A method for guiding emission trading

Abstract

The present application relates to the field of emission trading, and particularly relates to an emission trading guiding method, which comprises the following steps: when a first user performs an emission trading operation in an emission trading system, an original operation sequence of the first user is acquired; each original emission trading operation item in the original operation sequence carries operation behavior data; according to the operation behavior data carried by each original emission trading operation item, an abnormal emission trading operation item in an abnormal operation sequence in the original operation sequence and an abnormal operation feature corresponding to the abnormal operation sequence are identified; a process guiding scheme is generated according to the abnormal emission trading operation item and the abnormal operation feature; and process guiding of the first user in emission trading is performed based on the process guiding scheme. Through the present application, user operation sticking points can be effectively solved, and user experience and platform operation efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the field of emissions trading, and more specifically, to a method for guiding emissions trading. Background Technology

[0002] During the operation of the pollution rights trading platform, users often encounter various questions regarding account registration, trading procedures, material preparation, and fee payment. The existing customer service support system is mainly based on rules and static knowledge bases, which has many shortcomings and is difficult to meet users' personalized and efficient consultation and guidance needs.

[0003] Currently, existing technical solutions mainly include five forms: static FAQ document libraries, keyword matching self-service Q&A systems, human customer service team responses, fixed process guidance, and work order systems for recording and tracing. Among them, static FAQ document libraries require users to search or browse for answers themselves, lacking proactive guidance and personalized responses; keyword matching self-service Q&A systems can only match questions through simple keywords or regular expressions, lacking semantic understanding capabilities and having poor support for synonyms, typos, and multi-turn contexts; human customer service team responses rely on human experience, resulting in slow response times, a backlog of work orders during peak periods, and knowledge transfer relies on internal training documents, which can easily lead to inconsistent answers; fixed process guidance uses static instructions embedded in the platform interface, with all users receiving the same content, unable to dynamically adjust based on user behavior or bottlenecks; and work order systems can only record and archive user questions.

[0004] The aforementioned existing technical solutions all suffer from problems such as low response efficiency and insufficient personalization, failing to accurately match users' actual needs in the pollution rights trading process, making it difficult to effectively solve user operational bottlenecks, and affecting user experience and platform operational efficiency. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method for guiding emissions trading, which can effectively solve user operational bottlenecks and improve user experience. And platform operational efficiency.

[0006] In a first aspect, embodiments of this application provide a method for guiding emissions trading, the method comprising: When the first user performs a pollution rights trading operation in the pollution rights trading system, the first user's original operation sequence is obtained; each original pollution rights trading operation item in the original operation sequence carries operation behavior data. Based on the operational behavior data carried by each original pollution discharge rights trading operation item, identify the abnormal pollution discharge rights trading operation items in the abnormal operation sequence in the original operation sequence and the abnormal operation characteristics corresponding to the abnormal operation sequence. Based on the abnormal pollution discharge rights trading operation items and the abnormal operation characteristics, a process guidance scheme is generated; Based on the aforementioned process guidance scheme, the process of trading pollution discharge rights for the first user is guided.

[0007] In one possible implementation, the step of identifying abnormal pollution rights trading operations in abnormal operation sequences within the original operation sequence and the abnormal operation characteristics corresponding to the abnormal operation sequences, based on the operational behavior data carried by each original pollution rights trading operation item, includes: The original operation sequence is matched with the preset regular expressions corresponding to each preset operation trajectory pattern to obtain the abnormal operation sequence and the abnormal operation trajectory pattern corresponding to the abnormal operation sequence; the abnormal operation sequence includes abnormal pollution discharge rights trading operation items. The abnormal operation trajectory pattern and the preset pollution discharge rights trading operation thresholds corresponding to each preset operation behavior index are used to perform anomaly detection on the operation behavior data corresponding to the abnormal operation sequence to obtain the abnormal confidence and abnormal operation behavior indexes corresponding to the abnormal operation sequence in the abnormal operation features. If the anomaly confidence level is greater than a preset confidence threshold, then the anomaly operation category corresponding to the anomaly operation sequence in the anomaly operation characteristics is determined based on the anomaly operation mode corresponding to the anomaly operation sequence, the anomaly confidence level, the anomaly operation behavior indicators, and the anomaly discharge rights trading operation items in the anomaly operation sequence.

[0008] In one possible implementation, generating a process guidance scheme based on the abnormal pollution discharge rights trading operation item and the abnormal operation characteristics includes: Based on the abnormal emission rights trading operation items and abnormal operation characteristics, search the emission rights trading guidance knowledge base for guidance templates that meet the corresponding guidance conditions; Based on the abnormal pollution discharge rights trading operation items, text is added to each guide item in the guide template to obtain the process guidance content in the process guidance scheme; Based on the abnormal confidence level in the abnormal operation characteristics, the display parameters of the process guidance content in the process guidance scheme are determined.

[0009] In one possible implementation, the step of searching for a guidance template that meets the corresponding guidance conditions from the pollution rights trading guidance knowledge base based on the abnormal pollution rights trading operation item and abnormal operation characteristics includes: Based on the abnormal pollution discharge rights trading operation items, the abnormal operation category and abnormal confidence level in the abnormal operation characteristics, a precise match is made from the pollution discharge rights trading guidance knowledge base; If no matching guidance template is found that meets the corresponding guidance conditions, a fuzzy match is performed from the pollution rights trading guidance knowledge base based on the abnormal operation category in the abnormal operation characteristics. If no fuzzy match is found that matches the corresponding guidance conditions, the preset general guidance template will be determined as the guidance template that matches the corresponding guidance conditions.

[0010] In one possible implementation, the method further includes: After the first user completes the pollution discharge rights trading operation, obtain the complete transaction operation behavior data, process guidance record and transaction operation result of the first user in the process of executing the pollution discharge rights trading operation; Based on the complete transaction operation behavior data, process guidance record and transaction operation result, determine the process guidance result corresponding to the first user; If the process guidance result is successful, then the latest successful transaction process path corresponding to the pollution discharge rights trading operation is extracted from the complete transaction operation behavior data. Based on the latest successful transaction process path and all historical successful transaction process paths in the pollution rights trading process database, a standard transaction process path with the highest success rate is determined, so as to guide the process when a second user deviates from the standard transaction process path.

[0011] In one possible implementation, the method further includes: If the process guidance result is guidance failure, then the latest failed transaction process path corresponding to the pollution rights trading operation is extracted from the complete transaction operation behavior data; Based on the latest failed transaction process path and all historical failed transaction process paths in the pollution rights trading process database, the risky pollution rights trading operation item and risky transaction process path with the highest transaction failure rate are determined, so as to provide process warning when the second user executes the risky pollution rights trading operation item or follows the risky transaction process path.

