavior data within a preset time period. This comprehensive and detailed data processing strategy ensures that every piece of data can contribute value to the construction of a full clue library. By grouping historical behavior data based on user identification information, each user terminal corresponds to an independent and complete behavior data group, which can accurately capture the user's personalized needs and preferences.

[0110] In one embodiment, a building block comprises:

[0111] A processing submodule, used to perform structured processing on the behavior data group corresponding to each user terminal according to a predetermined format to form initial clue data of each user terminal;

[0112] The first classification submodule is used to classify the initial clue data using a clustering algorithm to obtain initial clue data of multiple categories;

[0113] The information submodule is used to use the association rule mining algorithm to perform association mining on each category of the initial clue data, and determine the association information and logical connection information between the initial clue data, the association information indicates the association between the initial clue data, and the logical connection information indicates the logical connection between the initial clue data;

[0114] A construction submodule is used to construct a network topology diagram of the initial clue data based on the correlation information and the logical connection information, so as to form a thinking chain of the initial clue data;

[0115] The import submodule is used to import the initial clue data and thought chain into the clue database to form a full clue library.

[0116] The embodiment of the present application can form standardized initial clue data by structured processing of the behavior data group of each user terminal, which greatly improves the readability and processability of the data. By using a clustering algorithm to classify the initial clue data, multiple user categories with similar characteristics can be obtained. Through the association rule mining algorithm, the correlation information and logical connection information between each category of initial clue data can be deeply mined. This information reveals the inherent connection and potential laws between user behaviors, which helps to better understand user needs and preferences and improve user satisfaction.

[0117] In one embodiment, the acquisition module 401 includes:

[0118] The acquisition submodule is used to obtain multiple initial clue data within a historical time period from the constructed full clue library;

[0119] The preprocessing submodule is used to preprocess the multiple clue data to obtain the multiple clue data.

[0120] The embodiment of the present application can remove duplicate, invalid and abnormal data and ensure the accuracy of data through preprocessing steps including data cleaning, data conversion and data standardization. The quality of clue data after preprocessing is higher, which provides a solid foundation for subsequent data analysis and mining.

[0121] In one embodiment, the partitioning module 402 includes:

[0122] A partitioning submodule is used to partition a plurality of clue data using a clustering algorithm to obtain a plurality of clue data sets;

[0123] An analysis submodule, for analyzing each clue data set based on a preset clue strategy, and determining clue type information of each clue data set;

[0124] A marking submodule, used for marking the clue data set as a target clue data set if the clue type information meets the preset clue condition;

[0125] The second classification submodule is used to adopt a classification algorithm to classify each clue data in the target clue data set, determine the clue type of each clue data, and obtain the clue type information of each clue data.

[0126] The embodiment of the present application can divide a large amount of clue data into multiple clue data sets through a clustering algorithm, which can significantly reduce the workload of subsequent analysis and make the processing process more efficient. By analyzing each clue data set based on a preset clue strategy, the clue type information of each set can be accurately determined. By screening the clue type information through preset clue conditions, the target clue data set that meets specific conditions can be quickly marked, reducing the interference of invalid clues. By classifying each clue data in the target clue data set, the clue type can be further refined to provide more detailed information for subsequent clue processing.

[0127] In one embodiment, the second classification submodule is also used to extract behavioral feature information of each clue data in the target clue data set; use a classification prediction model to perform type prediction on the behavioral feature information to obtain a type prediction result; based on the type prediction result, determine the clue type of each clue data to obtain clue type information of each clue data.

[0128] The embodiment of the present application can quickly obtain the key information points of each clue data by extracting the behavioral feature information of each clue data in the target clue data set. A classification prediction model is used to predict the type of the behavioral feature information, and a relatively accurate type prediction result can be obtained. Compared with manual classification, this model-based prediction method not only improves the accuracy of classification, but also greatly reduces labor costs. After determining the clue type of each clue data based on the type prediction result, the clue type information of each clue data can be obtained. This information is crucial for subsequent processing and decision-making. For example, different processing strategies or priorities can be adopted for different types of clues, so as to more effectively solve related problems.

