Request processing method, electronic equipment, storage medium and program product

Abstract

The invention provides a request processing method, electronic equipment, a readable storage medium and a computer program product. The request processing method comprises the following steps: receiving request information input by a user; intention recognition is conducted on the request information, the request type of the request information is determined, and the request type is a calculation type request or a query type request; if the request type is a calculation type request, extracting a structured request parameter in the request information, generating structured request data based on the structured request parameter, and determining a calculation engine suitable for the request information based on the structured request data; and inputting the structured request data into a calculation engine to obtain calculation result information corresponding to the request information.

Description

Technical Field

[0001] This disclosure relates to the technical fields of request processing, and in particular to a request processing method, electronic device, storage medium, and program product. Background Technology

[0002] In the real estate transaction sector, especially in the buying and selling of second-hand homes, various taxes and fees are involved, including deed tax, value-added tax, personal income tax, and stamp duty. The calculation rules for these taxes and fees vary depending on the type of tax and are influenced by multiple factors such as the nature of the property (ordinary or non-ordinary residential), the length of ownership, whether it is the first home purchase, and local city policies, making them highly complex and time-sensitive. For example, the deed tax rate varies depending on the city, property type, and size; whether value-added tax is exempt depends on whether the property has been held for two or five years; and personal income tax can be levied in full or on a differential basis. Currently, the calculation of these taxes and fees typically relies on manual parameter input by the user. The calculation logic is complex and prone to overlooking implicit conditions (such as policy adjustments or special property attributes), making it difficult for ordinary users to accurately grasp the calculation methods. Real estate agents also need to spend a significant amount of time verifying parameters in practice, making it difficult to guarantee the accuracy of the calculation results and processing efficiency.

[0003] Furthermore, mortgage calculations require comprehensive consideration of multiple variables, including loan amount, loan term, interest rate, and repayment method (such as equal principal and interest payments or equal principal payments). Different combinations of parameters result in significant differences in monthly payments and total interest expenses, directly impacting users' home-buying decisions. Existing loan calculation tools are mostly general-purpose applications, typically requiring users to input each parameter individually, leading to cumbersome interaction processes and making it difficult for users to quickly compare interest rate differences between different loan options, thus affecting decision-making efficiency.

[0004] Meanwhile, real estate transactions involve a large amount of policies, regulations, transaction procedures, and related professional knowledge, which are characterized by their distinct regional, professional, and dynamically updated nature. Ordinary users find it difficult to fully access and understand this information, while real estate agents, when providing consultation services, often need to memorize numerous policy clauses or consult scattered sources, making it difficult to ensure the accuracy of their responses. Summary of the Invention

[0005] This disclosure provides a request processing method, an electronic device, a storage medium, and a program product.

[0006] According to one aspect of this disclosure, a request processing method is provided, the method comprising: Receive user input request information; The request information is subjected to intent recognition to obtain intent recognition results. Based on the intent recognition results, the request type of the request information is determined, and the request type is either a calculation request or a query request. If the request type is a computational request, extract the structured request parameters from the request information, generate structured request data based on the structured request parameters, and determine the computational engine applicable to the request information based on the structured request data; The structured request data is input into the computing engine to obtain the calculation result information corresponding to the request information.

[0007] According to at least one embodiment of the request processing method of this disclosure, if the request type is a query request, query keywords are extracted from the request information, and matching information is retrieved from a preset knowledge base based on the query keywords; If matching information is found, query results are generated and output based on the matching information. If no matching information is found, external related data is searched based on the query keywords, and query results are generated and output based on the searched external related data.

[0008] According to a request processing method of at least one embodiment of this disclosure, the request information is subjected to intent recognition to obtain an intent recognition result, and the request type of the request information is determined based on the intent recognition result, including: Extract key descriptive information (keywords / keywords, and / or property codes, etc.) from the request information. Based on preset business scenario matching rules, the key description information is matched with business scenarios to determine the target business scenario; The request type of the request information is determined based on the target business scenario.

[0009] A request processing method according to at least one embodiment of this disclosure generates structured request data based on the structured request parameters, including: The target request body template corresponding to the structured request parameters is determined based on the structured request parameters, and the target request body template includes a calculation task type field; The structured request parameters are used to fill or replace the corresponding parameter fields in the target request body template to generate the structured request data.

[0010] According to at least one embodiment of the request processing method of this disclosure, before determining the target request body template corresponding to the structured request parameters based on the structured request parameters, generating structured request data based on the structured request parameters, the method further includes: Determine whether the structured request parameters include a property listing code; If a property code is included, property information corresponding to the property code is retrieved from a preset property database, and the structured request parameters are supplemented based on the property information.