[0012] In one possible implementation, the method further includes: The pollution rights trading question input by the first user is standardized to obtain a standard text of the pollution rights trading question; and the pollution rights trading history of the first user is obtained. The standard text of the pollution rights trading issue is input into the issue feature extraction model to obtain the issue feature vector corresponding to the pollution rights trading issue; the issue feature vector includes the pollution rights trading intention and the pollution rights trading entity; Based on the emission rights trading question vector corresponding to the standard text of the emission rights trading question and the question feature vector, emission rights trading documents are retrieved from the emission rights trading knowledge base; The historical dialogues on pollution rights trading, the pollution rights trading questions, and the retrieved pollution rights trading documents are input into the answer generation model to obtain the pollution rights trading answer corresponding to the pollution rights trading questions.

[0013] Secondly, embodiments of this application also provide a pollution rights trading guidance system, the system comprising: The acquisition module is used to acquire the original operation sequence of the first user when the first user performs pollution rights trading operations in the pollution rights trading system; each original pollution rights trading operation item in the original operation sequence carries operation behavior data. The identification module is used to identify abnormal pollution rights trading operation items in the abnormal operation sequence and the abnormal operation features corresponding to the abnormal operation sequence based on the operation behavior data carried by each original pollution rights trading operation item. The generation module is used to generate a process guidance scheme based on the abnormal pollution discharge rights trading operation items and the abnormal operation characteristics; The process guidance module is used to guide the first user through the pollution rights trading process based on the process guidance scheme.

[0014] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the pollution rights trading guidance method as described in any of the first aspects.

[0015] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the pollution rights trading guidance method as described in any of the first aspects.

[0016] This application provides a method for guiding pollution rights trading. The method includes: when a first user performs a pollution rights trading operation in a pollution rights trading system, obtaining the first user's original operation sequence; each original pollution rights trading operation item in the original operation sequence carries operation behavior data; based on the operation behavior data carried by each original pollution rights trading operation item, identifying abnormal pollution rights trading operation items in abnormal operation sequences within the original operation sequence and the abnormal operation features corresponding to the abnormal operation sequences; generating a process guidance scheme based on the abnormal pollution rights trading operation items and the abnormal operation features; and guiding the first user through the pollution rights trading process based on the process guidance scheme. This application can effectively solve user operation bottlenecks, improve user experience, and enhance platform operational efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a method for guiding emissions trading according to an embodiment of this application is shown; Figure 2 A flowchart illustrating the identification process of abnormal pollution discharge rights trading operation items and their corresponding abnormal operation characteristics provided in an embodiment of this application is shown. Figure 3 This paper shows a schematic diagram of the structure of a pollution rights trading guidance system provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0020] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] To enable those skilled in the art to utilize the content of this application, and in conjunction with the specific application scenario of "emissions trading," the following implementation methods are provided. For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application primarily describes the "emissions trading field," it should be understood that this is merely an exemplary embodiment.

[0022] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0023] The following is a detailed description of a method for guiding emissions trading provided in the embodiments of this application.

[0024] Reference Figure 1 The diagram shown is a flowchart illustrating a method for guiding emissions trading according to an embodiment of this application. The exemplary steps of this embodiment are described below: S101. When the first user performs a pollution rights trading operation in the pollution rights trading system, the original operation sequence of the first user is obtained; each original pollution rights trading operation item in the original operation sequence carries operation behavior data.

[0025] In this embodiment, when a first user performs a pollution rights trading operation in the pollution rights trading system, not only are the user's clicks, inputs, pauses, focus, and deletion / re-entry actions recorded, but the complete path and HTML hierarchy of each UI element are also obtained. For example, when the first user clicks the "Submit Registration" button, the precise location path of the button on the page is recorded, including its hierarchical relationship in the HTML structure. Simultaneously, for form fields, fine-grained behavioral data such as the user's dwell time, focus count, and deletion / re-entry count on each field are recorded. Specifically, a hash table is pre-established to manage the mapping relationship between UI element paths and the corresponding identifiers of the original pollution rights trading operation items. When a pollution rights trading operation request from the first user is received, the path information of the corresponding UI element is first obtained, and then it is checked whether the path already exists in the hash table as the identifier of the corresponding original pollution rights trading operation item. If it does not exist, the path is randomly converted into a unique identifier of the original pollution rights trading operation item using Unicode encoding, and this path-identifier pair is inserted into the hash table, while the path is added to the end of the pre-built array. In this way, complex UI operation paths are abstracted into concise symbol sequences, yielding the original operation sequence for the first user.

[0026] For example, in the pollution rights trading registration scenario, the original pollution rights trading operation items can be a company name input box, a business license number input box, a contact phone number input box, or a submit button. Assume the company name input box is mapped to symbol "α", the business license number input box to "β", the contact phone number input box to "γ", and the submit button to "δ". The first user's original operation sequence is then converted into a string of identifiers for the original pollution rights trading operation items, such as "α→β→β→β→β→β→γ→δ→δ→δ". Furthermore, the identifier corresponding to each original pollution rights trading operation item in the original operation sequence carries operation behavior data, such as dwell time, number of times the item was focused, and number of times it was deleted and re-entered.

[0027] S102. Based on the operational behavior data carried by each original emission rights trading operation item, identify the abnormal emission rights trading operation items in the abnormal operation sequence in the original operation sequence and the abnormal operation characteristics corresponding to the abnormal operation sequence.

[0028] Reference Figure 2 The diagram shown is a flowchart for identifying abnormal pollution discharge rights trading operations and their corresponding abnormal operation characteristics, as provided in this application embodiment. The detailed process is as follows: S201. Match the original operation sequence with the preset regular expressions corresponding to each preset operation trajectory pattern to obtain the abnormal operation sequence and the abnormal operation trajectory pattern corresponding to the abnormal operation sequence; the abnormal operation sequence includes abnormal pollution discharge rights trading operation items.

[0029] In the embodiments of this application, the preset operation trajectory pattern refers to the operation sequence that does not conform to normal operation logic. It is a specific operation trajectory feature that can be identified through regular expression matching. In layman's terms, it is "how the user performs abnormal operations" (such as "repeatedly clicking the submit button" or "switching back and forth between two input boxes"), which is the "specific manifestation" of abnormal operations. Referring to Table 1, the preset regular expressions and scenario examples corresponding to the various preset operation trajectory patterns provided in the embodiments of this application are shown.

