Business Text Summary Generation Method and System Based on an Intelligent Platform

Abstract

Embodiments of the present application relate to the field of artificial intelligence technology, and specifically to a method and system for generating business text summaries based on a smart platform. Obtain the smart government business conversation text stream; mine the business interaction state knowledge vector chain from the smart government business conversation text stream according to the node set mined from the business interaction state; based on the business element heat evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain, determine the state knowledge confidence of each business interaction state knowledge vector; based on the state knowledge confidence, determine the target key conversation text semantics from the business interaction state knowledge vector chain. The smart government platform system can realize the automatic summary generation function of the online business conversation to be processed, thereby improving the efficiency and quality of government affairs processing.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and more specifically, to a method and system for generating business text summaries based on a smart platform. Background Art

[0002] With the rapid development and popularization of information technology, the smart government affairs platform system has become an important means for the government affairs platform to provide public services and achieve government affairs transparency and efficiency. In these systems, processing and analyzing the government affairs business conversation text stream is a core task, which involves accurately understanding and efficiently responding to the interactions between users such as citizens and enterprises and the government affairs platform.

[0003] When traditional smart government affairs platforms process the government affairs business conversation text stream, they often rely on simple keyword matching or rule judgment. This method is inadequate when dealing with complex and changeable government affairs interactions. It cannot fully understand the true intentions and needs of users, nor can it accurately identify the key information in the conversation text, thus affecting the efficiency and quality of government affairs services. Summary of the Invention

[0004] To improve the technical problems existing in the related art, this application provides a method and system for generating business text summaries based on a smart platform.

[0005] In a first aspect, an embodiment of this application provides a method for generating a business text summary based on a smart platform, which is applied to a smart government affairs platform system. The method includes: obtaining a government affairs business conversation text stream; mining a business interaction status knowledge vector chain from the government affairs business conversation text stream according to a node set for mining business interaction status, where the node set for mining business interaction status is integrated by at least one business interaction status mining node based on a target government affairs matter handling task; determining the status knowledge confidence of each business interaction status knowledge vector based on the business element heat evaluation data of each business interaction status knowledge vector in the business interaction status knowledge vector chain, where the business element heat evaluation data is used to reflect the heat map statistical result of the business interaction status knowledge vector, and the status knowledge confidence is used to reflect the importance of the corresponding business interaction status knowledge vector; and determining the target key conversation text semantics from the business interaction status knowledge vector chain based on the status knowledge confidence.

[0006] In a second aspect, this application also provides a smart government affairs platform system, including: a memory for storing program instructions and data; and a processor for being coupled to the memory and executing the instructions in the memory to implement the method as described above.

[0007] In a third aspect, the present application also provides a computer storage medium containing instructions that, when executed on a processor, implement the above-described method.

[0008] To address the above problems, in recent years, some intelligent government affairs platform systems based on deep learning and natural language processing technologies have emerged. These systems attempt to understand the user's language by training a large number of models and have improved the processing accuracy to a certain extent. However, these systems often face challenges such as high model complexity, large computational resource consumption, and difficulty in adapting to changes in government affairs.

[0009] In view of the deficiencies of the prior art, the present application proposes an intelligent government affairs platform system and its processing method. This method extracts a business interaction state knowledge vector chain from the intelligent government affairs business conversation text stream by introducing the concept of a business interaction state mining node set. These node sets are flexibly integrated according to the target government affairs handling tasks, enabling the system to more accurately understand the user's interaction intentions and needs. At the same time, by introducing business element heat evaluation data and state knowledge confidence, the system can further optimize resource allocation and improve processing efficiency.

[0010] In summary, the intelligent government affairs platform system and its processing method of the present application aim to solve the problems and challenges existing in the prior art through innovative technical means and improve the efficiency and quality of government affairs services. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0012] Figure 1 is a flowchart showing a method for generating a business text summary based on an intelligent platform provided by an embodiment of the present application.

[0013] Figure 2 is a block diagram showing the structure of an intelligent government affairs platform system provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0015] Exemplary embodiments will be described in detail herein, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application.

[0016] It should be noted that the terms "first", "second", etc. in the description of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence.

[0017] The method embodiments provided by the embodiments of this application can be executed in a smart government affairs platform system, a computer device, or a similar computing device. Taking running on a smart government affairs platform system as an example, the smart government affairs platform system may include one or more processors (the processor may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory for storing data. Optionally, the above-mentioned smart government affairs platform system may further include a transmission device for communication functions. Those of ordinary skill in the art can understand that the above structure is only illustrative and does not limit the structure of the above-mentioned smart government affairs platform system. For example, the smart government affairs platform system may further include more or fewer components than those shown above, or have a different configuration from those shown above.

[0018] The memory can be used to store computer programs. For example, software programs and modules of application software, such as the computer program corresponding to a method for generating a business text summary based on a smart platform in the embodiments of this application. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above-mentioned method is implemented. The memory may include a high-speed random access memory, and may further include a non-volatile memory, such as one or more magnetic storage devices, a flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely set relative to the processor, and these remote memories can be connected to the smart government affairs platform system through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an enterprise internal network, a local area network, a mobile communication network, and combinations thereof.

[0019] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the smart government affairs platform system. In one instance, the transmission device includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device may be a radio frequency (abbreviated as RF) module, which is used to communicate with the Internet wirelessly.

[0020] Based on this, please refer to Figure 1 , Figure 1 is a schematic flowchart of a method for generating a business text summary based on a smart platform provided by the embodiments of this application. This method is applied to a smart government affairs platform system and may further include step 110-step 130.

[0021] Step 110, the intelligent government affairs platform system obtains the intelligent government affairs service session text stream; and mines the business interaction status knowledge vector chain from the intelligent government affairs service session text stream according to the node set mined by the business interaction status; wherein, the node set mined by the business interaction status is integrated by at least one business interaction status mining node based on the target government affairs item handling task.

[0022] Step 120, the intelligent government affairs platform system determines the status knowledge confidence of each business interaction status knowledge vector based on the business element heat evaluation data of each business interaction status knowledge vector in the business interaction status knowledge vector chain; wherein, the business element heat evaluation data is used to reflect the heat map statistical result of the business interaction status knowledge vector, and the status knowledge confidence is used to reflect the importance of the corresponding business interaction status knowledge vector.

[0023] Step 130, the intelligent government affairs platform system determines the target key session text semantics from the business interaction status knowledge vector chain based on the status knowledge confidence.

[0024] In the daily operation of the intelligent government affairs platform system, a large number of government affairs service session text streams will be processed. These text streams contain various interaction information between users, enterprises and the government, and are an important part of government affairs services. Next, how the intelligent government affairs platform system processes these session text streams and mines valuable information from them will be introduced in detail.

[0025] First of all, the intelligent government affairs platform system will obtain these intelligent government affairs service session text streams. These text streams may come from various channels such as online government affairs service platforms, social media, and emails. After obtaining these text streams, the system will process them using the pre-set node set mined by the business interaction status. These node sets are integrated based on the target government affairs item handling task, and they can identify and process various business interaction statuses in the text stream.

[0026] Through the processing of the node set mined by the business interaction status, the intelligent government affairs platform system will mine the business interaction status knowledge vector chain from the text stream. This vector chain is composed of a series of business interaction status knowledge vectors, and each vector represents a business interaction status in the text stream.

[0027] Next, the system will determine the status knowledge confidence of these vectors according to the business element heat evaluation data of each vector in the business interaction status knowledge vector chain. The business element heat evaluation data is obtained by statistically analyzing the business elements in the text stream, and it can reflect the heat map statistical result of the business interaction status knowledge vector. The status knowledge confidence is calculated based on these statistical results and is used to reflect the importance of the corresponding business interaction status knowledge vector.

[0028] Finally, the intelligent government affairs platform system determines the semantic meaning of the target key conversation texts from the business interaction status knowledge vector chain according to the status knowledge confidence. These semantic meanings of the target key conversation texts are the most important parts of the text stream, and they may contain key information such as the needs, problems, and suggestions of users and enterprises. By determining the semantic meaning of these target key conversation texts, the intelligent government affairs platform system can more accurately understand the needs of users and enterprises, so as to provide more efficient and accurate government affairs services.

[0029] Generally speaking, the intelligent government affairs platform system realizes the in-depth understanding and efficient processing of government affairs business conversations by obtaining and processing the intelligent government affairs business conversation text stream, mining the business interaction status knowledge vector chain therein, and then determining the semantic meaning of the target key conversation texts according to the status knowledge confidence of the vectors. This not only helps to improve the efficiency and quality of government affairs services, but also provides strong data support for government affairs decision-making.

[0030] In other application scenarios, it is possible to explore more deeply how the intelligent government affairs platform system processes the intelligent government affairs business conversation text stream and extracts valuable information from it.

[0031] In step 110, the intelligent government affairs platform system first obtains the intelligent government affairs business conversation text stream in real time or regularly from multiple channels (such as online government affairs service platforms, social media, emails, etc.). These text streams are the original records of the interactions between users, enterprises and the government, and contain a large amount of information. Once these text streams are obtained, the system uses the business interaction status mining node set to process them. These node sets are constructed based on advanced technologies such as machine learning and natural language processing (NLP), and they can identify and process various business interaction statuses in the text, such as consultations, applications, complaints, etc. The mining node set performs preprocessing operations such as word segmentation, part-of-speech tagging, and named entity recognition on the text stream to extract the key information in the text. Then, based on this information, the system constructs a business interaction status knowledge vector chain. Each knowledge vector represents a business interaction status in the text stream and contains information such as the characteristics and attributes of this status.