[0011] According to a request processing method of at least one embodiment of the present disclosure, determining the applicable computing engine for the request information based on the structured request data includes: Extract the computation task type field from the structured request data; Based on preset computing engine mapping rules, the computing engine corresponding to the computing task type field is determined, and it is determined as the computing engine applicable to the request information.

[0012] According to at least one embodiment of the request processing method of this disclosure, determining the target request body template corresponding to the structured request parameters based on the structured request parameters includes: The computation task type field is determined based on the mapping relationship between the combination of request parameters in the structured request parameters and the computation task type field. The target request body template corresponding to the structured request parameters is determined based on the computation task type field.

[0013] According to at least one embodiment of the request processing method of this disclosure, determining the computation task type field based on the mapping relationship between the combination of request parameters in the structured request parameters and the computation task type field includes: If the request parameter combination includes a combination of total house price and whether it is a first-time home purchase, then the calculation task type field is determined to be a tax calculation task; If the request parameter combination includes a combination of loan amount and loan term, then the calculation task type field is determined to be a loan calculation task.

[0014] According to another aspect of this disclosure, an electronic device is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, causing the processor to perform a request processing method according to any embodiment of this disclosure.

[0015] According to another aspect of this disclosure, a readable storage medium is provided, wherein executable instructions are stored therein, which, when executed by a processor, are used to implement a request processing method according to any embodiment of this disclosure.

[0016] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements a request processing method according to any embodiment of this disclosure. Attached Figure Description

[0017] The accompanying drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0018] Figure 1 A schematic diagram of the overall flow of a request processing method according to one embodiment of the present disclosure is shown.

[0019] Figure 2 This is a flowchart illustrating a request processing method according to another embodiment of this disclosure.

[0020] Figure 3 This is a flowchart illustrating the process of determining the request type of request information according to one embodiment of this disclosure.

[0021] Figure 4 This is a schematic diagram of a process for generating structured request data based on structured request parameters, according to one embodiment of this disclosure.

[0022] Figure 5 This is a flowchart illustrating another embodiment of the present disclosure of generating structured request data based on structured request parameters.

[0023] Figure 6 This is a flowchart illustrating an embodiment of the present disclosure of determining the applicable computing engine for the request information based on the structured request data.

[0024] Figure 7 This is a flowchart illustrating a preferred embodiment of the present disclosure of determining the target request body template corresponding to the structured request parameters based on the structured request parameters.

[0025] Figure 8 This is a schematic block diagram of the structure of a request processing apparatus according to one embodiment of the present disclosure.

[0026] Figure 9 This is a schematic block diagram of an electronic device according to one embodiment of the present disclosure. Detailed Implementation

[0027] The present disclosure will now be described in further detail with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are for illustrative purposes only and are not intended to limit the scope of the disclosure. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present disclosure are shown in the accompanying drawings.

[0028] It should be noted that, where there is no conflict, the embodiments and features described in this disclosure can be combined with each other. The technical solutions of this disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] In real estate transaction scenarios, such as second-hand housing transactions, users and brokers handle requests for tax calculation, loan calculation, and policy inquiries. Existing technologies are insufficient in request identification, structured parameter extraction, and computing resource matching, resulting in low processing efficiency and poor result accuracy.

[0030] Therefore, this disclosure proposes a request processing method.

[0031] Figure 1 A schematic diagram of the overall flow of a request processing method M100 according to one embodiment of this disclosure is shown. Figure 1 The method shown includes steps S110 to S140. This method can be executed by electronic devices such as mobile phones and computers.

[0032] Specifically, Figure 1 The methods shown include: S110, Receive request information input by the user.

[0033] For example, in the context of second-hand housing transactions, users (the real estate transaction party or real estate agent, etc.) can submit request information related to tax calculation, loan calculation, and policy inquiry through various input methods.

[0034] User input requests can be received via electronic devices (such as mobile phones, computers, etc.). Request information can be text, voice, property codes, etc., and can be in the form of natural language descriptions (such as "taxes and fees for a first home with a total price of 1 million"), voice commands, or property codes (such as "BJ123456").

[0035] Preferably, the process of receiving request information supports multimodal input. The electronic device can receive the request information submitted by the user through a preset input interface (such as a text box, a speech recognition module, or an encoded input box), providing a basis for subsequent intent recognition and parameter extraction.

[0036] S120. Perform intent recognition on the request information to obtain intent recognition results, and determine the request type of the request information based on the intent recognition results.

[0037] Step S120 can determine whether the request type of the request information is a calculation request or a query request by performing intent recognition on the request information received in step S110.