[0030] Table 1

[0031] S202. Using the abnormal operation trajectory pattern and the preset emission rights trading operation thresholds corresponding to each preset operation behavior indicator, perform anomaly detection on the corresponding operation behavior data in the abnormal operation sequence to obtain the abnormal confidence and abnormal operation behavior indicators corresponding to the abnormal operation sequence in the abnormal operation features.

[0032] In this embodiment, the higher the anomaly confidence level, the greater the probability that the abnormal operation sequence is an abnormal operation. Preset operation behavior indicators include dwell time, operation frequency, and operation trajectory pattern. The specific anomaly detection process is as follows: Step 1: Based on the comparison between the actual dwell time of the abnormal pollution discharge rights trading operation item in the abnormal operation sequence and the preset normal dwell time threshold, determine whether the dwell time index is an abnormal operation behavior index and determine the abnormal confidence level of the abnormal operation sequence under the operation time index.

[0033] In this embodiment, if the actual dwell time of an abnormal pollution discharge rights trading operation exceeds the upper limit of the preset normal operation time threshold, or the actual dwell time exceeds a preset multiple (3 times) of the lower limit of the preset normal operation time threshold, then the dwell time index is an abnormal operation behavior index; otherwise, the dwell time index is not an abnormal operation behavior index. The abnormal confidence level of the abnormal operation sequence under the operation time index is determined based on the difference between the actual operation time and the lower limit of the preset normal operation time threshold.

[0034] The actual operation time is subtracted from the lower limit of a preset normal operation time threshold (e.g., 30-60 seconds for company name, 60-120 seconds for business license number, 20-40 seconds for contact number, and 1-5 seconds for operation submission) to obtain the time difference. Based on this time difference, the method for determining the anomaly confidence level of the abnormal operation sequence under the operation time indicator can be reasonably set according to the actual situation. It simply needs to ensure that the larger the time difference, the greater the anomaly confidence level of the abnormal operation sequence under the operation time indicator.

[0035] Step 2: Based on the actual number of times the abnormal pollution discharge rights trading operation item in the abnormal operation sequence is focused and the actual number of times the item is deleted and re-entered, compare the values ​​with the corresponding preset normal operation frequency thresholds (number of times focused ≤ 3 times / field, number of times deleted and re-entered ≤ 2 times / field) to determine whether the operation frequency index is an abnormal operation behavior index and determine the abnormal confidence level of the abnormal operation sequence under the operation frequency index.

[0036] In this application embodiment, if the actual number of focusing attempts or the actual number of re-entries deleted exceeds the corresponding preset normal threshold for operation frequency, then the operation frequency index is determined as an abnormal operation behavior index; based on the difference between the actual number of focusing attempts and / or the actual number of re-entries deleted and the corresponding preset normal threshold for operation duration, the abnormal confidence level of the abnormal operation sequence under the operation frequency index is determined.

[0037] Specifically, if both the actual number of focus attempts and the actual number of deleted re-entries exceed the corresponding preset normal operation frequency threshold, the anomaly confidence level of the abnormal operation sequence under the operation frequency index is determined by the sum of the number of abnormal focus attempts (actual focus attempts exceeding the corresponding preset normal operation frequency threshold) and the number of abnormal deleted re-entries (actual deleted re-entries exceeding the corresponding preset normal operation frequency threshold). The specific determination method can be reasonably set according to the actual situation, as long as the larger the sum, the greater the anomaly confidence level of the abnormal operation sequence under the operation frequency index.

[0038] If only the actual number of focusing attempts exceeds the corresponding preset normal threshold for operation frequency, then the abnormal focusing attempts are determined based on the number of actual focusing attempts exceeding the corresponding preset normal threshold for operation frequency. The specific determination method can be reasonably set according to the actual situation, as long as the larger the number of abnormal focusing attempts, the greater the abnormal confidence of the abnormal operation sequence under the operation frequency index.

[0039] If only the actual number of deleted duplicates exceeds the corresponding preset normal operation frequency threshold, then the abnormal number of deleted duplicates is determined based on the actual number of deleted duplicates exceeding the corresponding preset normal operation frequency threshold. The specific determination method can be reasonably set according to the actual situation, as long as the larger the number of abnormal deleted duplicates, the greater the abnormal confidence of the abnormal operation sequence under the operation frequency index.

[0040] Step 3: Determine the preset anomaly confidence value corresponding to the abnormal operation trajectory pattern as the anomaly confidence value of the abnormal operation sequence under the operation trajectory pattern index.

[0041] Step 4: The weighted sum of the anomaly confidence scores of the abnormal operation sequence under all preset operation behavior indicators is determined as the anomaly confidence score corresponding to the abnormal operation sequence.

[0042] S203. If the anomaly confidence level is greater than the preset confidence level threshold, then the anomaly operation category corresponding to the anomaly operation sequence in the anomaly operation characteristics is determined based on the anomaly operation mode, anomaly confidence level, anomaly operation behavior indicators and anomaly discharge rights trading operation items in the anomaly operation sequence.

[0043] In this application's implementation, the abnormal operation category is a classification and summary of abnormal user operation behaviors, corresponding to the core scenario of identifying abnormal pollution rights trading operation items, and is the "classification label" of abnormal operations. In layman's terms, it is "which type of problem does this abnormal operation belong to" (for example, "repeatedly clicking the submit button" belongs to "verification failure type exception"), and is a "summary and classification" of abnormal operation patterns.

[0044] Here, based on the abnormal operation pattern, abnormal confidence level, abnormal operation behavior indicators, and abnormal pollution discharge rights trading operation items corresponding to the abnormal operation sequence, a matching is performed with the decision tree logic corresponding to each preset operation category. The preset operation category that matches successfully is determined as the abnormal operation category corresponding to the abnormal operation sequence in the abnormal operation features. Referring to Table 2, this is the matching table for each preset operation category provided in the embodiments of this application.

[0045] Table 2

[0046] S103. Generate a process guidance plan based on the abnormal pollution discharge rights trading operation items and abnormal operation characteristics.

[0047] In this implementation, for abnormal pollution discharge rights trading operations of the format confusion type, the system generates an interactive prompt box, including elements such as real-time format verification, a dynamic example generator, and format rule explanations. The guidance scheme not only includes static text descriptions but also provides real-time feedback and error correction suggestions based on the user's current input. The system also adjusts the display method and duration of the guidance scheme according to the severity of the abnormal pollution discharge rights trading operation. The process guidance scheme includes multiple guidance items, such as: Title: Format Error; Rule Text: Please enter ${length} digits of the Unified Social Credit Code; Example Text: ${example_code}; Verification Rule: ${verify_rule}; Display Method: Strong Prompt (Pop-up Highlight); Display Duration: Until correct input is received and disappears.

