Unified message intelligent generation and conversion method and system

Abstract

The invention discloses a unified message intelligent generation and conversion method, and the method comprises the steps: receiving multiple types of mobile messages, automatically recognizing and analyzing the contents and formats of the multiple types of mobile messages, and outputting classified mobile message data; according to the classified mobile messages, based on a user behavior analysis and demand prediction result of a pre-training prediction model, adopting a pre-constructed message template and rule to automatically generate various types of message contents; or the formats of the multiple types of mobile messages are automatically converted, and the message content meeting the requirements of the target user is generated; and automatically verifying the automatically generated or converted message content, determining the optimal sending time and the optimal sending mode of the message based on the behavior and demand prediction result of the user and the dynamic data of the message channel resource, and pushing the final message to the target user. By integrating the artificial intelligence technology, automatic identification, analysis, generation and conversion of multiple types of mobile messages are realized, and intelligentization and automation of processing of the multiple types of mobile messages are realized.

Description

Technical Field

[0001] The present application relates to the field of mobile information services, and in particular to a unified message (ie, multi-type mobile message) intelligent generation and conversion method and system thereof. Background Art

[0002] At present, with the rapid development of mobile information technology, mobile information services have become an important part of daily life and business activities. In the field of mobile information services, there are many types of service messages, including text messages, multimedia messages, instant messages, and various social application messages. Specific messages can also include: text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, email messages, etc. Each message type has a unique format and transmission protocol, and the message compatibility problem between different devices and applications is becoming increasingly prominent.

[0003] However, there are two main problems and shortcomings in traditional mobile information service systems: the message generation and conversion process mostly relies on manual intervention or predefined format conversion rules. This approach is not only inefficient when processing multiple types of messages, but also difficult to cope with the growing number of new message formats; in addition, the system lacks intelligent processing capabilities, resulting in an inability to respond flexibly to diverse and personalized message demands, and it is difficult to adapt to users' diverse demands for message content and format.

[0004] In order to solve the above-mentioned technical problems, it is urgent to propose a unified message automatic generation and conversion method and system, so as to realize the integration of various mobile message sources, automatically identify and parse the content and format of multiple types of messages by utilizing artificial intelligence technology, and intelligently generate or convert message content that meets user needs. Summary of the invention

[0005] In order to solve the above problems of the prior art that relies on manual intervention and has low conversion efficiency, a fast and efficient unified message intelligent generation and conversion method and system are implemented.

[0006] In a first aspect, an embodiment of the present application provides a unified message intelligent generation and conversion method, the method comprising:

[0007] Message receiving step: receiving multiple types of mobile messages, automatically identifying and parsing the content and format of multiple types of mobile messages, and outputting classified mobile message data; wherein the mobile messages include: text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, and email messages;

[0008] Automatic message generation and conversion steps: Based on the classified mobile messages, the user behavior analysis and demand prediction results of the pre-trained prediction model are used to automatically generate various types of message content using pre-built message templates and rules; or, the formats of various types of mobile messages are automatically converted to generate message content that meets the needs of target users;

[0009] Message scheduling and sending steps: automatically verify the automatically generated or converted message content, determine the best time and method to send the message based on the user's behavior and demand prediction results and the dynamic data of message channel resources, and push the final message to the target user.

[0010] As an optional implementation, in the first aspect of the present invention, the unified message intelligent generation and conversion method further includes:

[0011] Message user behavior analysis steps: Use cluster analysis algorithms to identify user groups with similar behaviors, use association rule mining to reveal potential connections between user behaviors, use time series analysis and trend analysis methods to detect and determine the changing trends of user behaviors, and output user behavior analysis results;

[0012] User demand prediction step: extract features from the preprocessed and identified message data, build a prediction model based on the extracted features, predict user demand based on the prediction model, and output the user demand prediction results.

[0013] As an optional implementation, in the first aspect of the present invention, the unified message intelligent generation and conversion method further includes:

[0014] Message feedback learning optimization steps: Collect and analyze user feedback data during the message interaction process, and improve the accuracy of user demand prediction by continuously training and optimizing the pre-trained model.

[0015] As an optional implementation manner, in the first aspect of the present invention, the message receiving step includes:

[0016] Message access step: receiving and integrating mobile message data from multiple channels and multiple protocol formats;

[0017] Message identification steps: perform identification preprocessing on mobile message data, convert the message data format, use a learning classification model to automatically classify the message data, parse the known format message content according to the pre-built template, and use a semantic analysis algorithm to parse the unknown format message content.

[0018] As an optional implementation, in the first aspect of the present invention, the above-mentioned message automatic generation and conversion step includes:

[0019] Automatic message generation step: Obtain the latest behavior analysis and user demand prediction results of the target user according to the user ID, and automatically generate various types of message content that meet the user's needs through natural language generation technology or the system's existing message templates and related rules in combination with the service type and service scenario business configuration information;

[0020] Automatic message conversion step: Use the message format parsing method to automatically convert between multiple types of mobile messages, and re-encode and repackage the message format.

[0021] As an optional implementation manner, in the first aspect of the present invention, the message scheduling and sending step includes:

[0022] Message verification step: Use the built-in format specification library to verify whether the results, encoding and data types of the automatically generated or converted message content meet the specifications, and use natural language analysis technology to verify the data accuracy of the semantics of the message content;

[0023] Message scheduling steps: Based on the user's behavior analysis results and preferences, combined with the message importance and urgency weight values, the best time to send the message is automatically calculated, and the best way to send the message is determined based on real-time monitoring of the message sending channel resource usage.