[0038] Specifically, natural language processing modules or rule matching algorithms can be used to perform semantic analysis on the request information, identify user intent, and classify it into calculation requests (such as tax or loan calculations) or query requests (such as policy regulations or transaction processes).

[0039] By performing intent recognition on the request information, step S120 can accurately distinguish diverse user request types, improving the targeting and efficiency of request processing in scenarios such as second-hand housing transactions.

[0040] Intent recognition of request information can be achieved through an intent recognition module / model (software), which can be in the form of an intelligent agent (i.e., a first intelligent agent, such as an artificial intelligence model).

[0041] S130. If the request type is a computational request, extract the structured request parameters from the request information, generate structured request data based on the structured request parameters, and determine the computational engine applicable to the request information based on the structured request data.

[0042] Specifically, structured parameters (such as total house price, loan amount, etc.) can be extracted from the request information through a parsing module / model. Below is an example of structured request parameters: Mortgage calculation: Is it your first home purchase? Yes; Loan method: Equal principal repayment; Total house price: 1 million; Loan term: 30 years.

[0043] In step S130, after extracting the structured request parameters from the request information, structured request data that can be executed by the computing engine is generated based on the extracted structured request parameters. The specific type of the structured request data can be a JSON request body. Those skilled in the art can also select or adjust the specific type of the structured request data, all of which fall within the protection scope of this disclosure.

[0044] The generation of structured request data based on the extracted structured request parameters can be achieved through a request data generation module / model.

[0045] In some implementations, preferably, the request data generation module / model fills the above-mentioned structured request parameters into structured request data (e.g., JSON request body) according to a preset structured request data template (e.g., JSON request body template).

[0046] The following is an example of structured request data generated based on the structured request parameters mentioned above: Json: { "task_type": "loan_calculation", "parameters": { "is_first": true, "repayment_method": "equal_principal", "price": 1000000, "loan_years": 30, "loan_rate": 4.9 }, "metadata": { "source": "user_input", "timestamp": "20XX-07-23T14:57:00+08:00" } } In step S130, after obtaining the structured request data, a calculation engine can be used to determine the applicable calculation engine for the request information based on the structured request data.

[0047] Among them, the calculation engine determination module / model can identify the type of calculation task (such as loan calculation / tax calculation) by analyzing task-related information in the structured request data, and select the corresponding calculation engine (such as loan calculation engine / tax calculation engine).

[0048] Multiple computing engines (i.e. computing execution modules) can be pre-configured.

[0049] Step S130 achieves efficient data organization and task adaptation by automatically extracting structured request parameters, generating structured request data (such as JSON request body), and matching it with the computing engine.

[0050] S140. Input the structured request data into the computing engine to obtain the calculation result information corresponding to the request information and output it to the user.

[0051] In some embodiments of this disclosure, the functions implemented by the parsing module, the request data generation module, and the calculation engine determination module in step S130 above can also be implemented by an intelligent agent (a second intelligent agent, i.e., an artificial intelligence model), and all of these fall within the protection scope of this disclosure.

[0052] The multiple computing engines in step S140 above can also be configured as a single intelligent agent (i.e., a third intelligent agent), all of which fall within the protection scope of this disclosure.

[0053] As can be seen, the request processing method disclosed herein, through modular process design, combined with multimodal input processing, intent recognition, structured request parameter extraction, structured request data generation, and calculation engine matching, achieves automated processing of user-input request information, significantly improving the automation level, processing efficiency, and accuracy of calculation results in scenarios such as second-hand housing transactions.

[0054] Figure 2 This is a flowchart illustrating a request processing method according to another embodiment of this disclosure.

[0055] Figure 2 The request processing method M200 shown includes steps S210 to S250.

[0056] Step S210 is the same as step S110 described above, and step S220 is the same as step S120 described above, so they will not be repeated here.

[0057] In S230, if the request type is a query request, query keywords are extracted from the request information, and matching information is retrieved from a preset knowledge base based on the query keywords.

[0058] Taking the second-hand housing transaction scenario as an example, if step S220 determines that the request type is a query request (such as policy and regulations or transaction process query), step S230 can extract query keywords (such as "deed tax policy" and "Beijing") from the request information received in step S210 through a query extraction module, and retrieve matching information from the preset knowledge base based on these keywords.

[0059] In some embodiments of this disclosure, natural language processing technology can be used to analyze the text or voice content (which can be converted into text) in the request information and extract keywords related to the query intent.

[0060] Subsequently, a search module can be used to match keywords with knowledge entries in the aforementioned preset knowledge base to retrieve information containing relevant policies or procedures.

[0061] The pre-set knowledge base can store data related to policies, regulations, and transaction processes such as second-hand housing transactions, and supports keyword retrieval.