[0048] The specific implementation process of the generation process guidance scheme is as follows: Step 1: Based on the abnormal emission rights trading operation items and abnormal operation characteristics, search for the corresponding guidance templates that meet the guidance conditions in the emission rights trading guidance knowledge base.

[0049] In this application's implementation, the pollution rights trading guidance knowledge base contains multiple preset guidance templates, each with corresponding guidance conditions. Specifically: i. Based on the abnormal emission rights trading operation items, the abnormal operation categories and abnormal confidence levels in the abnormal operation characteristics, perform precise matching from the emission rights trading guidance knowledge base.

[0050] In this application embodiment, a preset guidance template that meets the corresponding guidance conditions is determined from the pollution rights trading guidance knowledge base, where the abnormal pollution rights trading operation item, the abnormal operation category and the abnormal confidence level in the abnormal operation characteristics all meet the corresponding guidance conditions.

[0051] ii. If no matching template that meets the corresponding guidance conditions is found, a fuzzy match will be made from the pollution rights trading guidance knowledge base based on the abnormal operation category in the abnormal operation characteristics.

[0052] In this application embodiment, a preset guidance template that matches the corresponding guidance conditions in the abnormal operation category of the abnormal operation characteristics in the pollution rights trading guidance knowledge base is determined as a guidance template that meets the corresponding guidance conditions.

[0053] iii. If no fuzzy match is found that matches the corresponding guidance conditions, the preset general guidance template will be determined as the guidance template that matches the corresponding guidance conditions.

[0054] Step 2: Based on the abnormal pollution discharge rights trading operation items, add text to each guidance item in the guidance template to obtain the process guidance content in the process guidance plan.

[0055] In this embodiment, the essence of this step is to fill in the variables in the template with real content. Text is added to each guide item in the previous example template to obtain the process guidance content in the process guidance scheme: "Please enter the 15-digit unified social credit code, example: 91310115MA1F2X3Y4Z. Chinese characters, symbols, and spaces are not allowed."

[0056] Step 3: Based on the anomaly confidence level in the abnormal operation characteristics, determine the display parameters of the process guidance content in the process guidance scheme.

[0057] For example, with a confidence level of 0.88 (high), strong prompts are provided: the parameters are displayed as a pop-up / highlighted box; they are continuously displayed until the input is correct; real-time verification is performed, and errors are immediately alerted.

[0058] S104. Based on the process guidance scheme, guide the first user through the process of trading pollution discharge rights.

[0059] In this implementation, dynamically generated guidance content is presented to the first user in a visual manner, and input behavior is monitored in real time to provide immediate feedback. Specifically, personalized guidance is displayed: prompt boxes, highlighted boxes, bubble prompts, and step-by-step guidance bars. Real-time monitoring and error correction: The system provides immediate prompts when the first user's input in the current pollution discharge rights trading operation item does not conform to the rules; the prompts are automatically canceled after the input conforms to the rules. Example: User enters "123456" in β (business license number input box) → Immediate prompt: Insufficient length, please enter a 15-digit unified social credit code. Correct input—the prompt disappears automatically, allowing continued operation.

[0060] Furthermore, after the emissions trading operation is completed, the results are verified and patterns are learned to assess the guiding effect and to identify successful / failure patterns for system optimization. Specifically, this method also includes: Step 1: After the first user completes the pollution rights trading operation, obtain the complete transaction operation behavior data, process guidance records and transaction operation results of the first user during the execution of the pollution rights trading operation.

[0061] Step 2: Based on the complete transaction operation data, process guidance records, and transaction operation results, determine the process guidance result corresponding to the first user.

[0062] In this embodiment, based on complete transaction operation behavior data, process guidance records, and transaction operation results, the initial process guidance score corresponding to each preset guidance evaluation dimension is evaluated; the weighted sum of the initial process guidance scores corresponding to all preset guidance evaluation dimensions is determined as the target process guidance score for guiding the first user; the higher the target process guidance score, the better the process guidance effect; if the target process guidance score is greater than or equal to the preset process guidance score threshold, the process guidance result for the first user is considered successful; otherwise, the process guidance result for the first user is considered failed.

[0063] Among them, the preset guidance evaluation dimensions include three types of indicators: (1) Direct success indicators (the hardest indicators): whether the form submission is completed, whether the data is verified, and whether the page redirects normally; Example: After being guided in the business license number input box β, the user successfully submits the registration → Direct indicator = effective. (2) Behavior improvement indicators (to see if the operation becomes smoother): whether the operation time is shortened, whether the number of deletions and modifications and repeated operations are reduced, and whether the operation path is shorter and less circuitous; Example: Before guidance, there were 4 deletions and modifications, taking 210 seconds, and after guidance, there were 0 deletions and modifications, taking 70 seconds, indicating that the behavior has been significantly improved.

[0064] It should be noted that the initial process guidance score corresponding to each preset guidance evaluation dimension can be evaluated using a pre-trained AI model. The architecture of the AI ​​model is not limited, as long as it can achieve its function.

[0065] Step 3: If the process guidance result is successful, extract the latest successful transaction process path corresponding to the pollution rights trading operation from the complete transaction operation behavior data.

[0066] In this embodiment, the latest successful transaction process path is an operation sequence containing multiple original pollution rights trading operation items, which can be extracted using a large language model.

[0067] Step 4: Based on the latest successful transaction process path and all historical successful transaction process paths in the pollution rights trading process database, determine the standard transaction process path with the highest success rate, so as to guide the process when the second user deviates from the standard transaction process path.

[0068] In this embodiment, the latest successful transaction process path and all historical successful transaction process paths can be input into a large language model for text understanding, thereby determining the standard transaction process path with the highest success rate. When a second user deviates from the standard transaction process path, process guidance can be provided to optimize the process guidance method.

[0069] Step 5: If the process guidance result is guidance failure, then extract the latest failed transaction process path corresponding to the pollution discharge rights trading operation from the complete transaction operation behavior data.

[0070] In this embodiment, the latest failed transaction process path is an operation sequence containing multiple original pollution rights trading operation items, which can be extracted using a large language model.

[0071] Step 6: Based on the latest failed transaction process path and all historical failed transaction process paths in the pollution rights trading process database, determine the risky pollution rights trading operation item and risky transaction process path with the highest transaction failure rate, so as to provide process warning when the second user executes the risky pollution rights trading operation item or follows the risky transaction process path.

[0072] In this embodiment, the latest failed transaction process path and all historical failed transaction process paths can be input into a large language model for text understanding, thereby determining the risky pollution rights transaction operation item and risky transaction process path with the highest transaction failure rate, so as to provide process warning when a second user executes the risky pollution rights transaction operation item or follows the risky transaction process path.