[0024] In a second aspect, an embodiment of the present application provides a unified message intelligent generation and conversion system, which adopts the unified message intelligent generation and conversion method as described above, and the system includes:

[0025] Message receiving module: used to receive multiple types of mobile messages; wherein the mobile messages include: text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages and email messages;

[0026] Message identification module: used to automatically identify and parse the content and format of multiple types of mobile messages, and output classified mobile message data;

[0027] Message user behavior analysis module: Use cluster analysis algorithm to identify user groups with similar behaviors and output user behavior analysis results; predict user needs based on prediction models and output user demand prediction results;

[0028] Automatic message generation module: used to automatically generate various types of message content based on classified mobile messages, user behavior analysis and demand prediction results of pre-trained prediction models, and pre-built message templates and rules;

[0029] Automatic message conversion module: used to automatically convert multiple types of mobile message formats according to classified mobile messages and generate message content that meets the needs of target users;

[0030] Message scheduling module: used to automatically verify the content of automatically generated or converted messages, and determine the best time and method for sending messages based on the user's behavior and demand prediction results and the dynamic data of message channel resources;

[0031] Message output module: used to push messages to target users through a unified and integrated message channel.

[0032] As an optional implementation, in the second aspect of the present invention, the unified message intelligent generation and conversion system further includes:

[0033] Message feedback learning module: used to collect and analyze user feedback data during the message interaction process, and improve the accuracy of user demand prediction through continuous training and optimization of the pre-trained model.

[0034] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned unified message intelligent generation and conversion method.

[0035] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the unified message intelligent generation and conversion method as described above are implemented.

[0036] Compared with the related prior art, it has the following outstanding beneficial effects:

[0037] 1. The present invention realizes the automatic identification, analysis, generation and conversion of multiple types of mobile messages through deep integration of artificial intelligence technology, making a series of complex logical processes highly intelligent and automated, and ensuring that the entire process can be completed efficiently and accurately, greatly improving the efficiency of message processing, and significantly reducing the dependence on manual intervention. It not only saves a lot of human resources, but also effectively improves the accuracy and response speed of message processing, and makes this message processing process more intelligent, smooth and efficient;

[0038] 2. The present invention realizes that the system has strong compatibility and scalability, can support a variety of data transmission protocols and message formats, and realize seamless access to message data in different channels and formats; the system has good scalability and can adapt to the evolving communication technology and user needs, ensuring that new user needs are met in the long term;

[0039] 3. The present invention focuses on personalized user experience, and realizes intelligent generation and conversion of message content that meets user needs through in-depth analysis of user behavior and preferences, and sends it in the most appropriate way at the best time, significantly improving user experience and satisfaction; the system has a built-in comprehensive message verification mechanism to ensure that each message complies with format specifications and actual needs, and guarantees message accuracy and reliability; finally, the system has the ability to continuously learn and optimize, and by collecting user feedback data, it continuously optimizes performance and user experience, forming a closed loop of continuous improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 A schematic diagram of a unified message intelligent generation and conversion method according to an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of a unified message intelligent generation and conversion method according to another embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the architecture of a unified message intelligent generation and conversion system according to an embodiment of the present invention;

[0044] Figure 4 This is one of the flow charts of unified message intelligent generation and conversion control according to a specific embodiment of the present invention;

[0045] Figure 5 This is the second flow chart of unified message intelligent generation and conversion control according to a specific embodiment of the present invention;

[0046] Figure 6 This is the third flow chart of unified message intelligent generation and conversion control according to a specific embodiment of the present invention;

[0047] Figure 7 Schematic diagram of computer hardware of the present invention.

[0048] In the above picture:

[0049] 101 Message receiving step 102 Message automatic generation and conversion step 103 Message scheduling and sending step. DETAILED DESCRIPTION

[0050] It should be noted that the processor described in the present invention is the control center of the electronic device, which may be a processor or a general term for multiple processing elements. For example, it may be one or more central processing units (CPUs), or application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0051] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0052] In a specific implementation, as an embodiment, the processor may include one or more CPUs. Each of these processors may be a single core processor or a multi-core processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions). Electronic devices may include: servers, desktop computers, laptops, smart phones, tablet computers, embedded computers, etc., wherein the embedded computers include vehicles and robots, etc.

[0053] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0054] It should be noted that the structure of the electronic device shown in the drawings of the present invention does not constitute a limitation thereto, and the actual knowledge structure recognition device may include more or fewer components than shown in the drawings, or a combination of certain components, or a different arrangement of components.

[0055] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0056] It should also be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0057] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0058] It should also be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0059] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0060] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0062] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0063] In order to make the above features and effects of the present invention more clearly and understandably described, embodiments are given below and described in detail with reference to the accompanying drawings. This specification discloses one or more embodiments that include the features of the present invention. The disclosed embodiments are only for illustration. The scope of protection of the present invention is not limited to the disclosed embodiments, and the present invention is defined by the attached claims.

[0064] The following is a system embodiment corresponding to the above method embodiment. This embodiment can be implemented in conjunction with the above embodiment. The relevant technical details mentioned in the above embodiment are still valid in this embodiment. In order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiment.

[0065] The present invention aims to propose a unified message intelligent generation and conversion system, which can integrate multiple message sources, automatically identify and parse the content and format of multiple types of messages by utilizing artificial intelligence technology, intelligently generate message content that meets user needs, and automatically convert messages into a suitable format for sending according to the behavior, preferences or system requirements of the target recipient, so as to improve the efficiency of information transmission and user experience.