[0129] In one embodiment, the determination module 403 includes:

[0130] The extraction submodule is used to extract key features from each clue data to obtain key feature information;

[0131] A matching submodule is used to match key feature information with a preset priority strategy to determine the clue score of the clue data;

[0132] The prediction submodule is used to predict the priority level of the clue data based on the clue score and clue type information using a preset level prediction model to obtain a priority level prediction result;

[0133] The determination submodule is used to determine the clue priority of each clue data based on the priority level prediction result.

[0134] The embodiments of the present application can quickly identify the core information in the data by extracting key features from the clue data, reducing the time for processing a large amount of non-critical data, thereby improving the overall processing efficiency. By matching the key feature information with the preset priority strategy, the potential value or importance of each clue can be more accurately evaluated. Based on the clue score and clue type information, the priority level of the clue data is predicted using a preset level prediction model, so that resources can be reasonably allocated according to the priority of the clue.

[0135] In one embodiment, the matching submodule is also used to match the key feature information with a preset priority strategy to determine the importance level and urgency level of the clue data; obtain the importance score and importance weight value corresponding to the importance level, and obtain the urgency score and urgency weight value corresponding to the urgency level; and perform weighted processing on the importance score, importance weight value, urgency score and urgency weight value to obtain the clue score of the clue data.

[0136] The embodiment of the present application can use a preset priority strategy for matching, which can ensure the objectivity of the evaluation process. At the same time, by obtaining the corresponding scores and weight values, the characteristics and value of the clues can be further quantified to improve the accuracy of the evaluation. According to the clue scores, processing resources can be allocated more scientifically. Clues with high scores will be given priority to ensure that key tasks are responded to and processed in a timely manner.

[0137] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0138] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 6 having a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations 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 (ASIC), programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0139] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0140] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the clue data processing method, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0141] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run computer-readable instructions stored in the memory 61 or process data, such as computer-readable instructions for running a clue data processing method.

[0142] The network interface 63 may include a wireless network interface or a wired network interface, and the network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0143] The embodiment of the present application can achieve comprehensive integration and utilization of user behavior data by obtaining multiple clue data within a historical time period from the constructed full clue library. Based on the preset clue strategy, the clue data is accurately divided and the type information of each clue is determined, which helps the company to have a deeper understanding of user needs and preferences. At the same time, combined with the preset priority strategy, this solution can scientifically and reasonably determine the priority level of each clue to ensure that high-value clues are processed in a timely manner, thereby effectively improving the efficiency and accuracy of clue processing. By sending the clue data and clue priority level to the processing platform, the processing platform can accurately reach the user terminal based on this information, improve the efficiency of reaching users, and realize personalized marketing and service push. This not only helps to improve the user experience, but also significantly improves the company's marketing conversion rate and user satisfaction.

[0144] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions. The computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the clue data processing method as described above.

[0145] The embodiment of the present application can achieve comprehensive integration and utilization of user behavior data by obtaining multiple clue data within a historical time period from the constructed full clue library. Based on the preset clue strategy, the clue data is accurately divided and the type information of each clue is determined, which helps the company to have a deeper understanding of user needs and preferences. At the same time, combined with the preset priority strategy, this solution can scientifically and reasonably determine the priority level of each clue to ensure that high-value clues are processed in a timely manner, thereby effectively improving the efficiency and accuracy of clue processing. By sending the clue data and clue priority level to the processing platform, the processing platform can accurately reach the user terminal based on this information, improve the efficiency of reaching users, and realize personalized marketing and service push. This not only helps to improve the user experience, but also significantly improves the company's marketing conversion rate and user satisfaction.

[0146] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for 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 of each embodiment of the present application.

[0147] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A clue data processing method, characterized in that: The steps include: Acquire multiple clue data within a historical time period from the constructed full clue library, where the clue data in the full clue library is composed of historical behavior data of multiple user terminals; Based on a preset clue strategy, the plurality of clue data are divided to determine clue type information of each clue data; Determining the clue priority level of each clue data based on a preset priority strategy and the clue type information; Each clue data and the clue priority level are sent to a processing platform, so that the processing platform reaches the multiple user terminals based on each clue data and the clue priority level.