[0073] In addition, it can also analyze the differences in successful transaction process paths under different user profiles, and establish personalized optimal transaction process paths for different types of users, so as to guide the process when different types of users deviate from the corresponding optimal transaction process path.

[0074] In addition, this application embodiment also provides a process-guided question-and-answer mode to intelligently respond to user-inputted questions about pollution rights trading. Specifically: Step 1: Standardize the pollution rights trading question input by the first user to obtain the standard text of the pollution rights trading question; and obtain the user's pollution rights trading history dialogue.

[0075] In this application implementation, the original natural language form of the pollution rights trading question of the first user is transformed into a standard text of pollution rights trading questions that the system can recognize and process. Specifically: (1) Special characters (such as @, #, *, etc.) are removed, punctuation is standardized (Chinese punctuation is uniformly retained or all punctuation is removed), and redundant spaces are removed to avoid interfering with subsequent word segmentation and intent recognition. Example: The user inputs "I want to know how to trade pollution rights and what materials are needed?" - After cleaning: "I want to know how to trade pollution rights and what materials are needed". (2) The cleaned pollution rights trading question is split into independent words, the part of speech of each word is labeled (noun, verb, etc.), and keywords related to pollution rights trading are extracted to filter core information. Specific operations: a. Word segmentation: The Chinese word segmentation algorithm is used to split the sentence into a word sequence; b. Part of speech labeling: The part of speech of each word is labeled (such as "trade" as a verb and "pollution rights" as a noun); c. Keyword extraction: Words that are corely related to the user's question and fit the field of pollution rights trading are selected as the core basis for subsequent intent recognition.

[0076] Example: The issue of pollution rights trading after cleaning: "I want to know how to trade pollution rights and what materials are needed" - word segmentation result: ["I", "want", "know", "how", "trade", "pollution rights", "need", "prepare", "what", "materials"] - keyword extraction: ["trade", "pollution rights", "prepare", "materials"].

[0077] Step 2: Input the standard text of the pollution rights trading issue into the issue feature extraction model to obtain the issue feature vector corresponding to the pollution rights trading issue; the issue feature vector includes the pollution rights trading intention and the pollution rights trading entity.

[0078] In this implementation, the standard text of the pollution rights trading question is input into the question feature extraction model (Qwen-max model), combined with a pollution rights trading domain-specific prompt, to identify the first user's core intent, key entities, and intent confidence level, thus clarifying the core needs of the first user's question. Specific operation: - Model input: Standard text of the pollution rights trading question + pollution rights trading domain prompt (e.g., "Please identify the user's question intent and key entities regarding pollution rights trading, and output the confidence level"); - Model output: Question feature vector, containing the pollution rights trading intent, pollution rights trading entities, and the confidence level corresponding to the pollution rights trading intent (0-1 range, the closer to 1, the more accurate the intent recognition). Example: Input standard text of the pollution rights trading question + domain prompt → Output: {"intent": "Transaction process consultation","entities": ["Pollution rights trading", "Material preparation"], "confidence": 0.92}.

[0079] Step 3: Based on the emission rights trading question vector corresponding to the standard text of the emission rights trading question and the question feature vector, retrieve emission rights trading documents from the emission rights trading knowledge base.

[0080] In this embodiment, the standard text of pollution rights trading issues is converted into a computer-computable vector form, realizing a "text-to-vector" mapping and laying the foundation for subsequent similarity calculation. The similarity between the pollution rights trading issue vector and the issue feature vectors of all pollution rights trading documents in the pollution rights trading knowledge base is calculated, and the Top-K pollution rights trading document fragments with the highest similarity are selected to ensure that the search results highly match user needs.

[0081] Step 4: Input the historical dialogues on emissions trading, emissions trading questions, and retrieved emissions trading documents into the answer generation model to obtain the emissions trading answers corresponding to the emissions trading questions.

[0082] Example of answer for pollution rights trading: (1) Required materials: copy of the enterprise's business license; pollution discharge permit issued by the environmental protection department; pollution discharge monitoring reports for the past three years; legal person's identity document; power of attorney (if entrusted to handle the transaction). (2) Transaction process: account registration - material review - release of transaction information - matching transactions - signing of contract - fund settlement.

[0083] Furthermore, this embodiment of the application can dynamically update the knowledge base and related models for pollution rights trading guidance based on the output standard transaction process path, risky pollution rights trading operation items, risky transaction process path, and model optimization strategies, combined with the interactive data from the intelligent question-and-answer module. The module integrates successful path templates, high-failure-rate node information, typical error cases, and user feedback, synchronously updating the guidance template, abnormal pollution rights trading operation item identification thresholds, RAG retrieval vector library, and question-and-answer model parameters. It also incorporates new pollution rights trading policies and operating procedures, ensuring that the knowledge base remains synchronized with actual business scenarios and user needs. This continuously improves the accuracy of abnormal pollution rights trading operation item identification, personalized guidance, and intelligent question-and-answer, providing data support for the closed-loop optimization of the entire process mining and guidance system, and ensuring the long-term stable and efficient operation of the system.

[0084] Specifically, the knowledge base update process is as follows: Step 1: Successful Case Records. Updated data type: {"casetype": "successfulqa","question": "What materials are needed for pollution rights trading","answer":"The generated complete answer content","usersatisfaction": 5,"resolutiontime": 15,"knowledgesources": ["doc001", "doc045", "doc078"],"updateaction": "reinforceknowledgeweight"}. Step 2: Manual Processing Result Feedback. Feedback data structure: {"ticketid": "T20240115001","originalquestion": "Complex policy interpretation question","aiattempt": "Initial AI answer","humansolution": "Professional answer from human customer service","knowledgegap": "Lack of the latest policy interpretation","updateaction": "addnewknowledgeentry"}. Step 3: Success Path Model. Update path data records: {"processname": "Enterprise Registration Process","successfulpath": {"step": "Fill in basic information","avgtime": 120, "successrate": 0.95},{"step": "Upload documents", "avgtime": 180, "successrate": 0.88},{"step": "Submit for review", "avgtime": 30, "successrate":0.99}],"optimizationpoints": ["The document upload step needs clearer format instructions"],"updateaction": "optimizeguidancecontent"}. Step 4: Failure mode optimization. Failure Pattern Analysis: {"failurepattern":{"commonstuckpoint": "Business License Number Format","failurerate": 0.23,"typicalerrors": ["Incorrect format", "Insufficient digits", "Contains illegal characters"],"userfeedback": ["Insufficient clarity", "Example needs more detail"],"optimizationstrategy": "Add real-time format validation and more detailed examples"}}. Step 5: Data Aggregation. Collect all feedback data from Steps 1-4.Step 6: Knowledge Extraction: Extract new question-answer pairs from successful cases using NLP techniques. Step 7: Vector Update: Recalculate the vector representations of the knowledge base documents. Step 8: Model Fine-tuning: Incrementally train Qwen-max based on the new data. Step 9: Performance Validation: Validate the updated performance on the test set.