[0066] Embodiment 1

[0067] like Figure 1 As shown, Figure 1 This is a flow chart of a unified message intelligent generation and conversion method disclosed in an embodiment of the present invention. Figure 1 The unified message intelligent generation and conversion method shown can be applied to a unified message intelligent generation and conversion system or device, and the embodiment of the present invention does not limit it. Figure 1 As shown, the present invention provides a unified message intelligent generation and conversion method, the method comprising:

[0068] 101. Message receiving step: receiving multiple types of mobile messages, automatically identifying and parsing the content and format of multiple types of mobile messages, and outputting classified mobile message data; wherein the mobile messages include: text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, and email messages, etc., but the present invention is not limited thereto, and may also include other types of mobile messages;

[0069] In an embodiment of the present invention, optionally, the received mobile message data comes from an external network element, and the message can be obtained in real time, can be obtained periodically according to a preset time period, or can be actively obtained when needed, which is not specifically limited in the embodiment of the present invention.

[0070] Among them, mobile messages include: text messages, multimedia messages, instant messages, and various social application messages, etc., which are not specifically limited in the embodiments of the present invention; in the embodiments of the present invention, mobile messages receive and integrate message data from different channels and in different formats. The method and system of the present invention have strong compatibility and support multiple data transmission protocols, including Socket, Http / Https, WebService, API, and SDK, etc., so that external systems, applications, and devices can be seamlessly accessed. Advanced message queue data and data caching mechanisms are used to achieve stable operation in high-concurrency, high-traffic message access scenarios, and ensure that each message can be received and processed in a timely and accurate manner. The module stores the preliminarily processed data in the data cache area;

[0071] 102. Message automatic generation and conversion step: according to the classified mobile messages, based on the user behavior analysis and demand prediction results of the pre-trained prediction model, using pre-built message templates and rules, automatically generate multiple types of message content; or, automatically convert multiple types of mobile message formats to generate message content that meets the needs of target users;

[0072] In the embodiment of the present invention, among others, multiple types of messages are intelligently generated, that is, the latest behavior, preference and other information data of the target user are obtained according to the user identifier, and combined with the business configuration information such as the service type and service scenario, in the embodiment of the present invention, through natural language generation (NLG) technology (the present invention is not limited to this, and other technologies can also be used to implement it) or the system's existing rich message templates and related rules, various types of message content that meet actual needs are intelligently generated, wherein the messages include: text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, email messages, etc. The intelligently generated message content will be automatically submitted to the content review and verification process, and the messages that pass the content review and verification will be transmitted to the subsequent modules to ensure the quality and relevance of the intelligently generated message content;

[0073] In the embodiment of the present invention, the intelligent message conversion is to realize the automatic conversion between multiple types of messages such as short messages, multimedia messages (including video short messages, smart short messages, 5G messages, etc.), WeChat messages, APP messages, etc. The multi-type message format parsing technology is used to accurately identify and extract the key information of the content of multiple types of messages, and the built-in adaptation algorithm is used to re-encode and encapsulate this information to meet different message communication protocols and format requirements.

[0074] Among them, in the embodiment of the present invention, the multi-type message format parsing technology is an intelligent and adaptive message processing technology that can automatically identify, parse and extract key information of message content from different channels (including SMS, multimedia messages, WeChat, APP, etc.) without manual intervention, effectively improving the efficiency and flexibility of message processing. The key technical points include the following:

[0075] 1. Automatic identification of message types

[0076] Deep learning models (including convolutional neural networks, recurrent neural networks, etc.) are used to extract features of message content, including sender, receiver, timestamp, content subject, etc.; at the same time, the message header information (such as MIME type) is combined to quickly determine the message type.

[0077] 2. Content analysis and key information extraction

[0078] According to the message type and characteristics, the corresponding parsing strategy is called to accurately identify and extract the key information in the message content, specifically:

[0079] Text messages: Use natural language processing (NLP) technology (including word segmentation, named entity recognition, etc.) to deeply understand the text content and accurately extract key information;

[0080] Multimedia messages: Use computer vision and multimedia analysis technologies (including image recognition, video analysis, etc.) to extract key content information;

[0081] Social application information: Extract key fields by parsing specific formats (such as JSON, XML, etc.).

[0082] 3. Dynamic learning and optimization

[0083] A reinforcement learning mechanism is introduced to continuously optimize the parsing algorithm based on user feedback and parsing results. At the same time, a mapping relationship between message type and parsing strategy is established, and the parsing strategy library is dynamically adjusted to effectively improve parsing efficiency and accuracy.

[0084] Among them, in the embodiment of the present invention, the built-in adaptation algorithm specifically re-encodes and encapsulates the key information of the parsed message content to meet the target message communication protocol and format requirements. The key technical points include the following:

[0085] 1. Dynamic Adaptation Mechanism

[0086] According to the target message type, the optimal encoding and encapsulation strategy is dynamically selected from the encoding strategy library (including various message encoding strategies, such as UTF-8, GBK, etc.) and the encapsulation template library (providing standard encapsulation templates for various types of messages, such as WeChat message XML format, APP message JSON format, etc.) to ensure the accuracy and efficiency of message conversion.

[0087] 2. Cross-platform compatibility

[0088] Through a unified interface and protocol conversion layer (such as HTTP to Socket, SMPP to MQTT, etc.), conversion between different communication protocols is achieved to ensure seamless connection between different message systems.