[0032] In step 120, after obtaining the business interaction status knowledge vector chain, the intelligent e-government platform system will further analyze these vectors to determine their status knowledge confidence levels. This is achieved by evaluating the heat of business elements in the vectors. The heat evaluation data of business elements is obtained by statistically analyzing business elements (such as keywords, phrases, etc.) in the text stream. The frequency of occurrence, location, and context relationship of these elements in the text will all be taken into account. By presenting the statistical results of these elements in the form of a heat map, it can be intuitively seen which elements are more important in the text. The status knowledge confidence level is calculated based on the heat evaluation data of business elements. It reflects the importance of the corresponding business interaction status knowledge vector in the text stream. Vectors with high confidence levels represent the core information in the text, while vectors with low confidence levels may be secondary or irrelevant information.

[0033] In step 130, finally, the intelligent e-government platform system will determine the target key session text semantics from the business interaction status knowledge vector chain according to the status knowledge confidence level. These semantics are the most valuable information in the text stream, directly reflecting the needs and intentions of users and enterprises. The process of determining the target key session text semantics may involve comprehensive analysis and comparison of multiple vectors. The system will select the most important semantics based on factors such as the confidence level and relevance of the vectors. These semantics may include users' consultation questions, enterprises' application matters, complaint content, etc. Once the target key session text semantics are determined, the intelligent e-government platform system can take corresponding actions based on this information. For example, automatically reply to users' consultation questions, process enterprises' application matters, forward complaint content to relevant departments, etc. In this way, the system can process the e-government business session text stream more efficiently, improving the efficiency and quality of e-government services.

[0034] Through the introduction of the above detailed steps, it can be more clearly understood how the intelligent e-government platform system processes the intelligent e-government business session text stream and mines valuable information from it. This process involves multiple advanced technologies and methods, such as machine learning, natural language processing, statistical analysis, etc. The application of these technologies enables the system to more accurately understand the needs of users and enterprises, providing strong support for e-government services.

[0035] The above technical solution will be introduced below through a more practical application scenario.

[0036] Application scenario: Intelligent processing of citizen complaints

[0037] Citizen Mr. Li found that the park near the community where he lives is dirty and messy, and the garbage has not been cleared for a long time. He decided to submit a complaint through the intelligent e-government platform, hoping that the relevant department can handle it as soon as possible.

[0038] 1) Submitting a complaint

[0039] Mr. Li accessed the online complaint system of the smart government affairs platform through his mobile phone or computer, filled in the complaint content, including the specific location of the park and a description of the garbage accumulation situation, and uploaded on-site photos as evidence.

[0040] 2) Obtain the text stream

[0041] After the smart government affairs platform system received Mr. Li's complaint, it incorporated it into the smart government affairs business conversation text stream. This text stream contains Mr. Li's complaint content, timestamp, and other relevant metadata.

[0042] 3) Mine the knowledge vector chain

[0043] The system processes the complaint text using the business interaction status mining node set. These node sets identify key information in the text, such as the complaint type (environmental hygiene), the complaint object (park), the problem description (garbage accumulation), etc., and construct a business interaction status knowledge vector chain based on this information.

[0044] 4) Determine the state knowledge confidence

[0045] The system further analyzes each vector in the knowledge vector chain and determines their state knowledge confidence based on the business element heat map evaluation data. In this example, since the complaint content is clear and the environmental hygiene problem involved is also a hot topic of concern to the public, the confidence of the relevant vectors is relatively high.

[0046] 5) Determine the semantics of the key conversation text

[0047] Based on the state knowledge confidence, the system determines the target key conversation text semantics from the knowledge vector chain, that is, the public's complaint about the environmental hygiene of the park. This is the most valuable information in the text stream, directly reflecting the needs and intentions of the public.

[0048] 6) Automatic classification and forwarding

[0049] The smart government affairs platform system automatically classifies the complaint as an environmental hygiene problem according to the determined semantics of the key conversation text and forwards it to the relevant department for handling. At the same time, the system will also generate an automatic reply to inform Mr. Li that his complaint has been received and is being processed.

[0050] 7) Processing and feedback

[0051] After receiving the complaint, the relevant department will quickly take action to clean up the garbage in the park and improve the environmental hygiene situation of the park. After the processing is completed, the department will send feedback to Mr. Li through the smart government affairs platform, informing him of the processing result and expressing gratitude.

[0052] Through this application scenario, it can be seen how the intelligent government affairs platform system uses the above technical solutions to intelligently process citizens' complaints. The system can accurately identify and understand citizens' needs and intentions, automatically classify and forward complaints to relevant departments for handling, thereby improving the efficiency and quality of government affairs services. At the same time, the system can also provide timely feedback to citizens, enhancing the interaction and trust between the government and citizens.

[0053] Next, name explanations will be provided for the technical terms that appeared in the above steps 110 - 130.

[0054] Intelligent government affairs business conversation text stream: It refers to the text information stream generated during the business interaction process between users (including citizens, enterprises, etc.) and government affairs staff or service systems on the intelligent government affairs service platform provided by the government. These text streams contain various business conversation contents such as user consultations, applications, feedbacks, complaints, etc. For example, in an online tax consultation system, the continuous text stream composed of questions raised by taxpayers, answers from tax officers, and prompt information automatically generated by the system.

[0055] Business interaction status mining node set: A set of processing nodes set up to analyze and mine the business interaction status in the intelligent government affairs business conversation text stream. Each node is responsible for identifying, extracting, or processing specific information or patterns in the text stream. For example, in a social security business processing system, the business interaction status mining node set may include nodes for identifying the type of user consultation, nodes for extracting key information, and nodes for judging user intentions, etc.

[0056] Business interaction status knowledge vector chain: A data structure obtained after being processed by the business interaction status mining node set, consisting of a series of knowledge vectors representing different business interaction statuses. Each knowledge vector contains information such as the characteristics and attributes of the corresponding business interaction status. For example, when processing the conversation text stream of a citizen applying for a passport, the business interaction status knowledge vector chain may contain knowledge vectors representing different interaction statuses such as "consulting the passport application process", "submitting application materials", "confirming application information", etc.

[0057] Target government affairs matter handling task: Specific government affairs service matters provided by the government, such as household registration, tax declaration, social security payment, etc. These tasks usually require users to submit logical texts through the intelligent government affairs platform and be processed by government departments to be completed. For example, the tax declaration task carried out by enterprise users through the intelligent government affairs platform includes steps such as filling out the tax return form, uploading relevant supporting documents, and confirming the declaration information.

[0058] Business Interaction Status Mining Node: A single node in the set of business interaction status mining nodes, responsible for processing specific parts or specific types of business interaction statuses in the intelligent government affairs business session text stream. Each node has its unique functions and processing logics. For example, in a provident fund query system, a business interaction status mining node may be specifically responsible for extracting provident fund account information from the user's query statement for subsequent query operations.

[0059] In the intelligent government affairs platform system, integration (consolidation) specifically refers to the process of uniformly managing and coordinating multiple business interaction status mining nodes. This means that data sharing, exchange, and interoperability need to be achieved among different nodes to ensure that the entire system can efficiently and accurately process complex government affairs business session text streams. For example, an intelligent government affairs platform needs to handle business consultations in multiple fields such as taxation, social security, and provident fund. To achieve this goal, the system needs to integrate (consolidate) the mining nodes responsible for identifying tax-related interaction statuses, the mining nodes responsible for processing social security-related interaction statuses, and the mining nodes responsible for provident fund-related interaction statuses. In this way, when a user raises a cross-domain consultation question, the system can coordinate the work of each node, extract all key information related to the question, and give a comprehensive and accurate answer. By integrating (consolidating) business interaction status mining nodes, the intelligent government affairs platform system can better respond to complex and changing government affairs business needs, improve service quality and efficiency. At the same time, this also requires the system to have strong data processing capabilities, flexible architecture designs, and clear business process plans.

[0060] Business Interaction Status Knowledge Vector: The business interaction status knowledge vector is a data structure used to represent and store knowledge related to business interaction statuses in the intelligent government affairs platform system. Each knowledge vector contains information such as the characteristics, attributes, and relationships of a specific business interaction status, which helps the system understand and process complex government affairs business sessions. For example, in the business process of a citizen applying for a passport, an interaction status of "submitting application materials" can be represented as a knowledge vector, which contains attribute information such as the type, quantity, and format of the application materials.

[0061] Business Element Heat Evaluation Data: Business element heat evaluation data refers to the data used to evaluate the importance and attention of business elements (such as keywords, phrases, etc.) in the intelligent government affairs business session text stream by analyzing statistical information such as the occurrence frequency, position, and context relationship of these elements. These data are usually presented in the form of heat maps, intuitively reflecting the heat of each business element. For example, in a tax consultation text stream, "tax declaration deadline" and "tax preferential policies" may be business elements with relatively high occurrence frequencies and high user attention, and their heat evaluation data will reflect the important status of these elements in the text.