[0085] Among them, the knowledge base update frequency is as follows: Real-time update: user feedback and operation results; Daily update: knowledge base vector reconstruction; Weekly update: model parameter fine-tuning; Monthly update: comprehensive system performance evaluation.

[0086] In summary, the embodiments of this application have the following beneficial effects: Disadvantage 1: Severely insufficient semantic understanding ability: Existing technical limitations: Traditional keyword-matching self-service question-answering systems use simple string matching and regular expressions, which have the following technical limitations: Limited vocabulary matching: When a user enters "how to pay," if the system's preset keyword is "pay," it cannot match successfully, leading to a failed search; Lack of synonym recognition: When users express synonymous questions such as "pay fees," "payment process," and "payment steps," the system cannot identify them as the same question type; Poor grammatical error tolerance: When faced with colloquial expressions such as "how to pay," "how to pay," or situations where "pay" is written as "pay fee," the system's matching failure rate is as high as 70% or more.

[0087] The root cause of the technical flaw is that keyword matching is essentially a shallow matching based on literal text, which cannot understand the deep semantic structure and expressive intent of language.

[0088] The solution in this application embodiment utilizes the semantic understanding capabilities of a large domain model: deep semantic encoding: converting user questions into high-dimensional semantic vectors to capture the true intent behind words; contextual association analysis: understanding the meaning of questions in specific business scenarios; and diverse expression recognition: training models to recognize various expressions in the field of pollution rights trading.

[0089] Disadvantage 2: The passive service model leads to a poor user experience. Reasoning for existing technical problems: Technical defects of fixed-process guidance systems: Undifferentiated service: All users see the same operation instructions, and cannot provide targeted assistance based on the user's actual operation ability and where they are stuck; Lack of real-time monitoring: The system cannot perceive the specific difficulties encountered by users during operation and can only wait for users to actively ask for help; Inappropriate guidance timing: Static pop-ups and step-by-step diagrams often appear when users do not need them, but are missing when they are actually needed; Root cause of technical defects: Traditional systems lack the ability to analyze user behavior and cannot understand the user's operation status and changes in needs in real time.

[0090] The solution proposed in this application is as follows: Proactive service is achieved through process mining technology: Real-time behavior monitoring: Collects user operation trajectories and analyzes behavioral patterns such as dwell time, click paths, and repetitive operations; Intelligent checkpoint identification: When a user is detected to have lingered at a certain step for more than a threshold time or to have an abnormal operation sequence, it is automatically identified as a checkpoint; Personalized push mechanism: Based on the specific checkpoint type, the most relevant solutions are matched from the knowledge base and proactively pushed. Disadvantage 3: Lagging knowledge updates and high costs: Reasoning for existing technical problems: Technical limitations of manually maintaining FAQ and work order systems: Long update cycle: When pollution rights trading policies change, FAQ documents need to be manually modified one by one, which usually takes several weeks; Knowledge silo problem: Historical work orders contain a lot of valuable problem-solving experience, but due to the lack of an automated extraction mechanism, this knowledge cannot be effectively reused; Difficulty in ensuring consistency: Different customer service personnel answer questions based on their personal understanding, which can easily lead to inconsistencies; Root cause of technical defects: Traditional systems lack automated knowledge extraction, organization, and updating mechanisms, and rely too much on manual maintenance.

[0091] The solution proposed in this application is achieved through an automated knowledge management system: Incremental learning mechanism: The system automatically analyzes successfully solved problem cases, extracts effective question-and-answer patterns, and updates the knowledge base; Failure case mining: Identifies unsatisfactory answers from users, analyzes knowledge blind spots, and triggers a knowledge supplementation process; Version control and consistency guarantee: A unified knowledge source ensures the consistency and accuracy of all answers.

[0092] Disadvantage 4: Lack of multi-turn dialogue support capabilities: Existing technical issues: Limitations of keyword matching systems in dialogue: Loss of context: Each user question is treated as an independent event, making it impossible to understand the relationship between questions; Difficulty in information completion: When a user says "What materials are needed?", the system cannot understand that "that" refers to the previously discussed registration process; Fragmented dialogue experience: Users need to repeat background information with each question, increasing interaction costs; The root cause of the technical defects is that traditional systems lack dialogue state management and contextual understanding capabilities.

[0093] The solution in this application embodiment is: multi-turn dialogue context management: dialogue state tracking: maintaining a complete dialogue history and user intent state; intent continuation: identifying the logical relationship between subsequent questions and previous questions.

[0094] Disadvantage 5: Inadequate allocation of human customer service resources: Reasoning for existing technical problems: Resource allocation issues due to complete reliance on human customer service: High proportion of repetitive work: 80% of user questions are common, but still require manual answers one by one; Response delays during peak periods: During peak periods of user inquiries, work orders are backlogged, and the average response time is extended to more than 30 minutes; Difficulty in transferring professional knowledge: New customer service staff require long-term training to master the professional knowledge of pollution rights trading; The root cause of the technical defect is the lack of an intelligent triage mechanism, which makes it impossible to distinguish between simple and complex problems, resulting in a waste of human resources.

[0095] The solution implemented in this application is based on an AI-human collaborative service model: Intelligent problem classification: AI automatically identifies the complexity of problems, handling simple problems directly and transferring complex problems to human agents; Knowledge assistance system: providing intelligent knowledge recommendations for human customer service to improve the quality and efficiency of responses; Load balancing: AI handles most basic inquiries, while human agents focus on handling high-value, complex problems.

[0096] Based on the same inventive concept, this application also provides a pollution rights trading guidance system corresponding to the pollution rights trading guidance method. Since the principle of the system in this application is similar to the pollution rights trading guidance method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0097] Reference Figure 3 The diagram shown is a schematic of a pollution rights trading guidance system provided in an embodiment of this application. The system includes: The acquisition module 301 is used to acquire the original operation sequence of the first user when the first user performs a pollution rights trading operation in the pollution rights trading system; each original pollution rights trading operation item in the original operation sequence carries operation behavior data. The identification module 302 is used to identify abnormal pollution discharge rights trading operation items in the abnormal operation sequence in the original operation sequence and the abnormal operation features corresponding to the abnormal operation sequence based on the operation behavior data carried by each original pollution discharge rights trading operation item. The generation module 303 is used to generate a process guidance scheme based on the abnormal pollution discharge rights trading operation item and the abnormal operation characteristics; The process guidance module 304 is used to guide the first user through the pollution rights trading process based on the process guidance scheme.