[0089] Compared with the prior art, the method of the present invention has the following technical effects: it has high flexibility and scalability, can adapt to the evolving communication technology and user needs, and can perform self-optimization through continuous performance monitoring and feedback learning, thereby improving the efficiency and accuracy of message conversion;

[0090] 103. Message scheduling and sending steps: automatically verify the automatically generated or converted message content, determine the best time and method to send the message based on the user's behavior and demand prediction results and the dynamic data of message channel resources, and push the final message to the target user.

[0091] In an embodiment of the present invention, the method of the present invention needs to determine the best time and method for sending a message. Through comprehensive analysis of user behavior and preferences, including user active time periods, device types and states, and previous responses to messages, combined with an assessment of the urgency and importance of the message itself, different types of business messages (such as verification codes, marketing, etc.) are distinguished, and the best time to send the message is automatically calculated to ensure that the message arrives at a time when the user is most likely to pay attention and is convenient to receive; at the same time, the module will monitor the use of message channel resources in real time, including the congestion level of different channels, delivery speed, etc. Based on these dynamic data, intelligent selection of message diversion and sending methods is achieved to ensure that messages can be delivered to users efficiently and stably.

[0092] Among them, in the embodiment of the present invention, automatically calculating the best time to send a message is specifically to automatically calculate and optimize the best time to send a message by analyzing user behavior, preferences, device status and message characteristics.

[0093] The technical implementation is as follows:

[0094] 1. User behavior analysis: collect data such as users’ active time periods, device usage habits, message response history (such as time and method), and use machine learning algorithms (such as cluster analysis and time series analysis) to establish user behavior models and predict users’ active status and response probability in the future;

[0095] 2. Message feature evaluation: Classify and score messages based on their type (such as verification code, marketing, etc.), urgency, and importance, and determine different processing priorities and sending strategies;

[0096] 3. Calculation of optimal sending time: Combine the user behavior model and message characteristics, and use optimization algorithms (such as genetic algorithms and simulated annealing algorithms) to calculate the user's optimal receiving time window for different types of messages.

[0097] Embodiment 2

[0098] like Figure 2 As shown, Figure 2 is a flow chart of another unified message intelligent generation and conversion method disclosed in an embodiment of the present invention, Figure 2 The unified message intelligent generation and conversion method shown can be applied to a unified message intelligent generation and conversion system or device, and the embodiment of the present invention does not limit it. Figure 2 As shown, the present invention provides a unified message intelligent generation and conversion method, the method comprising:

[0099] 201. Message receiving step: receiving multiple types of mobile messages, automatically identifying and parsing the content and format of the multiple types of mobile messages, and outputting classified mobile message data;

[0100] As an optional implementation manner, the message receiving step includes:

[0101] 1. Message access step: receiving and integrating mobile message data from multiple channels and multiple protocol formats;

[0102] 2. Message identification step: Perform identification preprocessing on mobile message data, convert the message data format, use the learning classification model to automatically classify the message data, parse the known format message content according to the pre-built template, and use the semantic analysis algorithm to parse the unknown format message content.

[0103] In the embodiment of the present invention, the message recognition step obtains the latest access message data from the data cache in real time, and first performs a series of preprocessing operations on the data, including key steps such as data cleaning, encoding conversion and format standardization, converting the message data into a unified encoding format within the system, ensuring that the subsequent processing logic can correctly understand and parse the data, and laying a solid foundation for the entire recognition process; secondly, the module uses advanced machine learning classification algorithms (including random forests, support vector machines, deep learning networks, etc., the present invention is not limited to this) to automatically classify the preprocessed message data, extract keywords, phrases and word frequency features in the message as input, and accurately classify and judge the message (such as text messages, multimedia messages, instant messages, etc.) according to the trained model, providing clear guidance and basis for subsequent message processing. In addition, in terms of message content analysis, for messages of known formats, key information (such as time, amount, etc.) will be quickly extracted through template matching technology; and for messages of unknown formats or complex structures, natural language processing technology (NLP) is used for deep semantic analysis to understand the specific meaning of the message and accurately extract key information.

[0104] Among them, the template matching technology specifically includes:

[0105] 1. Template construction

[0106] Collect and analyze message samples of various known formats, and design corresponding message templates based on the analysis results. Each template contains information such as message format description, key information extraction rules and location.

[0107] 2. Template matching algorithm

[0108] (1) String matching algorithm: including simple string matching algorithms (such as BF algorithm), KMP algorithm, Boyer-Moore algorithm, etc., to search for substrings matching the template in the message content;

[0109] (2) Regular expression matching: Use an efficient regular expression engine (such as PCRE, re2, etc.) to match specific fields or formats in the message content.

[0110] 3. Template matching process

[0111] The pre-processed messages (such as removing spaces, converting uppercase and lowercase letters, etc.) are subjected to template matching. According to the type or characteristics of the message, the appropriate template and matching algorithm are selected for matching. If the match is successful, key information is extracted from the message content according to the extraction rules in the template.

[0112] The beneficial effects of the message content parsing method adopted by the present invention are: the flexible and changeable message content parsing method can adapt to the diversified message formats and complex message structures, ensuring the accuracy and comprehensiveness of message recognition; at the same time, the processing strategy can be flexibly adjusted according to actual needs, ensuring rapid response when processing messages with high real-time requirements, and strengthening the optimization of processing and recognition algorithms when processing messages with high accuracy, thereby improving the accuracy and reliability of message recognition. Finally, the message recognition results are stored in the data cache area.