[0062] State knowledge confidence: State knowledge confidence refers to the measure of the trust level or reliability of the intelligent government affairs platform system for a certain business interaction state knowledge vector. It is calculated based on information such as business element heat evaluation data and is used to assign different weights to different knowledge vectors during system decision-making. For example, if a business interaction state represented by a knowledge vector frequently appears in the text stream and is closely related to the user's core needs, then its state knowledge confidence will be relatively high.

[0063] Heat map statistical result: The heat map statistical result is the statistical analysis data presented in the form of a heat map, which is used to intuitively reflect the heat distribution of different business elements in the intelligent government affairs business conversation text stream. The depth of color or the size of the value in the heat map represents the importance and attention degree of each business element. For example, in the heat map statistical result of a social security business consultation text stream, it can be clearly seen that elements such as "pension receiving conditions" and "social security contribution ratio" are the hotspots of user consultation.

[0064] Importance degree: In the context of the intelligent government affairs platform system, the importance degree usually refers to the importance and influence of a certain business interaction state, business element or information in the overall business process or user needs. It can be quantitatively evaluated in various ways, such as frequency statistics, user feedback, etc. For example, in the business process of a citizen applying for a visa, information such as "visa application material list" and "visa processing duration" has a relatively high importance degree for the user because they are directly related to the success of the application and the user's itinerary arrangement.

[0065] Semantics of target key conversation text: The semantics of target key conversation text refers to the most representative and valuable core semantic information determined through system analysis and mining in the intelligent government affairs business conversation text stream. These information usually reflect the user's real needs, concerns or key links in business processing. For example, in a citizen complaint text stream, the semantics of target key conversation text may include key information points such as "complaint content", "complaint object", "expected solution method", etc., and these information are important bases for handling complaints and solving problems.

[0066] The intelligent government affairs platform system of this application has the following beneficial effects in processing the intelligent government affairs business conversation text stream:

[0067] Improve government affairs processing efficiency: By introducing the business interaction state mining node set, the system can automatically mine the business interaction state knowledge vector chain from the intelligent government affairs business conversation text stream. This processing method greatly reduces the workload of manual analysis and processing of the text stream, thereby improving the efficiency of government affairs processing;

[0068] Ensure information accuracy: The construction of the business interaction status knowledge vector chain is based on the business interaction status mining node sets, which are integrated according to the target government affair handling tasks. Such a design ensures that the mined information is closely related to the target government affairs, improving the accuracy of the information;

[0069] Optimize resource allocation: The system determines the status knowledge confidence of each knowledge vector according to the business element heat evaluation data in the business interaction status knowledge vector. This enables the system to prioritize the processing of those more important and urgent business interaction statuses, optimizing resource allocation and further enhancing the processing efficiency;

[0070] Enhance user experience: By accurately and quickly determining the semantics of the target key session text, the system can more precisely understand the needs and intentions of users, thus providing a more personalized and timely service response, significantly enhancing the user experience;

[0071] Enhance system flexibility: The intelligent government affairs platform system of this application can adapt to the changing requirements of different government affair handling tasks by integrating and consolidating different business interaction status mining nodes, demonstrating good scalability and flexibility.

[0072] In summary, the intelligent government affairs platform system of this application significantly improves the efficiency and quality of government affair processing through means such as automated mining, optimized resource allocation, and accurate understanding of user needs, while enhancing the flexibility and user-friendliness of the system.

[0073] In some preferred embodiments, the set of business interaction status mining nodes includes at least one or more business interaction status mining nodes such as a periodic linkage processing node, a matter linkage processing node, a user linkage processing node, a scenario linkage processing node, or an adjustable processing node. Mining the business interaction status knowledge vector chain from the intelligent government affairs business session text stream according to the set of business interaction status mining nodes includes at least one of the following: Mining the first business interaction status information continuously generated by the online business session within the target activation period from the intelligent government affairs business session text stream through the periodic linkage processing node, and determining the business interaction status knowledge vector of the first business interaction status information; or, mining the second business interaction status information continuously generated between different online business sessions from the intelligent government affairs business session text stream through the matter linkage processing node, and determining the business interaction status knowledge vector of the second business interaction status information; or, mining the third business interaction status information continuously and repeatedly generated by the online business session from the intelligent government affairs business session text stream through the user linkage processing node, and determining the business interaction status knowledge vector of the third business interaction status information; or, mining the fourth business interaction status information for realizing question-and-answer dialogue interaction in the target task process of the online business session from the intelligent government affairs business session text stream through the scenario linkage processing node, and determining the business interaction status knowledge vector of the fourth business interaction status information; or, mining the fifth business interaction status information generated by the online business session under the target government affair handling task from the intelligent government affairs business session text stream through the adjustable processing node, and determining the business interaction status knowledge vector of the fifth business interaction status information.

[0074] In some preferred embodiments, the design of the set of business interaction status mining nodes of the intelligent government affairs platform system is more detailed and comprehensive to meet the business interaction requirements in different situations. This set of nodes includes multiple business interaction status mining nodes such as a periodic linkage processing node, a matter linkage processing node, a user linkage processing node, a scenario linkage processing node, and an adjustable processing node. These nodes can mine the corresponding business interaction status knowledge vector chain from the intelligent government affairs business session text stream according to different business interaction characteristics.

[0075] Specifically, the system can mine the first business interaction status information continuously generated by the online business session within the target activation period from the intelligent government affairs business session text stream through the periodic linkage processing node. Here, the "target activation period" can be a preset time period, such as one day, one week, or one month, etc. Within this time period, the system will continuously monitor and analyze the online business session, extract the interaction status information related to the period, and determine the corresponding business interaction status knowledge vector accordingly.

[0076] In addition, the system can also extract the second business interaction status information continuously generated between different online business sessions from the intelligent government affairs business conversation text stream through the event linkage processing node. Here, "different online business sessions" refer to multiple business sessions initiated by multiple users or the same user at different time periods. The system will analyze the relevance and interaction status between these sessions, extract the interaction status information related to the event, and determine the corresponding business interaction status knowledge vector accordingly.

[0077] Furthermore, the user linkage processing node is responsible for extracting the third business interaction status information continuously and repeatedly generated in the online business session from the intelligent government affairs business conversation text stream. Here, "continuously and repeatedly generated" refers to the interaction status repeatedly mentioned or operated by the same user in the same business session. The system will identify and analyze the status and information of these repeated interactions, and extract the interaction status knowledge vector related to the user behavior.

[0078] The scenario linkage processing node focuses on extracting the fourth business interaction status information for question-and-answer dialogue interaction in the online business session during the target task process from the intelligent government affairs business conversation text stream. Here, the "target task process" refers to the specific processes and steps for users to handle government affairs. The system will analyze the question-and-answer dialogue interaction status and information of users in these processes and steps, and extract the interaction status knowledge vector related to the scenario.

[0079] Finally, the adjustable processing node is a more flexible node type, which can be customized and adjusted according to the specific requirements of government affairs handling tasks. Through the adjustable processing node, the system can extract the fifth business interaction status information generated in the online business session under the target government affairs handling task from the intelligent government affairs business conversation text stream. These information may involve multiple aspects such as user needs, business processes, policies and regulations, etc. The system will determine the corresponding business interaction status knowledge vector based on these information.

[0080] In summary, through these different types of business interaction status mining nodes, the intelligent government affairs platform system can more comprehensively and accurately extract the business interaction status knowledge vector chain from the intelligent government affairs business conversation text stream. This provides strong data support for subsequent business processing and summary generation, and helps to improve the efficiency and quality of government services.

[0081] In some other possible embodiments, the process of mining, by the periodic linkage processing node, the first service interaction status information continuously generated by the online service session within the target activation period from the intelligent government affairs service session text stream, and determining the service interaction status knowledge vector of the first service interaction status information includes at least one of the following: setting the periodic constraint value of the periodic linkage processing node; obtaining the detection results of each service interaction status information continuously generated by the online service session within the target activation period of the periodic constraint value; determining the service interaction status knowledge vector of the first service interaction status information based on the detection results; wherein, the detection results include at least one of the update times of each service interaction status information, the maximum status maintenance phase of each service interaction status information, the minimum status maintenance phase of each service interaction status information, or the generation result of each service interaction status information.

[0082] In some other possible embodiments, the intelligent government affairs platform system mines the first service interaction status information continuously generated by the online service session within the target activation period through the periodic linkage processing node, and determines the corresponding service interaction status knowledge vector accordingly. This process specifically includes the following steps.

[0083] First, the system sets the periodic constraint value of the periodic linkage processing node. This periodic constraint value is a preset time period that defines the length of the target activation period. For example, if the periodic constraint value is set to one day, then the system will focus on the service interaction status information continuously generated by the online service session within one day.

[0084] Next, the system obtains the detection results of each service interaction status information continuously generated by the online service session within the target activation period of the periodic constraint value. These detection results are obtained by real-time monitoring and analysis of the online service session, and they reflect the changes in each service interaction status within the target activation period.

[0085] The detection results may include various data such as the update times of each service interaction status information, the maximum status maintenance phase, the minimum status maintenance phase, and the generation result. Among them, the update times indicate the number of times a certain service interaction status information is updated within the target activation period; the maximum status maintenance phase and the minimum status maintenance phase respectively represent the state phases when a certain service interaction status information maintains the longest and shortest time within the target activation period; the generation result reflects the final state of a certain service interaction status information within the target activation period.