[0062] For example, when a user inputs the request information "Beijing first-home deed tax policy", the query extraction module extracts the query keywords "deed tax policy", "Beijing" and "first home", and the retrieval module retrieves knowledge entries related to Beijing's deed tax policy from the knowledge base (such as "first home deed tax rate 1%", i.e., matching information).

[0063] Continue to refer to Figure 2In some embodiments of this disclosure, step S240 or step S250 is performed after step S230.

[0064] S240. If matching information is found, generate and output query result information based on the matching information (this process can be implemented by a first query result generation module, and the query result information can be structured query result information).

[0065] S250. If no matching information is found, search for relevant external data based on the query keywords and generate and output query result information based on the searched relevant external data.

[0066] In scenarios such as second-hand housing transactions, if step S230 fails to retrieve a knowledge entry (i.e., matching information) that matches the query keywords (such as "deed tax policy" or "Beijing") in the preset knowledge base, step S250 can use an external data retrieval module to search for relevant external data sources (such as policy and regulation databases or official announcement websites) based on the query keywords extracted in step S230 to obtain the latest policy or process information.

[0067] Specifically, the external data retrieval module can call the network search function or connect to the preset external data source through the external data interface, and use the query keywords to search and obtain external data related to second-hand housing transactions (such as the latest deed tax policy).

[0068] Subsequently, a second query result generation module can parse and organize the searched external data to generate query result information (such as policy terms or process descriptions), and return it to the user through an output interface (such as screen display or voice broadcast).

[0069] Step S250 can be implemented based on an external data retrieval algorithm (external data retrieval module) and a result generation algorithm (second query result generation module) to ensure the accuracy and completeness of the query result information.

[0070] For example, if the user inputs the request information "Beijing first-home deed tax policy", and step S230 does not find matching information in the knowledge base, the external data retrieval module uses the query keywords "deed tax policy", "Beijing", and "first home" to search for the latest deed tax policy from external policy and regulation databases or official announcement websites (such as "Beijing first-home deed tax rate adjusted to 1.5%)". The second query result generation module organizes this information and outputs it as query result information (which can be structured query result information).

[0071] In step S230, the query extraction module and the retrieval module can be configured as a single agent; in step S240, the first query result generation module can be configured as a single agent; and in step S250, the external data retrieval module and the second query result generation module can be configured as a single agent. Alternatively, the query extraction module, the retrieval module, the first query result generation module, the external data retrieval module, and the second query result generation module can be configured as a single agent (i.e., the fourth agent).

[0072] Any adjustments or changes made by those skilled in the art to the specific implementation modules, model architecture, etc. of the above steps based on the technical solutions disclosed herein shall fall within the protection scope of this disclosure.

[0073] Figure 3 This is a flowchart illustrating the process of determining the request type of request information according to one embodiment of this disclosure.

[0074] refer to Figure 3 For the request processing methods of the various embodiments described above, the process of performing intent recognition on the request information, obtaining intent recognition results, and determining the request type of the request information based on the intent recognition results includes: S302. Extract key description information (keywords / keywords, and / or property codes, etc.) from the request information. S304. Based on preset business scenario matching rules, perform business scenario matching on the key description information to determine the target business scenario; S306. Determine the request type of the request information based on the target business scenario.

[0075] In step S302, the intent recognition module / model described above can be used to match the keywords extracted in step S302 (such as "taxes", "loans", "deed tax policy") with business scenarios to determine the target business scenario (such as tax calculation, loan calculation, policy query) corresponding to the requested information.

[0076] Specifically, based on preset business scenario matching rules (such as preset business scenario prompt templates or rule bases), the correlation between keywords and various business scenarios, such as second-hand housing transactions, can be analyzed.

[0077] In some embodiments of this disclosure, the above-mentioned prompt template may contain predefined keyword-scenario mapping relationships. For example, "taxes" and "deed tax" correspond to tax calculation scenarios, "loans" and "monthly payments" correspond to loan calculation scenarios, and "policies" or "regulations" correspond to policy query scenarios.

[0078] The intent recognition module can use semantic analysis or rule matching algorithms to compare keywords with the scene description in the prompt template to determine the most matching target business scenario.

[0079] For example, for the request information "taxes and fees for a first home with a total price of 1 million", S302 extracts the key description information "taxes and fees" and "first home", and S304 determines the target business scenario as "tax calculation" by matching the prompt template.

[0080] After identifying the target business scenario, step S306 uses the intent recognition module to determine whether the request type of the request information is a calculation request or a query request based on the mapping relationship between the business scenario and the request type.