[0113] 202. Message user behavior analysis steps: Use cluster analysis algorithm to identify user groups with similar behaviors, use association rule mining to reveal the potential connections between user behaviors, use time series analysis and trend analysis methods to detect and determine the changing trends of user behaviors, and output user behavior analysis results;

[0114] In the embodiment of the present invention, user behavior data is periodically obtained from multiple channels of the system, including application usage records, channel service browsing history, clickstream data, user feedback, etc. First, by cleaning, converting and integrating the collected data, the disorganized data is converted into an orderly, consistent and easy-to-analyze data set; secondly, machine learning algorithms and data mining techniques are used to deeply explore the patterns and trends behind user behaviors, that is, cluster analysis is used to identify user groups with similar behaviors, association rule mining is used to reveal the potential connections between user behaviors, and time series analysis and trend analysis methods are used to detect and judge the changing trends of user behaviors;

[0115] 203. User demand prediction step: extracting features from the preprocessed and identified message data, building a prediction model based on the extracted features, predicting user demand based on the prediction model, and outputting the user demand prediction result;

[0116] At the same time, in an embodiment of the present invention, in order to build an accurate prediction model, the module will perform feature extraction and selection, that is, extract features useful for the prediction task from the preprocessed and identified data, and reduce the number of features through feature dimensionality reduction technology to improve computing efficiency, and then build a prediction model (including regression model, classification model, time series prediction model, etc.) based on the extracted features and the actual requirements of the prediction task; finally, the analysis and prediction results are converted into a standardized format that is easy to understand and store and stored in the data cache.

[0117] 204. Message automatic generation and conversion step: according to the classified mobile messages, based on the user behavior analysis and demand prediction results of the pre-trained prediction model, using pre-built message templates and rules, automatically generate multiple types of message content; or, automatically convert multiple types of mobile message formats to generate message content that meets the needs of target users;

[0118] As an optional implementation, the above-mentioned message automatic generation and conversion step includes:

[0119] 1. Message automatic generation step 2041: obtaining the latest behavior analysis and user demand prediction results of the target user according to the user identifier, and automatically generating various types of message contents that meet the user's needs by combining the service type and service scenario business configuration information through natural language generation technology or the message templates and related rules stored in the system;

[0120] Based on the message sending user ID, the latest behavior, preference and other information data of the target user are retrieved from the database or data cache. The data includes application usage records, channel service browsing history, user feedback interaction behavior, etc., to provide rich materials for the personalized generation of messages. At the same time, the business configuration information, including service type, service scenario, etc., will be read and parsed to ensure that the generated message content is closely linked to the service requirements.

[0121] After obtaining user information and business configuration, natural language generation (NLG) technology is used to intelligently create message content that meets actual business needs (NLG technology can simulate the human language generation process and convert structured data into natural and fluent text). Through the above technology, various types of messages can be generated, including text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, email messages, etc. These message contents not only accurately convey service information, but also fully consider the user's personalized needs and preferences; in addition, in addition to using NLG technology, it also supports the use of rich message templates and related rules that already exist in the system to quickly generate messages. These templates and rules are summaries based on historical data and business experience, which can ensure that the generated message content meets industry standards and business requirements, and through the application of templates and rules, massive messages can be generated more efficiently while maintaining the consistency and accuracy of the message content.

[0122] In the specific implementation of the present invention, the message template and rule examples are:

[0123] 1. SMS message template

[0124]

Template name

[0125]

Template content

[0126] Dear ${username}, thank you for your support of our products! To thank our users, we are now launching

[0127] ${Promotional activity name}, unprecedented discount, activity time: ${activity start time} to ${activity end time}. Come and participate! For details, please click: ${activity link}

[0128] 2. Template corresponding rules

[0129] Rule 1: Based on the actual business situation, replace the variables ${user name}, ${promotion name}, ${activity start time}, ${activity end time}, and ${activity link} in the template with specific values.

[0130] Rule 2: Check the validity of the replaced specific values ​​to ensure that all values ​​correspond to the replacement, such as confirming the validity and security of ${active link}.

[0131] Rule 3: Perform compliance checks after a message is generated to ensure that the message content complies with industry standards and business requirements, such as checking whether it contains sensitive information and whether it is compliant.

[0132] The intelligently generated message content automatically enters the content review and verification process, which includes grammar checking, spelling proofreading, content compliance assessment and other steps to ensure the quality and relevance of the message. Only messages that pass the review and verification will be transmitted to subsequent modules for processing.

[0133] 2. Automatic message conversion step 2042: Use a message format parsing method to automatically convert between multiple types of mobile messages, and re-encode and re-encapsulate the message format.

[0134] Using multi-type message format parsing technology, we can accurately identify and extract key content information of received SMS, multimedia messages (including video SMS, smart SMS, 5G messages, etc.), WeChat messages, APP messages, etc. This format parsing technology can parse messages of different formats and protocols, extract key information, including text content, pictures, videos, etc., and provide an accurate data basis for subsequent message conversion through the parsing steps.

[0135] After extracting the key information from the message content, the information is re-encoded and packaged through the content configuration algorithm to meet the requirements of different message communication protocols and formats, and to achieve automatic conversion between multiple types of messages. In the above process, the module will adjust the layout, style and encoding method of the message according to the requirements of the target platform or application to ensure that the converted message can be transmitted and displayed normally on the target platform or application;

[0136] The beneficial effects of the automatic message conversion adopted by the present invention are: it has a high degree of flexibility and scalability, can adapt to the ever-changing communication technology and user needs, and performs self-optimization through continuous performance monitoring and feedback learning mechanism, so that the module can continuously improve the efficiency and accuracy of message conversion, and provide users with a better quality message service experience.