[0086] Then, the system will determine the business interaction status knowledge vector of the first business interaction status information based on these detection results. This process may involve operations such as statistics, analysis, and induction of the detection results to extract the key interaction status information related to the target government affairs handling task. For example, the system may judge the importance and urgency of a certain business interaction status information according to the data of the update times and the status maintenance stage, and then generate the corresponding business interaction status knowledge vector.

[0087] Finally, these business interaction status knowledge vectors will be used in subsequent business processing and summary generation tasks. They can help the system more accurately understand the user's needs and intentions, and improve the efficiency and quality of government services. At the same time, since these knowledge vectors are obtained based on the actual online business session data, they also have strong practicality and pertinence.

[0088] To facilitate the understanding of the above embodiments, a more detailed exemplary introduction is given below.

[0089] In the intelligent government affairs platform system, the periodic linkage processing node is a key component, which is responsible for mining the business interaction status information within a specific period from the online business session text stream. These information are crucial for understanding user behavior and optimizing service processes.

[0090] 1. Set the periodic constraint value of the periodic linkage processing node

[0091] Periodic constraint value: This is a time parameter used to define the "target activation period" of the online business sessions that the system focuses on. In other words, it stipulates the time range for the system to analyze the session text stream. For example, if the periodic constraint value is set to 24 hours, the system will only analyze the session data within the past 24 hours.

[0092] The system administrator or automated script will set this periodic constraint value according to business requirements. Different government affairs may require different periodic constraint values to more accurately capture the dynamic changes of user interactions.

[0093] 2. Obtain the detection results of the online business sessions

[0094] Once the periodic constraint value is set, the system will start monitoring and analyzing the online business sessions within the target activation period. These sessions may come from multiple channels (such as websites, mobile applications, social media, etc.) and involve different users and business scenarios.

[0095] Business interaction status information: This refers to the information left by the interaction behaviors of users with the system or other users during the process of handling government affairs. These information may include various forms such as text, voice, and images, reflecting the states of user operations, inquiries, feedback, etc.

[0096] Detection result: This is the result obtained by the system after analyzing the business interaction status information. It may contain data in multiple dimensions, such as the number of updates, the status maintenance stage, etc.

[0097] Number of updates: It refers to the number of times a certain business interaction status information is modified or updated within the target activation period. Frequent updates may indicate that users highly concern this matter or encounter some problems.

[0098] Maximum / minimum status maintenance stage: It refers to the longest / shortest time period during which a certain business interaction status information remains unchanged within the target activation period. This can help the system identify the stable and changing periods of user interaction.

[0099] 3. Determine the business interaction status knowledge vector based on the detection result

[0100] Business interaction status knowledge vector: This is a multi-dimensional data structure used to represent the key interaction status information mined from online business sessions. It may include multiple aspects such as user behavior patterns, demand preferences, service satisfaction, etc.

[0101] The system will construct or update the business interaction status knowledge vector according to the detection result. For example, if the number of updates of a certain business interaction status information is extremely high, the system may mark it as "high attention" or "potential problem" and increase the corresponding weight in the knowledge vector.

[0102] These knowledge vectors are crucial for subsequent business processing. They can help the system more accurately understand user needs, predict user behavior, optimize service processes, etc. For example, by identifying frequent problems and demands, the system can automatically recommend relevant solutions or guide users to more appropriate service channels.

[0103] Through the above detailed explanations and glossary, it can be seen the important role of the cycle linkage processing node in the intelligent government affairs platform system. It can not only mine valuable information from a large number of online business sessions, but also convert this information into actionable knowledge vectors, providing strong support for improving the quality and efficiency of government affairs services.

[0104] In an alternative design idea, determining the state knowledge confidence of each business interaction state knowledge vector based on the business element heat evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain includes: creating a first reference key text content and a second reference key text content based on the target government affair handling task, where the first reference key text content is composed of business interaction state knowledge vectors without popular topics in the target government affair handling task, and the second reference key text content is composed of business interaction state knowledge vectors with popular topics in the target government affair handling task; determining the business element heat evaluation data of each business interaction state knowledge vector in the first reference key text content and the second reference key text content in the business interaction state knowledge vector chain; and determining the state knowledge confidence of each business interaction state knowledge vector based on the business element heat evaluation data of the business interaction state knowledge vector.

[0105] In an alternative design idea, the intelligent government affair platform system will evaluate the state knowledge confidence of business interaction state knowledge vectors through specific methods. This process is mainly based on the business element heat evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain. The following are the detailed implementation steps.

[0106] First of all, the system will create two reference key text contents according to the target government affair handling task: the first reference key text content and the second reference key text content. There are obvious differences in their compositions. The first reference key text content is mainly composed of those business interaction state knowledge vectors without popular topics in the target government affair handling task. In other words, it contains relatively unpopular or less concerned information points. On the contrary, the second reference key text content is composed of those business interaction state knowledge vectors with popular topics in the target government affair handling task, that is, it contains information points that the public generally cares about or frequently discusses.

[0107] Next, the system will determine the business element heat evaluation data of each business interaction state knowledge vector in these two reference key text contents. The "business element heat evaluation data" here can be understood as the matching degree or correlation index between a certain business interaction state knowledge vector and the reference key text content. It may be obtained through algorithms such as text analysis and semantic comparison, and the specific value reflects the importance or influence of the knowledge vector in the corresponding text content.

[0108] Finally, based on these heat evaluation data of business elements, the system will determine the state knowledge confidence of each business interaction state knowledge vector. This confidence can be regarded as a comprehensive evaluation index for the accuracy and reliability of a certain business interaction state knowledge vector. It may comprehensively consider the performance of the knowledge vector in multiple dimensions, such as the degree of association with hot topics, the frequency of occurrence in the text content, the influence on other information, etc. Through this method, the system can more comprehensively evaluate the value of each business interaction state knowledge vector, providing more powerful support for subsequent business processing and decision-making.

[0109] It should be noted that the evaluation method under this design idea depends on high-quality reference key text content and accurate and effective heat evaluation algorithms for business elements. Therefore, in practical applications, the system may need to continuously optimize and adjust these reference texts and evaluation algorithms to adapt to the needs and changes of different government affairs handling tasks. At the same time, in order to improve the accuracy and reliability of the evaluation results, the system can also consider introducing other auxiliary information or expert opinions for comprehensive analysis.

[0110] In the next step, determining the heat evaluation data of business elements of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the first reference key text content and the second reference key text content includes: counting the cumulative value of the existence of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the first reference key text content as the first detection variable, and counting the cumulative value of the existence of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the second reference key text content as the second detection variable; determining the total number of business interaction state knowledge vectors included in the first reference key text content as the third detection variable, and determining the total number of business interaction state knowledge vectors included in the second reference key text content as the fourth detection variable; based on the first detection variable and the third detection variable, determining the first operation result between the cumulative value of the existence of each business interaction state knowledge vector in the first reference key text content and the total number of business interaction state knowledge vectors included in the first reference key text content; based on the second detection variable and the fourth detection variable, determining the second operation result between the cumulative value of the existence of each business interaction state knowledge vector in the second reference key text content and the total number of business interaction state knowledge vectors included in the second reference key text content; based on the first operation result and the second operation result, determining the heat evaluation data of business elements of each business interaction state knowledge vector in the first reference key text content and the second reference key text content.

[0111] In the following steps, the system will determine the business element heat evaluation data of the business interaction status knowledge vector in the first reference key text content and the second reference key text content through a series of calculation and evaluation operations. The following are the detailed implementation steps.

[0112] First, the system will count the cumulative value of each business interaction status knowledge vector in the business interaction status knowledge vector chain that exists in the first reference key text content. This value is called the first detection variable. This cumulative value may be obtained by calculating the frequency, duration, importance weight, etc. of the knowledge vector in the text content, reflecting the coverage and influence of the knowledge vector in the first reference key text content.

[0113] Similarly, the system will also count the cumulative value of each business interaction status knowledge vector in the business interaction status knowledge vector chain that exists in the second reference key text content. This value is called the second detection variable. The calculation method of this cumulative value is similar to that of the first detection variable, but it is for the second reference key text content.

[0114] Next, the system will determine the total number of business interaction status knowledge vectors contained in the first reference key text content. This number is called the third detection variable. This total number reflects the richness and coverage of the first reference key text content.

[0115] Similarly, the system will also determine the total number of business interaction status knowledge vectors contained in the second reference key text content. This number is called the fourth detection variable. This total number also reflects the richness and coverage of the second reference key text content.

[0116] Then, based on the first detection variable and the third detection variable, the system will calculate the first operation result between the cumulative value of each business interaction status knowledge vector in the business interaction status knowledge vector chain that exists in the first reference key text content and the total number of business interaction status knowledge vectors contained in the first reference key text content. This operation result may be a ratio, ranking, or other form of numerical value, used to measure the relative importance and influence of the knowledge vector in the first reference key text content.

[0117] Similarly, based on the second detection variable and the fourth detection variable, the system will calculate the second operation result between the cumulative value of each business interaction status knowledge vector in the business interaction status knowledge vector chain that exists in the second reference key text content and the total number of business interaction status knowledge vectors contained in the second reference key text content. This operation result is also used to measure the relative importance and influence of the knowledge vector in the second reference key text content.