[0081] Specifically, based on preset scenario-request type mapping rules, scenarios such as tax calculation or loan calculation can be mapped to calculation requests, and scenarios such as policy query or transaction process query can be mapped to query requests.

[0082] The intent recognition module can associate the target business scenario with the request type through logical judgment or classification algorithm to complete the determination of the above request type.

[0083] For example, for the "tax calculation" scenario identified in S304, S306 determines the request type as "calculation request" based on the scenario-request type mapping rule; for the "policy query" scenario, it is determined as "query request".

[0084] In some embodiments of this disclosure, if the intent recognition module cannot determine the request type of the request information in step S120 or step S220 described above, such as when the user inputs a vague or unclear request information, such as "Tell me what this system can do" or "How to calculate taxes", a user guidance module (which can be a sub-module of the intent recognition module or an independent module of the first intelligent agent described above) can generate and output guidance information to prompt the user for available functions or operating methods.

[0085] Specifically, the aforementioned intent recognition module can analyze the request information and detect whether it contains explicit business scenario keywords (such as "taxes", "loans", "policies").

[0086] If a business scenario cannot be matched, the user guidance module can retrieve functional descriptions related to second-hand housing transactions (such as tax calculation, loan calculation, policy inquiry instructions, etc.) from the preset guidance information database as guidance information to provide to the user, or generate dynamic guidance prompts to suggest that the user provide more specific request information (such as total house price, loan term or policy inquiry keywords).

[0087] Guidance information or prompts can be provided to users through output interfaces (such as screen display or voice broadcast).

[0088] For example, when a user inputs the request information "how to calculate taxes", the intent recognition module in steps S120 / S220 cannot directly determine a specific business scenario (because there are no specific business scenario keywords). The user guidance module detects the keyword "taxes" and retrieves the function description of tax calculation from the guidance information database to generate guidance information: Please provide information such as the total price of the house and whether it is the first house to calculate taxes, such as "taxes for the first house with a total price of 1 million".

[0089] Figure 4 This is a schematic diagram of a process for generating structured request data based on structured request parameters, according to one embodiment of this disclosure.

[0090] refer to Figure 4 In some embodiments of this disclosure, the step S130 described above, which generates structured request data based on the structured request parameters, preferably includes: S402. Determine the target request body template (i.e., the preset request body) corresponding to the structured request parameters based on the structured request parameters. The target request body template includes a calculation task type field. S404. Use the structured request parameters to fill or replace the corresponding parameter fields in the target request body template to generate the structured request data.

[0091] In step S402, the request data generation module described above (which can be a sub-module of the second intelligent agent) can determine the target request body template corresponding to the structured request parameters (such as total house price, whether it is the first house, and loan term) extracted in step S130.

[0092] Specifically, a set of preset request body templates (such as JSON format templates) can be maintained. Each request body template corresponds to a specific calculation task type (such as tax calculation, loan calculation) and includes a calculation task type field (such as task_type) and parameter fields (such as price, is_first).

[0093] The request data generation module analyzes the structured request parameters and, based on predefined request parameter-request body template mapping rules, identifies the calculation task type that matches the request parameters (such as the tax calculation templates corresponding to "total house price" and "whether it is the first home purchase"), and then selects the corresponding target request body template.

[0094] For example, for the structured request parameter "Total house price: 1 million, First-time homebuyer: Yes", S402 analyzes the parameter combination, determines the calculation task type as "Tax Calculation" based on the request parameter-request body template mapping rule, and selects the corresponding JSON request body template: Json: { "task_type": "tax_calculation", "parameters": { "price": null, "is_first": null }, "metadata": { "source": null, "timestamp": null } } Step S402 can be achieved through rule matching or logical judgment to ensure the accurate correspondence between the structured request parameters and the request body template.

[0095] After determining the target request body template in step S402, step S404 uses the request data generation module to fill or replace the structured request parameters extracted in step S130 into the corresponding parameter fields of the target request body template selected in S402, and fill or replace the determined computing task type into the computing task type field of the target request body template, thereby generating structured request data that can be executed by the computing engine.

[0096] Specifically, based on the parameter field definitions in the target request body template (such as price, is_first), the key-value pairs of the structured request parameters can be mapped one by one to the template parameter fields, and specific values ​​(such as 1000000, true) can be filled in. Metadata fields (such as source, timestamp) can also be added.

[0097] If the template parameter fields do not completely match the structured request parameters, default values ​​or empty values ​​can be used to ensure that complete structured request data (such as JSON request body) is generated.

[0098] For example, based on the tax calculation template selected in S402, S404 fills the structured request parameters "Total house price: 1 million, First-time homebuyer: Yes" into the template field, generating structured request data: Json: { "task_type": "tax_calculation", "parameters": { "price": 1000000, "is_first": true }, "metadata": { "source": "user_input", "timestamp": "20XX-07-23T14:57:00+08:00" } } Step S404 can be implemented using a data mapping algorithm.