[0137] 205. Message scheduling and sending step: automatically verify the automatically generated or converted message content, determine the best time and best way to send the message based on the user's behavior and demand prediction results and the dynamic data of the message channel resources, and push the final message to the target user;

[0138] As an optional implementation manner, the message scheduling and sending step includes:

[0139] 1. Message verification step: Use the built-in format specification library to verify whether the results, encoding and data types of the automatically generated or converted message content meet the specifications, and use natural language analysis technology to verify the data accuracy of the semantics of the message content;

[0140] In an embodiment of the present invention, a strict format check is performed on the intelligently generated or automatically converted message content through a built-in format specification library (the library contains format requirements and specifications for various types of messages), including message content structure, encoding, and data type, to ensure that it is consistent with actual requirements, so as to avoid message parsing failure or content confusion due to format errors; secondly, natural language processing technology is used to conduct an in-depth analysis of the semantics of the message content, and meticulous checks are performed from aspects such as vocabulary, grammar, and context to ensure that the message expression is clear, accurate, and not misleading or ambiguous; then, the module uses a data verification algorithm to check the accuracy of key data elements (such as date, time, numerical value, etc.) contained in the message to ensure the correctness and consistency of the data, so as to avoid misunderstandings or confusion caused by data errors; finally, it is also responsible for quality control of the message to ensure that each message meets all quality and compliance standards before sending, and only messages that pass the verification can enter the subsequent sending processing flow.

[0141] In the specific implementation of the present invention, a built-in format specification library: an example of a short message format specification is as follows:

[0142] (1) SMS content structure requirements: It must include an opening greeting, a clear subject or purpose, clear action instructions (such as clicking a link, replying, etc.), and marketing content must provide an unsubscribe option. It must not contain any illegal or sensitive words.

[0143] (2) SMS encoding standards: The text encoding is UTF-8 or GB2312 to ensure multi-language compatibility; special characters or control characters are not allowed.

[0144] Data type specifications: Date and time format is YYYY-MM-DD HH:MM; numerical values ​​use Arabic numerals, and currency, percentages, etc. must have clear units.

[0145] 2. Message scheduling steps: Based on the user's behavior analysis results and preferences, combined with the message importance and urgency weight values, the best time to send the message is automatically calculated, and the best way to send the message is determined based on real-time monitoring of the usage of message sending channel resources.

[0146] In the embodiment of the present invention, by comprehensively analyzing the historical behavior and preferences of the user, the analysis covers the user's active time period, device type and status, and previous responses to messages. By deeply understanding the user's behavior module and preferences, a personalized sending strategy can be formulated for the message; at the same time, the urgency and importance of the message itself will be evaluated. Different types of business messages have different urgency and importance (such as verification code messages need to be delivered immediately, while marketing information can be delivered during the user's relatively idle time period), and appropriate sending priorities are assigned according to their nature; finally, based on the analysis results of user behavior and message attributes, the module will automatically calculate the best message sending time to ensure that the message is delivered at the time when the user is most likely to pay attention and convenient to receive. In addition, the resource usage of different message channels will be monitored in real time, including congestion level, delivery speed, delivery success rate, etc., and the message diversion strategy will be dynamically adjusted to intelligently select the optimal message sending channel and method to achieve efficient and stable message delivery.

[0147] 206. Message feedback learning optimization steps: Collect and analyze user feedback data during the message interaction process, and improve the accuracy of user demand prediction by continuously training and optimizing the pre-trained model.

[0148] In the embodiment of the present invention, all kinds of feedback data of users in the process of message interaction are collected comprehensively and in real time, and the data covers interactive behaviors such as user clicks, opens, and replies to messages, as well as the behavior logs of users after receiving messages. By deeply mining and analyzing these data, key factors affecting user experience can be identified, such as the suitability of sending time, the attractiveness of message content, etc. On this basis, machine learning algorithms (including classification, regression, clustering, etc.) are used to model and train user feedback data, learn user behavior patterns from historical data, and predict user responses to different types of messages. At the same time, through continuous training and optimization of the model, the accuracy of the prediction is improved, providing solid data support for subsequent processes; the module has a strong dynamic adjustment capability, and can continuously optimize the intelligent generation, conversion and scheduling strategies of messages according to real-time feedback and prediction results, so that the message system can respond to changes in user behavior in a timely manner, and by establishing a closed-loop feedback mechanism, user feedback is incorporated into the cycle of system learning and optimization, forming a closed loop of continuous improvement, so as to continuously improve the performance of the message system and user experience.

[0149] Embodiment 3

[0150] like Figure 3As shown, an embodiment of the present application provides a unified message intelligent generation and conversion system, which adopts the unified message intelligent generation and conversion method as described above. The system includes: a message access module 301, a message identification module 302, a message user behavior analysis module 303, a message generation module 304, a message conversion module 305, a message verification module 3061, a message intelligent scheduling module 306, a message output module 307, and a message feedback learning module 308.