[0098] In one possible implementation, the identification module 302 is specifically used to match the original operation sequence with preset regular expressions corresponding to each preset operation trajectory pattern to obtain an abnormal operation sequence and an abnormal operation trajectory pattern corresponding to the abnormal operation sequence; the abnormal operation sequence includes abnormal pollution discharge rights trading operation items; the abnormal operation trajectory pattern and preset pollution discharge rights trading operation thresholds corresponding to each preset operation behavior index are used to perform anomaly detection on the operation behavior data corresponding to the abnormal operation sequence to obtain the abnormal confidence level and abnormal operation behavior index corresponding to the abnormal operation sequence in the abnormal operation features; if the abnormal confidence level is greater than the preset confidence level threshold, the abnormal operation category corresponding to the abnormal operation sequence in the abnormal operation features is determined according to the abnormal operation pattern corresponding to the abnormal operation sequence, the abnormal confidence level, the abnormal operation behavior index, and the abnormal pollution discharge rights trading operation items in the abnormal operation sequence.

[0099] In one possible implementation, the generation module 303 is specifically configured to: search for a guidance template that meets the corresponding guidance conditions from the pollution rights trading guidance knowledge base based on the abnormal pollution rights trading operation items and abnormal operation characteristics; add text to each guidance item in the guidance template based on the abnormal pollution rights trading operation items to obtain the process guidance content in the process guidance scheme; and determine the display parameters of the process guidance content in the process guidance scheme based on the abnormal confidence level in the abnormal operation characteristics.

[0100] In one possible implementation, the generation module 303 is further configured to: Based on the abnormal pollution discharge rights trading operation items, the abnormal operation category and abnormal confidence level in the abnormal operation characteristics, a precise match is made from the pollution discharge rights trading guidance knowledge base; If no matching guidance template is found that meets the corresponding guidance conditions, a fuzzy match is performed from the pollution rights trading guidance knowledge base based on the abnormal operation category in the abnormal operation characteristics. If no fuzzy match is found that matches the corresponding guidance conditions, the preset general guidance template will be determined as the guidance template that matches the corresponding guidance conditions.

[0101] In one possible implementation, the system further includes a guidance backtracking module 305. Specifically, after the first user completes the pollution rights trading operation, the guidance backtracking module 305 acquires complete transaction operation behavior data, process guidance records, and transaction operation results of the first user during the execution of the pollution rights trading operation; determines the process guidance result corresponding to the first user based on the complete transaction operation behavior data, process guidance records, and the transaction operation results; if the process guidance result is successful, extracts the latest successful transaction process path corresponding to the pollution rights trading operation from the complete transaction operation behavior data; and determines the standard transaction process path with the highest transaction success rate based on the latest successful transaction process path and all historical successful transaction process paths in the pollution rights trading process database, so as to provide process guidance when the second user deviates from the standard transaction process path.

[0102] In one possible implementation, the guide backtracking module 305 is further configured to: If the process guidance result is guidance failure, then the latest failed transaction process path corresponding to the pollution rights trading operation is extracted from the complete transaction operation behavior data; Based on the latest failed transaction process path and all historical failed transaction process paths in the pollution rights trading process database, the risky pollution rights trading operation item and risky transaction process path with the highest transaction failure rate are determined, so as to provide process warning when the second user executes the risky pollution rights trading operation item or follows the risky transaction process path.

[0103] In one possible implementation, the system further includes an intelligent question-answering module 306, which is specifically used to standardize the pollution rights trading question input by the first user to obtain a standard text of the pollution rights trading question; and to obtain the pollution rights trading history dialogue of the first user; input the standard text of the pollution rights trading question into a question feature extraction model to obtain a question feature vector corresponding to the pollution rights trading question; the question feature vector includes pollution rights trading intent and pollution rights trading entity; retrieve pollution rights trading documents from the pollution rights trading knowledge base based on the pollution rights trading question vector corresponding to the standard text of the pollution rights trading question and the question feature vector; and input the pollution rights trading history dialogue, the pollution rights trading question, and the retrieved pollution rights trading documents into an answer generation model to obtain a pollution rights trading answer corresponding to the pollution rights trading question.

[0104] This application provides a pollution rights trading guidance system, which can effectively solve user operation bottlenecks and improve user experience and platform operation efficiency.

[0105] like Figure 4As shown in the embodiment of this application, an electronic device 400 includes a processor 401, a memory 402, and a bus. The memory 402 stores machine-readable instructions executable by the processor 401. When the electronic device is running, the processor 401 communicates with the memory 402 via the bus, and the processor 401 executes the machine-readable instructions to perform the steps of the pollution rights trading guidance method described above.

[0106] Specifically, the memory 402 and processor 401 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 401 runs the computer program stored in the memory 402, it can execute the above-mentioned pollution rights trading guidance method.

[0107] Corresponding to the above-described method for guiding emissions trading, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described method for guiding emissions trading.

[0108] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0109] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0111] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0112] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for guiding emissions trading, characterized in that, The method includes: When the first user performs a pollution rights trading operation in the pollution rights trading system, the first user's original operation sequence is obtained; each original pollution rights trading operation item in the original operation sequence carries operation behavior data. Based on the operational behavior data carried by each original pollution discharge rights trading operation item, identify the abnormal pollution discharge rights trading operation items in the abnormal operation sequence in the original operation sequence and the abnormal operation characteristics corresponding to the abnormal operation sequence. Based on the abnormal pollution discharge rights trading operation items and the abnormal operation characteristics, a process guidance scheme is generated; Based on the aforementioned process guidance scheme, the process of trading pollution discharge rights is guided for the first user; The step of identifying aberrant pollution rights trading operation items in aberrant operation sequences within the original operation sequence and the aberrant operation characteristics corresponding to the aberrant operation sequences based on the operational behavior data carried by each original pollution rights trading operation item includes: The original operation sequence is matched with the preset regular expressions corresponding to each preset operation trajectory pattern to obtain the abnormal operation sequence and the abnormal operation trajectory pattern corresponding to the abnormal operation sequence; the abnormal operation sequence includes abnormal pollution discharge rights trading operation items; the preset operation trajectory pattern refers to the operation sequence manifestation form that does not conform to normal operation logic, and is a specific operation trajectory feature that can be identified through regular expression matching. The abnormal operation trajectory pattern and the preset pollution discharge rights trading operation thresholds corresponding to each preset operation behavior index are used to perform anomaly detection on the corresponding operation behavior data in the abnormal operation sequence to obtain the anomaly confidence and anomaly operation behavior index corresponding to the abnormal operation sequence in the abnormal operation features; the higher the anomaly confidence, the greater the probability that the abnormal operation sequence is an abnormal operation. If the anomaly confidence level is greater than a preset confidence threshold, then the anomaly operation pattern corresponding to the anomaly operation sequence, the anomaly confidence level, the anomaly operation behavior index, and the anomaly pollution discharge rights trading operation item in the anomaly operation sequence are matched with the decision tree logic corresponding to each preset operation category; the preset operation category that is successfully matched is determined as the anomaly operation category corresponding to the anomaly operation sequence in the anomaly operation features; the anomaly operation category is a classification and summary of the user's anomaly operation behavior.