[0099] Figure 5 This is a flowchart illustrating another embodiment of the present disclosure of generating structured request data based on structured request parameters, including steps S502, S504, S506, and S508.

[0100] S506 is the same as S402, and S508 is the same as S404, so they will not be described again.

[0101] refer to Figure 5 Preferably, before S506, determining the target request body template corresponding to the structured request parameters based on the structured request parameters, generating structured request data based on the structured request parameters further includes: S502. Determine whether the structured request parameters include the property code; S504. If a property code is included, retrieve property information corresponding to the property code from a preset property database based on the property code, and supplement the structured request parameters based on the property information.

[0102] In step S502, a parameter parsing module (which can be a sub-module of the second agent) can be used to check the structured request parameters extracted in step S130 to determine whether they contain a housing code (such as "BJ123456").

[0103] Specifically, the parameter parsing module can detect the existence of predefined housing code by analyzing the fields of the structured request parameters.

[0104] A property code is a unique identifier associated with a specific property. It is usually composed of letters and numbers and is used to identify the property's attribute information (such as total price, area, and whether it is a first-time home purchase).

[0105] The parameter parsing module can determine the existence of a property code through field matching or rule checking algorithms.

[0106] If a property code is detected, S504 is triggered to retrieve property information; if no property code is found, proceed directly to S506.

[0107] For example, for the structured request parameter "Property Code: BJ123456, First-time Homebuyer: Yes", S502 checks the parameter field, detects "BJ123456", and confirms that it contains the property code.

[0108] If S502 confirms that the structured request parameters include a housing code, step S504 can retrieve the corresponding housing information (such as total house price, area, and property rights term) from the preset housing database based on the housing code through a housing information retrieval module (which can be a sub-module of the second intelligent agent).

[0109] Specifically, the property code can be used as the query key to access the property database through the database query interface and obtain the property record that matches the code.

[0110] Preferably, the retrieved property information is parsed into a structured format and used to supplement missing fields in the structured request parameters (such as adding price or area).

[0111] The supplemented structured request parameters form a complete parameter set.

[0112] Step S504 can be implemented using a database retrieval algorithm and / or a parameter merging algorithm to ensure the integrity of the request parameters.

[0113] For example, for the structured request parameter "Property Code: BJ123456, First-time Homebuyer: Yes", S504 uses BJ123456 to query the property database and retrieves the property information "Total Price: 1 million, Area: 90 square meters". Then, "Total Price: 1 million, Area: 90 square meters" is added to the structured request parameter to form a complete parameter set: "Property Code: BJ123456, First-time Homebuyer: Yes, Total Price: 1 million, Area: 90 square meters".

[0114] Figure 5 The implementation methods shown (S502, S504, S506, S508) improve the efficiency and accuracy of generating structured request data in scenarios such as tax calculation and loan calculation by determining the property code and supplementing the structured request parameters before generating structured request data, and by using a templated data generation process, thus providing reliable data support for the accurate invocation of the calculation engine.

[0115] Figure 6 This is a flowchart illustrating an embodiment of the present disclosure of determining the applicable computing engine for the request information based on the structured request data.

[0116] refer to Figure 6 The computing engine used to determine the applicable request information based on the structured request data in S130 described above preferably includes: S602. Extract the computing task type field from the structured request data; S604. Based on the preset computing engine mapping rules, determine the computing engine corresponding to the computing task type field, and determine it as the computing engine applicable to the request information.

[0117] Step S602 can extract the computation task type field (such as task_type) from the structured request data (such as JSON request body) generated in S130 by the computation engine determination module (which can be a sub-module of the second intelligent agent) described above.

[0118] For example, in the context of second-hand housing transactions, structured request data includes a task type field (such as "tax_calculation" or "loan_calculation") to identify the specific calculation task requested by the user (such as tax calculation or loan calculation).

[0119] The computation engine's determination module can parse the structure of structured request data, locate the task type field (task_type field), and obtain its value through field extraction algorithms (such as key-value pair matching), thereby ensuring accurate identification of the computation task type field.

[0120] Step S604 uses the calculation engine determination module to map the calculation task type field (such as "tax_calculation") extracted in S602 to the corresponding calculation engine (such as tax calculation engine) based on the preset calculation engine mapping rules.

[0121] The preset mapping rules can predefine the correspondence between calculation task types and calculation engines (e.g., "tax_calculation" corresponds to the tax calculation engine, and "loan_calculation" corresponds to the loan calculation engine).