[0151] Message access module 301: used to receive mobile messages of multiple business types; the module provides a variety of technical docking methods, including Socket, Http / Https, WebService, API, SDK, etc., and realizes the integration and unification of multiple types of message communication interaction protocols. The peripheral system can perform unified transmission of multiple types of message data through the module, effectively avoiding the complex mode that a single type of message must be accessed through an independent dedicated module;

[0152] Message identification module 302: used to automatically identify and parse the content and format of multiple types of mobile messages, and output classified mobile message data; the message identification module 302 obtains and analyzes business message data, identifies its type and content, that is, first performs standardized preprocessing on the message data, then uses a classification algorithm to determine the message type, and then performs in-depth analysis on the identified type of message to extract key content information and context, and finally transmits the identification results and analysis data to subsequent application modules;

[0153] Message user behavior analysis module 303: Use cluster analysis algorithm to identify user groups with similar behaviors and output user behavior analysis results; predict user needs based on prediction models and output user demand prediction results; track and analyze user interaction behavior data with the system, including but not limited to user message reading preferences, message interaction behaviors, message customization service configuration, etc. Through the above data, the module can build user portraits and predict user needs, thereby providing user preference information for intelligent generation of message content;

[0154] like Figure 4As shown, the message automatic generation module 304 is used to automatically generate various types of message content based on classified mobile messages, user behavior analysis and demand prediction results based on pre-trained prediction models, and pre-built message templates and rules; intelligently generate multiple types of messages, that is, obtain the latest behavior, preference and other information data of the target user according to the user identifier, and combine the service type, service scenario and other business configuration information, through natural language generation (NLG) technology or the system's existing rich message templates and related rules, intelligently generate various types of message content that meet actual needs (including text SMS, video SMS, smart SMS, 5G messages, APP messages, WeChat messages, email messages, etc.). The intelligently generated message content will be automatically submitted to the content review and verification process, and the messages that pass the content review and verification will be transmitted to subsequent modules to ensure the quality and relevance of the intelligently generated message content;

[0155] like Figure 5 As shown, the message automatic conversion module 305 is used to automatically convert multiple types of mobile message formats according to classified mobile messages, generate message content that meets the needs of target users, and realize automatic conversion between multiple types of messages such as text messages, multimedia messages (including video text messages, smart text messages, 5G messages, etc.), WeChat messages, APP messages, etc. The module uses multi-type message format parsing technology to accurately identify and extract key information of multi-type message content, and re-encodes and encapsulates this information through a built-in adaptation algorithm to meet different message communication protocols and format requirements. In addition, the module is also highly flexible and scalable, can adapt to evolving communication technologies and user needs, and can perform self-optimization through continuous performance monitoring and feedback learning to improve message conversion efficiency and accuracy;

[0156] Message intelligent scheduling module 306: used to automatically verify the content of the automatically generated or converted message, and determine the best time and method of sending the message based on the user's behavior and demand prediction results and the dynamic data of the message channel resources; the module comprehensively analyzes the user's behavior and preferences, including the user's active time period, device type and status, and previous responses to messages, and evaluates the urgency and importance of the message itself, distinguishes different types of business messages (such as verification codes, marketing, etc.), and automatically calculates the best time to send the message to ensure that the message arrives at the time when the user is most likely to pay attention and convenient to receive; at the same time, the module will monitor the use of message channel resources in real time, including the congestion level and delivery speed of different channels. Based on these dynamic data, the intelligent selection of message diversion and sending methods is realized to ensure that the message can be delivered to the user efficiently and stably.

[0157] The message intelligent scheduling module 306 also includes: a message verification module 3061, which is used to verify the content of intelligently generated and converted messages, and ensure that each intelligently generated and converted message meets the corresponding format specifications and actual requirements before sending through a refined technical process. The module verifies whether the structure, encoding and data type of the message content are consistent with the actual requirements through the built-in format specification library, and uses natural language processing technology to conduct an in-depth analysis of the semantics of the message content to ensure that it is clearly expressed and accurate. In addition, the module uses a data verification algorithm to check the accuracy of the data contained in the message, including date, time, value, etc., to ensure its accuracy and reliability;

[0158] Message output module 307: used to push messages to target users through a unified and integrated message channel. The message generation module is used to intelligently generate multiple types of messages, that is, to obtain the latest behavior, preference and other information data of the target user according to the user identifier, and to combine the service type, service scenario and other business configuration information, through natural language generation (NLG) technology or the system's existing rich message templates and related rules, to intelligently generate various types of message content that meet actual needs (including text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, email messages, etc.). The intelligently generated message content will be automatically submitted to the content review and verification process, and the messages that pass the content review and verification will be transmitted to subsequent modules to ensure the quality and relevance of the intelligently generated message content;

[0159] The unified message intelligent generation and conversion system further includes:

[0160] like Figure 6 As shown, the message feedback learning module 308 is used to collect and analyze the feedback data of users during the message interaction process, and improve the accuracy of user demand prediction by continuously training and optimizing the pre-trained model. Use these feedback data to continuously optimize and improve the performance and user experience of the message system. The module identifies the key factors that affect the user experience through multi-dimensional data analysis, and combines machine learning models to predict the user's response to different types of messages, and customizes the message content and sending strategy based on the personalized recommendation algorithm; at the same time, the module optimizes the message generation and scheduling strategy based on real-time feedback and prediction results through dynamic adjustment capabilities, and establishes a closed-loop feedback mechanism to ensure that the system can continue to learn and adapt to changes in user behavior.

[0161] Embodiment 4

[0162] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the above-mentioned unified message intelligent generation and conversion method are implemented.

[0163] Embodiment 5

[0164] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the unified message intelligent generation and conversion method described above are implemented.

[0165] In addition, combined Figure 1 The unified message intelligent generation and conversion analysis method described in the embodiment of the present application can be implemented by an electronic device, such as a computer device. Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0166] In some of these embodiments, the computer device may further include a communication interface 83 and a bus 80. Figure 7 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0167] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0168] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0169] The processor 81 implements any one of the pre-wiring static timing analysis methods in the above embodiments by reading and executing computer program instructions stored in the memory 82 .

