Business opportunity full-link intelligent inquiry and collaborative decision-making method and system

Abstract

The invention provides a business opportunity full-link inquiry and collaborative decision-making method and system in the technical field of enterprise information management, and the method comprises the steps: receiving a business opportunity creation request through a server, and processing a customer demand to generate structured business opportunity data; whether intelligent inquiry is started or not is determined according to the requirement definiteness and the quotation library matching degree, if yes, an order is dynamically sent to a purchasing terminal, the quotation library is updated and the business opportunity is associated after quotation is processed, then a scheme draft is generated based on business opportunity data, a business terminal adjusts the scheme draft, a quotation scheme document is generated, and operation and states are recorded in the whole process to form a digital file; and automatically generating a visual report for evaluating the conversion efficiency, the root cause and the performance through the analysis model. The business opportunity full-link management method has the advantages that the cooperation efficiency of business opportunity full-link management, the resource matching accuracy, the customer demand response speed and the data-driven decision-making ability are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of enterprise information management technology, and in particular to a method and system for intelligent inquiry and collaborative decision-making across the entire business opportunity chain. Background Technology

[0002] In business operations, efficiently acquiring and converting business opportunities is a core operational aspect. Currently, when handling business opportunities involving multiple product categories (such as bidding, centralized procurement, and supplying major clients), companies generally adopt a multi-role collaborative model of "salesperson-business relations-procurement." Specifically, salespersons are responsible for connecting with clients and collecting procurement needs; business relations personnel are responsible for registering business opportunities, developing solutions, and initiating price inquiries; and procurement personnel are responsible for connecting with suppliers and completing product price inquiries and quotation information entry. During this process, companies also need to record and analyze data across the entire business opportunity chain, from registration to successful or unsuccessful transactions, for performance evaluation, process optimization, and decision support.

[0003] However, existing technologies mainly rely on offline communication, email, instant messaging tools, and fragmented office documents (such as Excel spreadsheets) for information transmission and collaboration, which has the following significant technical drawbacks: 1. Low information collaboration efficiency and poor process controllability: Information transmission between roles relies on manual operation. Key data such as business opportunity requirements, inquiry instructions, and quotation results cannot be synchronized in real time, which easily leads to information discrepancies, omissions of instructions, and delays in order dispatch. The entire process lacks a unified online platform for standardization and constraint, resulting in uncontrollable progress in business opportunity development and low collaboration efficiency.

[0004] 2. Insufficient intelligence in the inquiry process and inaccurate resource matching: The allocation of inquiry tasks relies entirely on the manual judgment and assignment of sales personnel, making it difficult to accurately match the most suitable procurement personnel. Furthermore, the workload of procurement personnel cannot be dynamically assessed, easily leading to uneven task allocation, response delays, and even matching errors. In addition, the quotation data obtained by procurement personnel is mostly stored in unstructured, scattered formats, lacking an effective mechanism for data accumulation and reuse. This results in the need for repeated inquiries when facing similar business opportunities, leading to a waste of human resources.

[0005] 3. Poor flexibility in solution generation, making it difficult to quickly respond to ambiguous needs: When customer needs are vague, business personnel need to manually filter and combine solutions from massive amounts of scattered product information, resulting in a large workload and long cycle. Existing technology lacks intelligent recommendation capabilities based on historical data, making it impossible to quickly generate preliminary draft solutions that fit the budget and product category for business personnel, leading to slow response to diverse customer needs.

[0006] 4. Lack of end-to-end data traceability and analysis capabilities, resulting in weak decision support: Data from various stages of the business opportunity process (such as demand registration, inquiry records, quotation versions, communication records, and transaction results) is scattered across different roles and media, failing to form a centralized, structured data chain. Enterprises struggle to accurately attribute non-sales failures (e.g., distinguishing between internal process issues and external customer factors), and cannot automatically calculate key indicators such as performance of each role and business opportunity conversion rates. This leads to a lack of data support for business decisions and unclear directions for process optimization.

[0007] 5. Low standardization of commodity data management: Due to the lack of unified commodity data standards and a central repository, the quotation formats and parameter specifications entered by different procurement personnel are inconsistent, resulting in uneven data quality. This greatly hinders the retrieval, comparison, and cross-project reuse of commodity data, which goes against the industry trend of standardized commodity data management.

[0008] In summary, existing technologies suffer from technical problems such as disconnected collaboration, low levels of intelligence, data silos, and weak decision support, failing to meet enterprises' urgent need for efficient, intelligent, and data-driven management of the entire business opportunity chain.