[0122] The computation engine determination module can identify the computation engine that matches the computation task type field by looking up a mapping table or a rule matching algorithm, and determine it as the computation engine (i.e., execution module) applicable to the request information, ensuring that the structured request data is efficiently and accurately allocated to the appropriate computation engine.

[0123] Figure 7 This is a flowchart illustrating a preferred embodiment of the present disclosure of determining the target request body template corresponding to the structured request parameters based on the structured request parameters.

[0124] The method for determining the target request body template corresponding to the structured request parameters based on the structured request parameters (steps S402 / S506) as described in the above-mentioned embodiments preferably includes: S7002. Determine the calculation task type field based on the mapping relationship between the combination of request parameters in the structured request parameters (the request parameters may be the total house price, house area, loan amount, loan term, whether it is the first house, etc.) and the calculation task type field; S7004. Determine the target request body template corresponding to the structured request parameters based on the computing task type field.

[0125] In step S7002, the request data generation module (which can be a sub-module of the second intelligent agent) analyzes the structured request parameters extracted in S130 and determines the corresponding calculation task type field (such as "tax_calculation" or "loan_calculation") based on the predefined mapping relationship between "request parameter combination" and "calculation task type field".

[0126] For example, in a second-hand housing transaction scenario, a combination of request parameters (which can be a combination of two or more request parameters) can be a subset of structured request parameters. This combination can include key parameter fields related to a specific calculation task (e.g., "total house price + whether it's the first home purchase" for tax calculation, "loan amount + loan term" for loan calculation). Any selection or adjustment of the specific parameter configuration of the request parameter combination and the preset mapping relationship between the request parameter combination and the "calculation task type field" by those skilled in the art, based on the guidance of this disclosure, falls within the protection scope of this disclosure.

[0127] Specifically, the request data generation module can use rule matching or semantic analysis algorithms to check the field content of the request parameter combination, query the preset mapping rule table (such as "total house price + whether it is the first home" → "tax_calculation"), thereby determining the calculation task type field, providing an accurate basis for S7004 to select the target request body template for calculation task classification.

[0128] S7004 maps the calculation task type field to the corresponding request body template (such as "tax_calculation" → tax calculation template) by looking up the template mapping table or using a rule matching algorithm, ensuring the compatibility between the request body template and the combination of request parameters.

[0129] For example, if the combination of request parameters includes a combination of total house price and whether it is a first-time home purchase, then the calculation task type field is determined to be a tax calculation task; If the request parameter combination includes a combination of loan amount and loan term, then the calculation task type field is determined to be a loan calculation task.

[0130] Based on any of the above embodiments, this disclosure also provides a request processing apparatus.

[0131] Figure 8 This is a schematic block diagram of the structure of a request processing apparatus according to one embodiment of the present disclosure.

[0132] like Figure 8 As shown, the request processing device includes: The request receiving module 8002 receives the request information input by the user; The intent recognition module 8004 performs intent recognition on the request information, obtains intent recognition results, and determines the request type of the request information based on the intent recognition results. The request type is either a calculation request or a query request. If the request type is a computational request, the second intelligent agent 8006 extracts the structured request parameters from the request information, generates structured request data based on the structured request parameters, and determines the computational engine applicable to the request information based on the structured request data. The third intelligent agent 8008 inputs the structured request data into the computing engine used by the third intelligent agent 8008 to obtain the calculation result information corresponding to the request information.

[0133] Preferably, the request processing apparatus further includes: The fourth intelligent agent 8010, if the request type is a query request, extracts query keywords from the request information and retrieves matching information from a preset knowledge base based on the query keywords; if matching information is retrieved, it generates and outputs query result information based on the matching information; if no matching information is retrieved, it searches for external related data based on the query keywords and generates and outputs query result information based on the searched external related data.

[0134] The aforementioned request processing device can be in the form of computer software, and each module of the aforementioned request processing device can be implemented through computer software modules.

[0135] The specific implementation process of the functions and roles of each module in the above request processing device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0136] The execution subject of the request processing method in the specific embodiments of this disclosure can be an electronic device such as a mobile phone or computer.

[0137] Therefore, based on any of the above embodiments, this disclosure also provides an electronic device that can execute the request processing method of any of the embodiments described above.

[0138] Figure 9 This is a schematic block diagram of an electronic device 1000 according to one embodiment of the present disclosure.

[0139] The hardware architecture of the electronic device 1000 can be implemented using a bus architecture. The bus architecture can include any number of interconnect buses and bridges, depending on the specific application of the hardware and overall design constraints. Bus 1100 connects various circuits, including one or more processors 1200, memory 1300, and / or hardware modules. Bus 1100 can also connect various other circuits 1400, such as peripheral devices, voltage regulators, power management circuits, external antennas, etc.