[0118] Finally, based on the first operation result and the second operation result, the system will determine the business element heat evaluation data of each business interaction status knowledge vector in the first reference key text content and the second reference key text content. This evaluation data may be a comprehensive score, rating, or other form of indicator, used to comprehensively evaluate the overall performance and value of the knowledge vector in the two reference key text contents.

[0119] Through such a calculation and evaluation process, the system can more accurately understand the importance and influence of each business interaction status knowledge vector in different text contents, providing more powerful data support for subsequent business processing and decision-making.

[0120] For ease of understanding, the calculation process can be introduced in more detail through formulas. The following is the formula representation based on the foregoing description:

[0121] 1. Define variables

[0122] (V_{ik}): The cumulative value of the (i)-th knowledge vector in the business interaction status knowledge vector chain in the (k)-th reference key text content ((k = 1) is the first reference key text content, (k = 2) is the second reference key text content).

[0123] (T_k): The total number of business interaction status knowledge vectors contained in the (k)-th reference key text content.

[0124] 2. Calculate detection variables

[0125] For each knowledge vector (i), it is necessary to calculate its cumulative values (V_{i1}) and (V_{i2}) in the two reference key text contents, as well as the total numbers (T_1) and (T_2) of knowledge vectors in the two reference key text contents.

[0126] 3. Calculate operation results

[0127] The first operation result ((R_{i1})): Represents the importance of the (i)-th knowledge vector in the first reference key text content. It can be calculated by the following formula:

[0128] [R_{i1}=frac{V_{i1}}{T_1}]

[0129] Here, (R_{i1}) is the ratio of the cumulative value of the (i)-th knowledge vector in the first reference key text content to the total number, reflecting the relative importance of the knowledge vector in the first text.

[0130] The second operation result ((R_{i2})): Represents the importance of the (i)-th knowledge vector in the second reference key text content. It can be calculated by the following formula:

[0131] [R_{i2}=frac{V_{i2}}{T_2}]

[0132] Similarly, (R_{i2}) is the ratio of the cumulative value of the (i)-th knowledge vector in the second reference key text content to the total number, reflecting the relative importance of the knowledge vector in the second text.

[0133] 4. Determine the heat map evaluation data of business elements

[0134] The heat map evaluation data of business elements ((H_i)) can be determined based on a certain combination of the first operation result and the second operation result. For example, the global average measurement index of the two can be simply taken, or weighted averaging can be performed by assigning different weights according to business requirements.

[0135] [H_i=A·R_{i1}+B·R_{i2}]

[0136] Among them, (A) and (B) are weight coefficients, which are set according to specific circumstances, and (A + B = 1).

[0137] If both (A) and (B) are set to 0.5, it means that their importance is the same. If a certain reference key text content is considered more important, the weights can be adjusted accordingly.

[0138] Through these formulas, the system can quantify the importance of each business interaction status knowledge vector in different reference key text contents, and perform subsequent business processing and decision support based on this.

[0139] In a preferred technical solution, for the heat map evaluation data of business elements based on the business interaction status knowledge vector, determining the status knowledge confidence of each business interaction status knowledge vector includes: performing interval numerical mapping processing on the heat map evaluation data of the business interaction status knowledge vector to obtain the interval numerical mapping result of the heat map evaluation data of the business elements; performing feature transformation processing based on the interval numerical mapping result of the heat map evaluation data of the business elements, and using the obtained feature transformation result as the status knowledge confidence of each business interaction status knowledge vector.

[0140] In a preferred technical solution, the system will determine the status knowledge confidence of each business interaction status knowledge vector through a series of processing steps. The following are the detailed implementation steps.

[0141] First, the system performs interval numerical mapping processing on the business element heat evaluation data of the business interaction status knowledge vector. Interval numerical mapping is a technique that maps original data into a specific interval, usually used for data normalization or standardization. In this step, the system maps the business element heat evaluation data of each business interaction status knowledge vector into a preset numerical interval to obtain the interval numerical mapping result of the business element heat evaluation data.

[0142] This preset numerical interval can be set according to actual needs. For example, it can be set between 0 and 1, or other numerical ranges. The mapping process can be achieved through linear transformation, non-linear transformation, etc., depending on the distribution characteristics of the data and business requirements.

[0143] Next, the system performs feature transformation processing based on the interval numerical mapping result of the business element heat evaluation data. Feature transformation is a method of converting original features into a feature representation that is more conducive to model learning. In this step, the system further converts the interval numerical mapping result into a feature form that is more suitable for representing the confidence of state knowledge.

[0144] The specific method of feature transformation can be selected according to actual needs. For example, methods such as normalization, standardization, and discretization can be used. The transformed features will be more able to reflect the importance and confidence of the business interaction status knowledge vector, providing more powerful support for subsequent business processing and decision-making.

[0145] Finally, the system uses the obtained feature transformation result as the state knowledge confidence of each business interaction status knowledge vector. This state knowledge confidence is a comprehensive evaluation index used to measure the accuracy and reliability of each business interaction status knowledge vector. It can be used in multiple aspects such as subsequent business decision-making, recommendation systems, and risk assessment, helping the system better understand and utilize the information in the business interaction status knowledge vector.

[0146] Through such processing steps, the system can more accurately evaluate the state knowledge confidence of each business interaction status knowledge vector, providing more powerful data support for subsequent business processing and decision-making. At the same time, this technical solution also has a certain degree of flexibility and scalability, and can be adjusted and optimized according to different business requirements and data characteristics.

[0147] In some exemplary embodiments, determining the target key session text semantics from the business interaction status knowledge vector chain based on the status knowledge confidence includes: determining the semantic feature dimensions of the target key session text semantics based on the target government affair handling task; determining the confidence interval of the status knowledge confidence of the candidate target key session text semantics based on the semantic feature dimensions; and determining the target key session text semantics from each business interaction status knowledge vector in the business interaction status knowledge vector chain based on the confidence interval.

[0148] In some exemplary embodiments, the system determines the target key session text semantics according to the status knowledge confidence. The following are the detailed implementation steps.

[0149] First, the system determines the semantic feature dimensions of the target key session text semantics based on the target government affair handling task. The semantic feature dimensions are multiple aspects or angles for describing and measuring the text semantics, such as the theme, sentiment, entities, etc. of the text. In this step, the system selects the relevant semantic feature dimensions according to the requirements and characteristics of the specific government affair handling task for subsequent text semantic analysis and determination.

[0150] Next, the system determines the confidence interval of the status knowledge confidence of the candidate target key session text semantics based on the determined semantic feature dimensions. The confidence interval is a concept in statistics used to estimate the range within which the true value of a parameter may exist, and here it is used to measure the reliability and accuracy of the status knowledge confidence. The system calculates a reasonable confidence interval according to the selected semantic feature dimensions and the corresponding status knowledge confidence for screening the target key session text semantics that meet the conditions.

[0151] Finally, the system determines the target key session text semantics from each business interaction status knowledge vector in the business interaction status knowledge vector chain based on the determined confidence interval. Specifically, the system traverses each business interaction status knowledge vector in the business interaction status knowledge vector chain and calculates whether its status knowledge confidence falls within the determined confidence interval. If the status knowledge confidence of a certain business interaction status knowledge vector falls within the confidence interval and its corresponding text semantics match the selected semantic feature dimensions, then the system determines it as the target key session text semantics.

[0152] It should be noted that in practical applications, the system may flexibly adjust and optimize the above steps according to specific business requirements and data characteristics. For example, a more complex semantic analysis model can be adopted to improve the accuracy of text semantic recognition, or the setting of the confidence interval can be dynamically adjusted according to historical data, etc.

[0153] Through such a processing flow, the system can more accurately determine the key session text semantics related to the target government affair handling task from the business interaction status knowledge vector chain, providing strong support for subsequent business processing and decision-making.

[0154] In some optional design examples, the method further includes: updating the priority of each intelligent government affair business session text in the intelligent government affair business session text stream according to the priority of session output; performing joint semantic embedding on each intelligent government affair business session text after priority update; and cleaning the noise business session text in the intelligent government affair business session text stream.

[0155] In some optional design examples, the system will further optimize the intelligent government affair business session text stream, specifically including the following steps.

[0156] First, the system will update the priority of each intelligent government affair business session text in the intelligent government affair business session text stream according to the priority of session output. The priority of session output is comprehensively determined according to factors such as business requirements, user level, and urgency of session content. In this step, the system will evaluate each intelligent government affair business session text and update its priority according to the evaluation result. The update of priority can adopt a dynamic adjustment method to adapt to business requirements in different situations.

[0157] For example, for the intelligent government affair business session text involving important matters or emergencies, the system may increase its priority to ensure that these sessions can be processed in a timely manner. For some regular or low-urgency sessions, the system may reduce their priority and arrange them to be processed at a later time.

[0158] Secondly, the system will perform joint semantic embedding on each intelligent government affair business session text after priority update. Joint semantic embedding is a method of mapping multiple texts into the same semantic space for comparison and association at the semantic level. In this step, the system will use a pre-trained semantic embedding model or algorithm to convert each intelligent government affair business session text into a vector representation and embed these vectors into the same semantic space.