2. The method according to claim 1, characterized in that: Before the step of acquiring a plurality of clue data in a historical time period from the constructed full clue library, the method further includes: Obtain historical behavior data of multiple user terminals within a preset time period; Extracting user identification information from the historical behavior data according to a preset user identification rule; According to the user identification information, the historical behavior data is grouped to obtain a behavior data group corresponding to each user terminal; Based on the behavior data group corresponding to each user terminal, a full clue library is constructed.

3. The method according to claim 2, characterized in that The constructing of a full clue library based on the behavior data group corresponding to each user terminal specifically includes: Performing structural processing on the behavior data group corresponding to each user terminal according to a predetermined format to form initial clue data of each user terminal; Using a clustering algorithm to classify the initial clue data to obtain multiple categories of initial clue data; Adopting an association rule mining algorithm, performing association mining on the initial clue data of each category, and determining association information and logical connection information between the initial clue data, wherein the association information indicates the association between the initial clue data, and the logical connection information indicates the logical connection between the initial clue data; According to the relevance information and the logical connection information, a network topology diagram of the initial clue data is constructed to form a thought chain of the initial clue data; Import the initial clue data and the thought chain into the clue database to form a complete clue database.

4. The method according to claim 3, characterized in that The step of obtaining multiple clue data within a historical time period from the constructed full clue library specifically includes: Obtain multiple initial clue data within a historical time period from the established full clue library; Preprocessing the plurality of clue data to obtain a plurality of clue data; The step of dividing the plurality of clue data based on the preset clue strategy and determining the clue type information of each clue data specifically includes: Using a clustering algorithm to divide the plurality of clue data to obtain a plurality of clue data sets; Based on the preset clue strategy, each clue data set is analyzed to determine the clue type information of each clue data set; If the clue type information meets the preset clue condition, marking the clue data set as a target clue data set; A classification algorithm is adopted to classify each clue data of the target clue data set, determine the clue type of each clue data, and obtain the clue type information of each clue data.

5. The method according to claim 4, characterized in that The step of adopting a classification algorithm to classify each clue data of the target clue data set, determining the clue type of each clue data, and obtaining the clue type information of each clue data specifically includes: Extracting behavior feature information of each clue data of the target clue data set; Using a classification prediction model to perform type prediction on the behavior feature information to obtain a type prediction result; Based on the type prediction result, the clue type of each clue data is determined, and the clue type information of each clue data is obtained.

6. The method according to claim 4, characterized in that The step of determining the clue priority level of each clue data based on the preset priority strategy and the clue type information specifically includes: Performing key feature extraction processing on each clue data to obtain key feature information; Matching the key feature information with a preset priority strategy to determine a clue score of the clue data; Based on the clue score and the clue type information, a preset level prediction model is used to perform level prediction on the priority level of the clue data to obtain a priority level prediction result; Based on the priority level prediction result, the clue priority of each clue data is determined.

7. The method according to claim 6, characterized in that The step of matching the key feature information with a preset priority strategy to determine the clue score of the clue data specifically includes: Matching the key feature information with a preset priority strategy to determine the importance level and urgency level of the clue data; Obtaining the importance score and importance weight value corresponding to the importance level, and obtaining the urgency score and urgency weight value corresponding to the urgency level; The importance score, the importance weight value, the urgency score and the urgency weight value are weighted to obtain a clue score of the clue data.

8. A clue data processing device, characterized in that: include: An acquisition module, used to acquire a plurality of clue data within a historical time period from a constructed full clue library, wherein the clue data in the full clue library is composed of historical behavior data of a plurality of user terminals; A division module, used for dividing the plurality of clue data based on a preset clue strategy, and determining clue type information of each clue data; A determination module, configured to determine the priority level of each clue data based on a preset priority strategy and the clue type information; The sending module is used to send each clue data and the clue priority level to the processing platform, so that the processing platform can reach the multiple user terminals based on each clue data and the clue priority level.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of the clue data processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the clue data processing method as described in any one of claims 1 to 7 are implemented.

Images