[0140] Bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one connection line is used in this diagram, but this does not imply that there is only one bus or only one type of bus.

[0141] This disclosure also provides a readable storage medium storing a computer program that, when executed by a processor, is used to implement the methods described above. A "readable storage medium" can be any means capable of containing, storing, communicating, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples of a readable storage medium include: an electrical connection with one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable read-only memory (CDROM), etc.

[0142] This disclosure also provides a computer program product, the methods of which can be implemented wholly or partially through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented wholly or partially as a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed, all or part of the processes or functions of this disclosure are performed.

[0143] Computer programs or instructions can be stored in a readable storage medium or transferred from one readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The readable storage medium can be any available medium capable of access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video optical disc; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium can be a volatile or non-volatile storage medium, or it can include both volatile and non-volatile types of storage media.

[0144] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] In the description of this specification, the references to terms such as "one embodiment / mode," "some embodiments / modes," "example," "specific example," or "some examples," etc., refer to specific features, structures, or characteristics described in connection with that embodiment / mode or example, which are included in at least one embodiment / mode or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / mode or example. Moreover, the specific features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments / modes or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments / modes or examples described in this specification, as well as the features of different embodiments / modes or examples.

[0149] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0150] Those skilled in the art should understand that the above embodiments are merely for illustrating the present disclosure and are not intended to limit the scope of the disclosure. Those skilled in the art can make other changes or modifications based on the above disclosure, and these changes or modifications still fall within the scope of the present disclosure.

Claims

1. A request processing method, characterized in that, The method includes: Receive user input request information; The request information is subjected to intent recognition to obtain intent recognition results. Based on the intent recognition results, the request type of the request information is determined, and the request type is either a calculation request or a query request. If the request type is a computational request, extract the structured request parameters from the request information, generate structured request data based on the structured request parameters, and determine the applicable computational engine for the request information based on the structured request data; and The structured request data is input into the computing engine to obtain the calculation result information corresponding to the request information.

2. The request processing method according to claim 1, characterized in that, If the request type is a query request, extract query keywords from the request information, and retrieve matching information from a preset knowledge base based on the query keywords; If matching information is found, query results are generated and output based on the matching information. If no matching information is found, external related data is searched based on the query keywords, and query results are generated and output based on the searched external related data.

3. The request processing method according to claim 1, characterized in that, The request information is subjected to intent recognition to obtain intent recognition results. Based on the intent recognition results, the request type of the request information is determined, including: Extract key descriptive information from the request information; Based on preset business scenario matching rules, the key description information is matched against business scenarios to determine the target business scenario; and The request type of the request information is determined based on the target business scenario.

4. The request processing method according to claim 1, characterized in that, Generate structured request data based on the structured request parameters, including: The target request body template corresponding to the structured request parameters is determined based on the structured request parameters, and the target request body template includes a calculation task type field; The structured request parameters are used to fill or replace the corresponding parameter fields in the target request body template to generate the structured request data.

5. The request processing method according to claim 4, characterized in that, Before determining the target request body template corresponding to the structured request parameters based on the structured request parameters, generating structured request data based on the structured request parameters further includes: Determine whether the structured request parameters include a property listing code; If a property code is included, property information corresponding to the property code is retrieved from a preset property database, and the structured request parameters are supplemented based on the property information.

6. The request processing method according to claim 1 or 4, characterized in that, Determining the appropriate computing engine for the request information based on the structured request data includes: Extract the computation task type field from the structured request data; Based on preset computing engine mapping rules, the computing engine corresponding to the computing task type field is determined, and it is determined as the computing engine applicable to the request information.

7. The request processing method according to claim 4, characterized in that, Determining the target request body template corresponding to the structured request parameters based on the structured request parameters includes: The computation task type field is determined based on the mapping relationship between the combination of request parameters in the structured request parameters and the computation task type field. The target request body template corresponding to the structured request parameters is determined based on the computation task type field.

8. The request processing method according to claim 7, characterized in that, The computation task type field is determined based on the mapping relationship between the combination of request parameters in the structured request parameters and the computation task type field, including: If the request parameter combination includes a combination of total house price and whether it is a first-time home purchase, then the calculation task type field is determined to be a tax calculation task; If the request parameter combination includes a combination of loan amount and loan term, then the calculation task type field is determined to be a loan calculation task.

9. An electronic device, characterized in that, include: The memory stores execution instructions; as well as A processor that executes execution instructions stored in the memory, causing the processor to perform the request processing method according to any one of claims 1 to 8.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the request processing method according to any one of claims 1 to 8.

Images