[0159] Through joint semantic embedding, the system can more accurately understand the semantic relationships and similarities between each intelligent government affair business session text, providing richer semantic information for subsequent session processing. This helps the system better grasp user needs and intentions, improving the accuracy and efficiency of business processing.

[0160] Finally, the system will clean the noisy business conversation texts in the intelligent government affairs business conversation text stream. Noisy business conversation texts refer to those conversation texts that are irrelevant to business processing, contain errors or redundant information. These texts may interfere with the normal processing of the system and reduce the accuracy and efficiency of business processing. Therefore, the system needs to identify and clean them.

[0161] During the cleaning process, the system can adopt rule-based methods, machine learning-based methods, or a combination of both to identify and filter out noisy business conversation texts. For example, the system can formulate some rules to identify common noisy text patterns, or use machine learning algorithms to train classifiers to automatically identify and filter noisy texts. Through the cleaning process, the system can retain valuable intelligent government affairs business conversation texts and improve the quality and efficiency of subsequent business processing.

[0162] In some alternative embodiments, the method further includes steps 210 - 220.

[0163] Step 210: Input the semantics of the target key conversation text into a deep structured semantic model to create a business text summary generation network.

[0164] Step 220: Input the intelligent government affairs business conversation text to be processed in the online business conversation to be processed into the business text summary generation network to obtain the business text summary of the online business conversation to be processed.

[0165] In some alternative embodiments, the intelligent government affairs platform system further expands its functions, including steps 210 and 220, to achieve automatic summary generation of the online business conversation to be processed. The following is a detailed example explanation of these steps.

[0166] In step 210, input the semantics of the target key conversation text into a deep structured semantic model to create a business text summary generation network.

[0167] In this step, the intelligent government affairs platform system takes the semantics of the previously determined target key conversation text as input and inputs it into a deep structured semantic model. This model is a trained deep learning network that can deeply understand and structurally process the input text semantics. Through this process, the system can capture the core information and semantic structure in the text, providing a basis for subsequent summary generation.

[0168] The deep structured semantic model contains multiple processing layers, and each processing layer is responsible for extracting different levels of features of the text. These features include but are not limited to lexical features, syntactic features, semantic roles, etc. By extracting and integrating these features layer by layer, the model can construct a comprehensive and refined text representation that not only retains the key information of the original text but also facilitates subsequent processing and analysis.

[0169] After the semantic information of the target key session text is input into the deep structured semantic model, the system will use this model to create a business text summary generation network. This network is specifically designed to process the intelligent government affairs business session text and can automatically generate a concise and accurate business text summary according to the input text semantics.

[0170] In step 220, the to-be-processed intelligent government affairs business session text of the to-be-processed online business session is input into the business text summary generation network to obtain the business text summary of the to-be-processed online business session.

[0171] After creating the business text summary generation network, the intelligent government affairs platform system can start processing the to-be-online business session. When the system receives a new to-be-processed intelligent government affairs business session text, it will input this text into the previously created summary generation network.

[0172] The summary generation network will first preprocess the input text, including operations such as word segmentation, stop word removal, and normalization, so as to convert the text into a format suitable for model processing. Then, the network will use the deep structured semantic model to perform in-depth semantic analysis and structured processing on the processed text, and extract the key information and semantic structure in the text.

[0173] Next, the summary generation network will generate a concise and accurate business text summary according to the extracted key information and semantic structure. This summary contains the core content and key information in the original text but removes the redundant and secondary parts, enabling users to quickly understand the main content and key points of the session.

[0174] Finally, the intelligent government affairs platform system will return the generated business text summary to the user or store it in the system for subsequent use. In this way, users can quickly understand the main content and processing results of the to-be-processed online business session by viewing the summary.

[0175] Through the implementation of the above step 210 and step 220, the intelligent government affairs platform system can realize the function of automatically generating summaries for to-be-processed online business sessions, thereby improving the efficiency and quality of government affairs processing.

[0176] In some other embodiments, the method further includes: creating first reference key text content and second reference key text content according to a target government affair handling task; determining a derived target key session text semantics based on the first reference key text content and the second reference key text content; wherein, the derived target key session text semantics is used to create a derived business text summary generation network that matches the target government affair handling task, so that the derived business text summary generation network determines a business text summary of the to-be-processed online business session under the target government affair handling task.

[0177] In some other embodiments, the intelligent government affairs platform system further enhances its function by creating reference key text content to determine a derived target key session text semantics, and accordingly creating a derived business text summary generation network that matches a specific government affair handling task. The following is a detailed illustrative explanation.

[0178] First, the system creates first reference key text content and second reference key text content according to a target government affair handling task. These reference key text contents are obtained based on an in-depth understanding and analysis of the target government affair handling task, and they include key information, business processes, policies and regulations, etc. that may be involved in handling this task. The first reference key text content and the second reference key text content may focus on different aspects respectively. For example, the first reference key text content may focus more on user needs and business processes, while the second reference key text content may focus more on policies and regulations and business norms.

[0179] Next, the system determines a derived target key session text semantics based on the first reference key text content and the second reference key text content. This process may involve technical means such as in-depth parsing, information extraction, and semantic fusion of the reference key text content. Through this process, the system can generate a comprehensive, accurate, and closely related derived target key session text semantics for the target government affair handling task.

[0180] This derived target key session text semantics plays a crucial role in the subsequent steps. The system uses it to create a derived business text summary generation network that matches the target government affair handling task. This network is designed specifically for processing business session texts under a specific government affair handling task, and it can automatically generate concise and accurate business text summaries according to the input session texts.

[0181] When the system receives a new online business session to be processed, it enters the session text into the previously created derived business text summary generation network. The network will first preprocess and analyze the input text to extract key information and features. Then, it will use the derived semantic of the target key session text to guide the summary generation process, ensuring that the generated summary is closely related to the target government affairs matter handling task and accurately reflects the core content and key points of the original session text.

[0182] Finally, the system will return the generated business text summary to the user or store it in the system for subsequent use. In this way, users can quickly understand the main content and processing results of the online business session to be processed under the target government affairs matter handling task by viewing the summary.

[0183] In this way, the intelligent government affairs platform system can more accurately process and analyze the business session text under specific government affairs matter handling tasks, improving the efficiency and quality of government services. At the same time, since the summary generation network is derived for specific tasks, it has stronger pertinence and adaptability, and can better meet the needs and expectations of users.

[0184] It should be noted that determining the semantic of the derived target key session text is the core innovation point in this application, and it is crucial for enhancing the processing ability and service quality of the intelligent government affairs platform system. The following will introduce this core invention point in more detail to ensure its readability and coherence.

[0185] In the intelligent government affairs platform system, determining the semantic of the derived target key session text is a complex and delicate process. This process aims to extract the most critical and representative semantic information from a vast amount of government affairs business session text to guide subsequent business processing and summary generation.

[0186] First, the system will conduct an in-depth analysis and understanding of the target government affairs matter handling task. This includes a comprehensive review and interpretation of aspects such as the nature, purpose, involved business processes, policies and regulations of the task. Through this process, the system can establish a comprehensive understanding of the target task, providing a solid foundation for determining the semantic of the subsequent key session text.

[0187] Next, based on the understanding of the target task, the system will create the first reference key text content and the second reference key text content. These two parts of content describe and define the target task from different perspectives and emphases. For example, the first reference key text content may focus on describing user needs and business processes, while the second reference key text content may pay more attention to policies and regulations and business norms. These two parts of content complement each other and jointly constitute a complete description of the target task.

[0188] Then, the system will apply advanced natural language processing techniques and deep learning algorithms to deeply analyze and extract information from the first reference key text content and the second reference key text content. This process includes multiple steps such as lexical analysis, syntactic analysis, and semantic role labeling, aiming to extract key information elements and semantic structures from the text.

[0189] After extracting the key information, the system will further perform semantic fusion and reasoning. It will combine the context information and domain knowledge to integrate and reason about the extracted key information, generating a derivative target key conversation text semantics that is comprehensive, accurate, and closely related to the target government affairs handling task. This semantics not only contains the key information in the original text but also incorporates the system's understanding and reasoning results of the target task.

[0190] Finally, this derivative target key conversation text semantics will be used to guide subsequent business processing and summary generation. The system will create a derivative business text summary generation network that matches the target government affairs handling task based on this semantics. This network can automatically generate a concise and accurate business text summary according to the input conversation text, helping users quickly understand the main content and processing results of the conversation.

[0191] In summary, determining the derivative target key conversation text semantics is the core innovation point in this application. It generates a comprehensive, accurate, and closely related derivative target key conversation text semantics to the target task through in-depth understanding and analysis of the target government affairs handling task, combined with natural language processing techniques and deep learning algorithms. This semantics provides strong guidance for subsequent business processing and summary generation, improving the processing ability and service quality of the intelligent government affairs platform system.

[0192] In an independent embodiment, after inputting the to-be-processed intelligent government affairs business conversation text of the to-be-processed online business conversation into the business text summary generation network to obtain the business text summary of the to-be-processed online business conversation, the method includes: determining at least one structured semantic tree of the to-be-processed online business conversation and the storage guidance feature of each structured semantic tree according to the business text summary, where each structured semantic tree includes a conversation semantic block of the to-be-processed online business conversation; for each structured semantic tree, inputting the structured semantic tree and the corresponding storage guidance feature into a text storage optimization network to obtain an initial structured conversation text after updating the structured semantic tree; performing text repetition on the corresponding initial structured conversation text according to the structured semantic tree to obtain a target structured conversation text after updating the structured semantic tree; and performing structured storage on the to-be-processed online business conversation according to the target structured conversation texts corresponding to each structured semantic tree.