[0170] In summary, compared with the prior art, the method of the present invention has the following beneficial effects:

[0171] 1. The present invention proposes a unified message processing framework that can integrate multiple message sources and realize automatic identification, parsing, generation and conversion of multiple types of messages;

[0172] 2. The present invention uses natural language generation (NLG) technology, multi-type message format parsing technology and adaptation algorithm, and realizes intelligent generation and automatic conversion of multi-type messages based on information such as user behavior, preferences and business configuration;

[0173] 3. The present invention realizes intelligent optimization of message sending timing and sending through a refined message verification process and an intelligent scheduling algorithm based on user behavior analysis;

[0174] 4. The present invention collects and analyzes user feedback data, continuously optimizes message generation, conversion and scheduling strategies, and forms a closed loop of continuous improvement.

[0175] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0176] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A unified message intelligent generation and conversion method, characterized in that: The method comprises: Message receiving step: receiving multiple types of mobile messages, automatically identifying and parsing the content and format of the multiple types of mobile messages, and outputting classified mobile message data; wherein the mobile messages include: text messages, video messages, smart messages, 5G messages, APP messages, WeChat messages, and email messages; Automatic message generation and conversion step: according to the classified mobile messages, based on the user behavior analysis and demand prediction results of the pre-trained prediction model, using pre-built message templates and rules, automatically generate multiple types of message content; or automatically convert the multiple types of mobile message formats to generate message content that meets the needs of target users; Message scheduling and sending step: automatically verify the automatically generated or converted message content, determine the best time and best way to send the message based on the user's behavior and demand prediction results and message channel resource dynamic data, and push the final message to the target user.

2. The unified message intelligent generation and conversion method according to claim 1, characterized in that: The method further comprises: Message user behavior analysis steps: Use cluster analysis algorithms to identify user groups with similar behaviors, use association rule mining to reveal potential connections between user behaviors, use time series analysis and trend analysis methods to detect and determine the changing trends of user behaviors, and output user behavior analysis results; User demand prediction step: extract features from the message data after preprocessing and identification, build a prediction model based on the extracted features, predict user demand based on the prediction model, and output the user demand prediction result.

3. The unified message intelligent generation and conversion method according to claim 2, characterized in that: The method further comprises: Message feedback learning optimization step: collect and analyze user feedback data during the message interaction process, and improve the accuracy of user demand prediction by continuously training and optimizing the pre-trained model.

4. The unified message intelligent generation and conversion method according to claim 1 or 3, characterized in that: The message receiving step comprises: Message access step: receiving and integrating mobile message data from multiple channels and multiple protocol formats; Message identification step: perform identification preprocessing on the mobile message data, convert the message data format, use a learning classification model to automatically classify the message data, parse the known format message content according to a pre-built template, and use a semantic analysis algorithm to parse the unknown format message content.

5. The unified message intelligent generation and conversion method according to claim 1 or 3, characterized in that: The message automatic generation and conversion steps include: Automatic message generation step: obtaining the latest behavior analysis and user demand prediction results of the target user according to the user identifier, and automatically generating various types of message content that meet the user's needs through natural language generation technology or the system's existing message templates and rules in combination with the service type and service scenario business configuration information; Automatic message conversion step: Use the message format parsing method to automatically convert between multiple types of mobile messages, and re-encode and repackage the message format.

6. The unified message intelligent generation and conversion method according to claim 5, characterized in that: The message scheduling and sending step comprises: Message verification step: Use the built-in format specification library to verify whether the results, encoding and data types of the automatically generated or converted message content meet the specifications, and use natural language analysis technology to verify the data accuracy of the semantics of the message content; Message scheduling step: Based on the user's behavior analysis results and preferences, combined with the message importance and urgency weight values, automatically calculate the best time to send the message, and determine the best way to send the message based on real-time monitoring of message sending channel resource usage.

7. A unified message intelligent generation and conversion system, using the unified message intelligent generation and conversion method as claimed in any one of claims 1 to 6, characterized in that: The system comprises: Message access module: used to receive multiple types of mobile messages; Message identification module: used to automatically identify and parse the content and format of the multi-type mobile messages, and output classified mobile message data; Message user behavior analysis module: uses a cluster analysis algorithm to identify user groups with similar behaviors and outputs user behavior analysis results; predicts user needs based on the prediction model and outputs user demand prediction results; Automatic message generation module: used to automatically generate various types of message contents according to the classified mobile messages, based on the user behavior analysis and demand prediction results of the pre-trained prediction model, using pre-built message templates and rules; Message automatic conversion module: used to automatically convert the multi-type mobile message formats according to the classified mobile messages to generate message contents that meet the needs of target users; Message intelligent scheduling module: used to automatically verify the automatically generated or converted message content, and determine the best time and best way to send the message based on the user's behavior and demand prediction results and message channel resource dynamic data; Message output module: used to push the message to the target user through a unified and integrated message channel.

8. The unified message intelligent generation and conversion system according to claim 7, characterized in that: The system further comprises: Message feedback learning module: used to collect and analyze user feedback data during the message interaction process, and improve the accuracy of user demand prediction by continuously training and optimizing the pre-trained model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the unified message intelligent generation and conversion method described in any one of claims 1 to 6 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the unified message intelligent generation and conversion method according to any one of claims 1 to 6 are implemented.

Images