2. The method for guiding emissions trading according to claim 1, characterized in that, The step of generating a process guidance scheme based on the abnormal pollution discharge rights trading operation item and the abnormal operation characteristics includes: Based on the abnormal emission rights trading operation items and abnormal operation characteristics, search the emission rights trading guidance knowledge base for guidance templates that meet the corresponding guidance conditions; Based on the abnormal pollution discharge rights trading operation items, text is added to each guide item in the guide template to obtain the process guidance content in the process guidance scheme; Based on the abnormal confidence level in the abnormal operation characteristics, the display parameters of the process guidance content in the process guidance scheme are determined.

3. The method for guiding emissions trading according to claim 2, characterized in that, The step of searching for a guidance template that meets the corresponding guidance conditions from the pollution rights trading guidance knowledge base based on the abnormal pollution rights trading operation items and abnormal operation characteristics includes: Based on the abnormal pollution discharge rights trading operation items, the abnormal operation category and abnormal confidence level in the abnormal operation characteristics, a precise match is made from the pollution discharge rights trading guidance knowledge base; If no matching guidance template is found that meets the corresponding guidance conditions, a fuzzy match is performed from the pollution rights trading guidance knowledge base based on the abnormal operation category in the abnormal operation characteristics. If no fuzzy match is found that matches the corresponding guidance conditions, the preset general guidance template will be determined as the guidance template that matches the corresponding guidance conditions.

4. The method for guiding emissions trading according to any one of claims 1 to 3, characterized in that, The method further includes: After the first user completes the pollution discharge rights trading operation, obtain the complete transaction operation behavior data, process guidance record and transaction operation result of the first user in the process of executing the pollution discharge rights trading operation; Based on the complete transaction operation behavior data, process guidance record and transaction operation result, determine the process guidance result corresponding to the first user; If the process guidance result is successful, then the latest successful transaction process path corresponding to the pollution discharge rights trading operation is extracted from the complete transaction operation behavior data. Based on the latest successful transaction process path and all historical successful transaction process paths in the pollution rights trading process database, a standard transaction process path with the highest success rate is determined, so as to guide the process when a second user deviates from the standard transaction process path.

5. The method for guiding emissions trading according to claim 4, characterized in that, The method further includes: If the process guidance result is guidance failure, then the latest failed transaction process path corresponding to the pollution rights trading operation is extracted from the complete transaction operation behavior data; Based on the latest failed transaction process path and all historical failed transaction process paths in the pollution rights trading process database, the risky pollution rights trading operation item and risky transaction process path with the highest transaction failure rate are determined, so as to provide process warning when the second user executes the risky pollution rights trading operation item or follows the risky transaction process path.

6. The method for guiding emissions trading according to claim 1, characterized in that, The method further includes: The pollution rights trading question input by the first user is standardized to obtain a standard text of the pollution rights trading question; and the pollution rights trading history of the first user is obtained. The standard text of the pollution rights trading issue is input into the issue feature extraction model to obtain the issue feature vector corresponding to the pollution rights trading issue; the issue feature vector includes the pollution rights trading intention and the pollution rights trading entity; Based on the emission rights trading question vector corresponding to the standard text of the emission rights trading question and the question feature vector, emission rights trading documents are retrieved from the emission rights trading knowledge base; The historical dialogues on pollution rights trading, the pollution rights trading questions, and the retrieved pollution rights trading documents are input into the answer generation model to obtain the pollution rights trading answer corresponding to the pollution rights trading questions.

7. A pollution rights trading guidance system, characterized in that, The system includes: The acquisition module is used to acquire the original operation sequence of the first user when the first user performs pollution rights trading operations in the pollution rights trading system; each original pollution rights trading operation item in the original operation sequence carries operation behavior data. The identification module is used to identify abnormal pollution rights trading operation items in the abnormal operation sequence and the abnormal operation features corresponding to the abnormal operation sequence based on the operation behavior data carried by each original pollution rights trading operation item. The generation module is used to generate a process guidance scheme based on the abnormal pollution discharge rights trading operation items and the abnormal operation characteristics; The process guidance module is used to guide the first user through the pollution rights trading process based on the process guidance scheme. Specifically, the identification module is used to match the original operation sequence with preset regular expressions corresponding to each preset operation trajectory pattern to obtain an abnormal operation sequence and the abnormal operation trajectory pattern corresponding to the abnormal operation sequence; the abnormal operation sequence includes abnormal pollution discharge rights trading operation items; the preset operation trajectory pattern refers to the operation sequence manifestation form that does not conform to normal operation logic, and is a specific operation trajectory feature that can be identified through regular expression matching; the abnormal operation trajectory pattern and the preset pollution discharge rights trading operation thresholds corresponding to each preset operation behavior indicator are used to perform anomaly detection on the corresponding operation behavior data in the abnormal operation sequence to obtain the abnormal operation. The abnormal operation sequence is defined in the feature as having an abnormal confidence level and an abnormal operation behavior index. The higher the abnormal confidence level, the greater the probability that the abnormal operation sequence is an abnormal operation. If the abnormal confidence level is greater than a preset confidence threshold, then the abnormal operation mode corresponding to the abnormal operation sequence, the abnormal confidence level, the abnormal operation behavior index, and the abnormal pollution discharge rights trading operation item in the abnormal operation sequence are matched with the decision tree logic corresponding to each preset operation category. The preset operation category that is successfully matched is determined as the abnormal operation category corresponding to the abnormal operation sequence in the abnormal operation feature. The abnormal operation category is a classification and summary of the user's abnormal operation behavior.

8. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the pollution rights trading guidance method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the pollution rights trading guidance method as described in any one of claims 1 to 6.

Images