[0193] In an independent embodiment, the system details the processing flow for the online business session to be processed. The following are the specific steps and explanations of this embodiment.

[0194] First, the system inputs the text of the online business session to be processed, specifically the text of the intelligent government affairs business session to be processed, into the business text summary generation network to obtain the business text summary of the online business session to be processed. The business text summary generation network is a deep learning model that can perform semantic understanding and information extraction on the input session text, generating a concise summary that contains key information.

[0195] Next, the system determines at least one structured semantic tree of the online business session to be processed and the storage guidance features of each structured semantic tree based on the business text summary. The structured semantic tree is a structured representation of the session text that can clearly reflect the semantic structure and information hierarchy in the text. The storage guidance features are the feature information used to guide text storage, such as the importance and urgency of the text.

[0196] Then, for each structured semantic tree, the system inputs the structured semantic tree and the corresponding storage guidance features into the text storage optimization network to obtain the initial structured session text after updating the structured semantic tree. The text storage optimization network is a deep learning model that can optimize the session text according to the input structured semantic tree and storage guidance features, generating an initial structured session text that is more suitable for storage and retrieval.

[0197] After that, the system performs text paraphrasing on the corresponding initial structured session text according to the structured semantic tree to obtain the target structured session text after updating the structured semantic tree. Text paraphrasing is a natural language processing technique that can rephrase the text while maintaining the original meaning. Through text paraphrasing, the system can further optimize the expression of the initial structured session text, improving the readability and comprehensibility of the text.

[0198] Finally, the system performs structured storage on the online business session to be processed according to the target structured session texts corresponding to the structured semantic trees. Structured storage is a way of storing text data in a certain structure and format, which can improve the organization and retrievability of data. Through structured storage, the system can save the online business session to be processed in a clearer and more organized manner, providing convenience for subsequent business processing and decision support.

[0199] In an independent embodiment, the storage guidance features of each of the structured semantic trees include at least one of the following: logical text for describing the conversational semantic blocks of the structured semantic tree; logical text for prompting the structured labels of the initial structured conversation text corresponding to the structured semantic tree.

[0200] In an independent embodiment, the system defines specific storage guidance features for each structured semantic tree. These storage guidance features play a crucial role in the structured storage process of conversation text, helping the system to understand and organize text data more accurately. The following is a detailed explanation of these storage guidance features.

[0201] First, the storage guidance features of each structured semantic tree may include logical text for describing the conversational semantic blocks of the structured semantic tree. Conversational semantic blocks are the smallest units with independent meanings in conversation text, which may be a sentence, a phrase, or a word. Logical text is an abstract description of these conversational semantic blocks, which summarizes the main content and function of the semantic blocks in concise language. Through the logical text, the system can quickly identify and understand the key information in the conversation text, facilitating subsequent storage and retrieval.

[0202] For example, in a conversation about consulting government affairs, a conversational semantic block may be "asking about the conditions and procedures for applying for a residence permit". The corresponding logical text can be "Consultation on the conditions and procedures for applying for a residence permit", which concisely summarizes the theme and content of the semantic block.

[0203] Second, the storage guidance features may also include logical text for prompting the structured labels of the initial structured conversation text corresponding to the structured semantic tree. Structured labels are a way of marking different parts of the conversation text, which can help the system better organize and understand the structure and hierarchy of the text. Logical text is an explanation and description of these structured labels, which describes the meaning and function of the labels in easy-to-understand language.

[0204] Taking the same government affairs consultation conversation as an example, assuming that the conversation text is marked with three structured labels: "question", "answer", and "matters needing attention". The corresponding logical texts can be "Questions raised by users", "Answers given by staff", and "Matters needing attention during the handling process". These logical texts clearly describe the content and function represented by each label, helping the system to understand and store the structured information of the conversation text more accurately.

[0205] In summary, by defining storage guiding features including logical text for each structured semantic tree, the system can more accurately identify, understand, and store the key information and structured information in the conversation text. This helps improve the organization, retrievability, and comprehensibility of the conversation text, providing strong support for subsequent business processing and decision-making.

[0206] In an independent embodiment, for each of the structured semantic trees, the text retelling of the corresponding initial structured conversation text according to the structured semantic tree to obtain the target structured conversation text after updating the structured semantic tree includes: determining the initial structural text features of each semantic tree branch of the structured semantic tree and the initial structural text features of each semantic tree branch of the corresponding initial structured conversation text; determining the first transitional structured conversation text, where the initial structural text features of each semantic tree branch of the first transitional structured conversation text are the difference between the initial structural text features of the same semantic tree branch of the structured semantic tree and the initial structural text features of the same semantic tree branch of the corresponding initial structured conversation text; setting the initial structural text features of the first semantic tree branch in the first transitional structured conversation text as the first feature variable to obtain the second transitional structured conversation text, where the initial structural text features of the first semantic tree branch are greater than the preset feature variable; performing dilated convolution on the second transitional structured conversation text to obtain the third transitional structured conversation text, and obtaining the target structured conversation text after updating the structured semantic tree according to the structured semantic tree and the third transitional structured conversation text.

[0207] In an independent embodiment, the system deeply processes the structured semantic tree and the corresponding initial structured conversation text to generate the updated target structured conversation text. The following is a detailed step-by-step explanation.

[0208] First, the system determines the initial structural text features of each semantic tree branch of each structured semantic tree and the initial structural text features of each semantic tree branch of the corresponding initial structured conversation text. Semantic tree branches are different parts of the structured semantic tree, and each part represents a specific meaning or topic in the conversation text. Initial structural text features are the preliminary descriptions and measurements of these semantic tree branches, which can include features such as vocabulary, grammar, and semantics.

[0209] Next, the system determines a first transitional structured conversation text. The characteristic of this transitional text is that the initial structural text features of each semantic tree branch are the differences between the initial structural text features of the same semantic tree branch in the structured semantic tree and the initial structural text features of the corresponding initial structured conversation text in the same semantic tree branch. That is to say, the system obtains an intermediate state text by calculating the differences, and this text is related to both the original structured semantic tree and the initial structured conversation text in terms of structure.

[0210] Then, the system sets the initial structural text features of the first semantic tree branch in the first transitional structured conversation text as the first feature variable to obtain a second transitional structured conversation text. Here, the first semantic tree branches refer to those branches whose initial structural text features are greater than the preset feature variable. The first feature variable is a preset threshold or criterion for screening and adjusting text features. Through this step of processing, the system can further adjust and optimize the structure and features of the transitional text.

[0211] Next, the system performs a dilated convolution operation on the second transitional structured conversation text to obtain a third transitional structured conversation text. Dilated convolution is a special convolution operation that can expand the receptive field without increasing the model complexity, thereby capturing more context information. Here, the system uses dilated convolution to further extract and integrate the key information in the transitional text to generate a more accurate and coherent text.

[0212] Finally, the system obtains the target structured conversation text after updating the structured semantic tree based on the original structured semantic tree and the third transitional structured conversation text processed by dilated convolution. This target text not only retains the key information and structural features of the original conversation text but also improves the quality and readability of the text through a series of processing and optimization operations. At the same time, it also provides a more valuable data basis for subsequent business processing and decision support.

[0213] In an independent embodiment, for each of the structured semantic trees, obtaining the target structured conversation text after updating the structured semantic tree according to the structured semantic tree and the third transitional structured conversation text includes: determining a first discrete measurement index and a first global average measurement index of the initial structural text features of each semantic tree branch of the structured semantic tree; determining a second discrete measurement index and a second global average measurement index of the initial structural text features of each semantic tree branch of the third transitional structured conversation text; for each semantic tree branch of the structured semantic tree, determining the target structural text feature of the semantic tree branch based on the first global average measurement index, the initial structural text features of the third transitional structured conversation text in the semantic tree branch, the second global average measurement index, the first discrete measurement index, and the second discrete measurement index; and generating the target structured conversation text after updating the structured semantic tree according to the target structural text features of each semantic tree branch of the structured semantic tree.

[0214] In an independent embodiment, the system obtains the updated target structured conversation text through in-depth processing of the structured semantic tree and the third transitional structured conversation text. The following is a detailed explanation of this process.

[0215] First, the system determines a first discrete measurement index and a first global average measurement index of the initial structural text features of each semantic tree branch of the structured semantic tree. The first discrete measurement index is used to evaluate the difference or dispersion between the initial structural text features of each semantic tree branch, which can help the system identify which branches have larger variations or uncertainties in their features. The first global average measurement index is obtained by averaging the initial structural text features of all semantic tree branches, which reflects the overall level or trend of the structured semantic tree in terms of structural text features.

[0216] Next, the system determines a second discrete measurement index and a second global average measurement index of the initial structural text features of each semantic tree branch of the third transitional structured conversation text. Similar to the first discrete measurement index and the first global average measurement index, the second discrete measurement index is used to evaluate the difference or dispersion between the initial structural text features of each semantic tree branch in the third transitional structured conversation text, and the second global average measurement index reflects the overall level or trend of the entire third transitional structured conversation text in terms of structural text features.

[0217] Then, for each semantic tree branch in the structured semantic tree, the system determines the target structured text features of that semantic tree branch based on the first global average measurement metric, the initial structured text features of the third transitional structured conversation text in that semantic tree branch, the second global average measurement metric, the first discrete measurement metric, and the second discrete measurement metric. The processing in this step takes into account the overall feature level of the original structured semantic tree, the features of the transitional text, as well as the differences and dispersion between them, and obtains more accurate and comprehensive target structured text features by integrating this information.

[0218] Specifically, the system can use a preset algorithm or model to calculate and process these metrics as input parameters to obtain the target structured text features of each semantic tree branch. This calculation process can be a complex mathematical model or machine learning algorithm, which can be flexibly adjusted and optimized according to actual requirements and data characteristics.

[0219] Finally, based on the target structured text features of each semantic tree branch in the structured semantic tree, the system generates the target structured conversation text after updating the structured semantic tree. This target text not only retains the key information and structural features of the original structured semantic tree, but also conducts a more in-depth and comprehensive optimization process on the text by comprehensively considering multiple metrics and the information of the transitional text. At the same time, it also provides a more accurate, reliable, and valuable data basis for subsequent business processing and decision support.

[0220] Figure 2 The structural block diagram of the intelligent government affairs platform system is shown, including: a memory 310 for storing program instructions and data; a processor 320 for being coupled with the memory 310 and executing the instructions in the memory 310 to implement the above method.

[0221] Furthermore, a computer storage medium is provided, containing instructions that, when executed on a processor, implement the above method.

[0222] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0223] In addition, each functional module in various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0224] If the described functions are implemented in the form of software function modules 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 application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs. It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the said element.

[0225] The above are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and variations can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for generating business text summaries based on an intelligent platform, characterized in that: Applied to the smart government affairs platform system, the method includes: Get the text stream of smart government affairs business conversation; Mining a business interaction state knowledge vector chain from the smart government affairs business conversation text stream according to a business interaction state mining node set; wherein the business interaction state mining node set is obtained by integrating at least one business interaction state mining node based on the target government affairs matter handling task; Based on the business element thermal evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain, determine the state knowledge confidence of each business interaction state knowledge vector; wherein the business element thermal evaluation data is used to reflect the heat map statistics of the business interaction state knowledge vector, and the state knowledge confidence is used to reflect the importance of the corresponding business interaction state knowledge vector; Based on the state knowledge confidence, determining the target key conversation text semantics from the business interaction state knowledge vector chain; Enter the semantics of the target key conversation text into the deep structured semantic model to create a business text summary generation network; enter the smart government business conversation text of the online business conversation to be processed into the business text summary generation network to obtain the business text summary of the online business conversation to be processed; At least one structured semantic tree of the online business session to be processed and storage guidance features of each structured semantic tree are determined according to the business text summary, each structured semantic tree includes a session semantic block of the online business session to be processed; for each structured semantic tree, the structured semantic tree and the corresponding storage guidance features are input into a text storage optimization network to obtain an initial structured session text after the structured semantic tree is updated; the corresponding initial structured session text is textually repeated according to the structured semantic tree to obtain a target structured session text after the structured semantic tree is updated; and the online business session to be processed is structuredly stored according to the target structured session text corresponding to each structured semantic tree.

2. The method for generating business text summaries based on a smart platform according to claim 1, characterized in that: The business interaction state mining node set includes at least one or more business interaction state mining nodes among a period linkage processing node, an event linkage processing node, a user linkage processing node, a scenario linkage processing node or an adjustable processing node, and mining a business interaction state knowledge vector chain from the smart government business conversation text flow according to the business interaction state mining node set includes at least one of the following: Mining first business interaction state information continuously generated by the online business session within the target activation period from the smart government business session text flow through the periodic linkage processing node, and determining a business interaction state knowledge vector of the first business interaction state information; Alternatively, the second business interaction state information continuously generated between different online business sessions is mined from the smart government business session text stream through the event linkage processing node, and the business interaction state knowledge vector of the second business interaction state information is determined; Alternatively, mining the third business interaction state information that is continuously and repeatedly generated by the online business session from the text stream of the smart government business session through the user linkage processing node, and determining the business interaction state knowledge vector of the third business interaction state information; Alternatively, mining fourth business interaction state information of the online business conversation realizing question-answering dialogue interaction in the target task process from the smart government business conversation text flow through the scenario linkage processing node, and determining the business interaction state knowledge vector of the fourth business interaction state information; Alternatively, the fifth business interaction state information generated by the online business conversation under the target government affairs matter handling task is mined from the smart government affairs business conversation text stream through an adjustable processing node, and a business interaction state knowledge vector of the fifth business interaction state information is determined; Among them, the first business interaction status information continuously generated by the online business session within the target activation period is mined from the smart government business session text flow through the periodic linkage processing node, and the business interaction status knowledge vector of the first business interaction status information is determined, including at least one of the following: setting the periodic constraint value of the periodic linkage processing node; obtaining the detection result of each business interaction status information continuously generated by the online business session within the target activation period of the periodic constraint value; determining the business interaction status knowledge vector of the first business interaction status information based on the detection result; wherein the detection result includes at least one of the update number of each business interaction status information, the maximum state maintenance stage of each business interaction status information, the minimum state maintenance stage of each business interaction status information, or the generation result of each business interaction status information.

3. The method for generating business text summaries based on a smart platform according to claim 1, characterized in that: The determining of the state knowledge confidence of each business interaction state knowledge vector based on the business element thermal evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain includes: Creating a first reference key text content and a second reference key text content based on the target government affairs matter handling task, wherein the first reference key text content is composed of business interaction state knowledge vectors that do not have hot topics in the target government affairs matter handling task, and the second reference key text content is composed of business interaction state knowledge vectors that have hot topics in the target government affairs matter handling task; Determine business element thermal evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the first reference key text content and the second reference key text content; Based on the business element thermal evaluation data of the business interaction state knowledge vector, the state knowledge confidence of each business interaction state knowledge vector is determined.

4. The method for generating business text summaries based on a smart platform according to claim 3 is characterized in that: The determining of the business element thermal evaluation data of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the first reference key text content and the second reference key text content includes: Counting the cumulative value of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the first reference key text content as a first detection variable, and counting the cumulative value of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the second reference key text content as a second detection variable; Determine the total number of business interaction state knowledge vectors contained in the first reference key text content as a third detection variable, and determine the total number of business interaction state knowledge vectors contained in the second reference key text content as a fourth detection variable; Based on the first detection variable and the third detection variable, determining a first operation result between a cumulative value of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the first reference key text content and a total number of business interaction state knowledge vectors contained in the first reference key text content; Based on the second detection variable and the fourth detection variable, determining a second operation result between a cumulative value of each business interaction state knowledge vector in the business interaction state knowledge vector chain in the second reference key text content and a total number of business interaction state knowledge vectors contained in the second reference key text content; Based on the first operation result and the second operation result, the business element thermal evaluation data of each business interaction state knowledge vector in the first reference key text content and the second reference key text content is determined.

5. The method for generating business text summaries based on a smart platform according to claim 3 is characterized in that: The determining of the state knowledge confidence of each business interaction state knowledge vector based on the business element thermal evaluation data of the business interaction state knowledge vector comprises: Performing interval numerical mapping processing on the business element thermal evaluation data of the business interaction state knowledge vector to obtain an interval numerical mapping result of the business element thermal evaluation data; Feature conversion processing is performed based on the interval numerical mapping result of the business element thermal evaluation data, and the obtained feature conversion result is used as the state knowledge confidence of each business interaction state knowledge vector.

6. The method for generating business text summaries based on a smart platform according to claim 1, characterized in that: The determining the target key conversation text semantics from the business interaction state knowledge vector chain based on the state knowledge confidence includes: Based on the target government affairs handling task, determining the semantic feature dimension of the target key conversation text semantics; Determine a confidence interval of the state knowledge confidence of the semantics of the target key conversation text to be selected based on the semantic feature dimension; Based on the confidence interval, target key conversation text semantics are determined from each business interaction state knowledge vector of the business interaction state knowledge vector chain.

7. The method for generating a business text summary based on a smart platform according to any one of claims 1 to 6, characterized in that: The method further comprises: According to the priority of the session output, the priority of each smart government service session text in the smart government service session text stream is updated; Perform joint semantic embedding on each smart government service conversation text after priority update; and clean up the noise service conversation text in the smart government service conversation text stream.

8. The method for generating business text summaries based on a smart platform according to claim 1, characterized in that: The method further comprises: A first reference key text content and a second reference key text content are created according to the target government affairs matter handling task; based on the first reference key text content and the second reference key text content, a derived target key conversation text semantics is determined; wherein the derived target key conversation text semantics is used to create a derived business text summary generation network that matches the target government affairs matter handling task, so that the derived business text summary generation network determines the business text summary of the online business session to be processed under the target government affairs matter handling task.

9. A smart government affairs platform system, characterized in that: include: Memory, used to store program instructions and data; A processor, coupled to a memory, and configured to execute instructions in the memory to implement the method according to any one of claims 1 to 8.

10. A computer storage medium, characterized in that: Contains instructions, which, when executed on a processor, implement the method according to any one of claims 1 to 8.

Images