[0009] Therefore, how to provide a method and system for intelligent inquiry and collaborative decision-making across the entire business opportunity chain, so as to improve the collaborative efficiency, resource matching accuracy, customer demand response speed, and data-driven decision-making capabilities of the entire business opportunity chain management, has become an urgent technical problem to be solved. Summary of the Invention

[0010] The technical problem to be solved by this invention is to provide a method and system for intelligent inquiry and collaborative decision-making across the entire business opportunity chain, thereby improving the collaborative efficiency, resource matching accuracy, customer demand response speed, and data-driven decision-making capabilities of the entire business opportunity chain management.

[0011] In a first aspect, the present invention provides a method for intelligent price inquiry and collaborative decision-making across the entire business opportunity chain, comprising the following steps: Step S1: The server receives a business opportunity creation request initiated by a business terminal. The business opportunity creation request carries customer demand information collected and uploaded by the salesperson's terminal. The server decrypts and verifies the business opportunity creation request to obtain the customer demand information, parses the customer demand information to extract key elements and generate a structured business opportunity data object, and assigns a globally unique business opportunity number for storage. Step S2: The server determines whether to start the intelligent inquiry task based on the demand clarity score in the business opportunity data object and the matching score of matching the demand clarity score with the standardized product quotation database. Step S3: If the server determines that the intelligent inquiry task does not need to be started, proceed to step S4; if it determines that the intelligent inquiry task needs to be started, obtain the core parameter set of the inquiry set by the business terminal, call the intelligent order dispatch engine, dynamically allocate the inquiry task to the optimal purchasing terminal, and push the task notification of the inquiry task to the purchasing terminal; the server receives the original quotation data of the supplier submitted by the purchasing terminal, preprocesses the original quotation data of the supplier to generate quotation data records, and synchronously updates them to the standardized commodity quotation database, and establishes an association index between the quotation data records and the business opportunity number; Step S4: The server obtains product data based on the business opportunity data object and the standardized product price library to generate at least one draft solution. Step S5: The server creates and manages a set of solutions for the same business opportunity, and adds the solution draft as an initial solution instance to the solution set; the business terminal performs independent visual combination and pricing adjustment for each solution instance in the solution set; the server responds to the instructions of the business terminal and generates a standardized quotation solution document from one or more selected solution instances. Step S6: The server continuously records operation events, status change information, and data flow information of various business terminals, salesperson terminals, and purchasing terminals related to the business opportunity, forming a complete digital archive of the entire business opportunity chain; the decision analysis model is run to analyze the digital archive of the entire business opportunity chain, and automatically generates a visual analysis report for evaluating the conversion efficiency of the business opportunity, the root causes of non-sales, and the performance of related roles.

[0012] Furthermore, in step S1, the business opportunity data object carries at least the business opportunity number, business opportunity type, requirement content, requirement clarity score, customer information, and budget; the requirement content includes a requirement summary and a requirement list; The calculation process for the demand clarity score is as follows: The required content is input into a pre-trained requirement classification model to obtain an initial clarity probability value; the structuring degree and completeness of the required content are scored based on a preset rule set to obtain an auxiliary score value; the initial clarity probability value and the auxiliary score value are weighted and fused to obtain the final clarity score.

[0013] Furthermore, in step S2, determining whether to initiate the intelligent price inquiry task specifically involves: If the requirement clarity score is higher than a preset first threshold and the matching score is higher than a preset second threshold, then it is determined that the intelligent inquiry task will not be started. If the requirement clarity score is lower than the first threshold, or the matching score is lower than the second threshold, then the intelligent inquiry task is initiated.

[0014] Furthermore, in step S3, the step of calling the intelligent order dispatch engine to dynamically allocate the inquiry task to the optimal procurement terminal specifically involves: Calculate the semantic similarity between the core parameter set of the inquiry and the pre-configured domain of expertise tag set of each procurement terminal to obtain the parameter matching score; Obtain the number of incomplete inquiry tasks and the historical average task processing time for each procurement terminal, and calculate the current load factor for each procurement terminal. Based on the predefined weights, the parameter matching score and load coefficient are combined to calculate the overall priority value of each purchasing terminal for the current inquiry task, and the purchasing terminal with the highest overall priority value is selected as the target terminal. Based on the target terminal and the comprehensive priority value, the dispatch result is generated and pushed to the business terminal for confirmation. Based on the confirmation signal from the business terminal, the task details of the inquiry task are packaged into a task notification and pushed to the target terminal.

[0015] Furthermore, in step S3, the preprocessing of the supplier's original quotation data to generate quotation data records specifically involves: After performing a pre-defined mandatory field integrity check on the supplier's original quotation data, the supplier's original quotation data from different data sources and with different formats are mapped to a predefined unified data model to perform format standard conversion. Then, natural language processing is performed on the product names and specifications in the supplier's original quotation data to convert them into standard terms for semantic normalization. This completes the preprocessing of the supplier's original quotation data and generates quotation data records that conform to predetermined standards. Generate a globally unique version number for the quoted data record, and associate the version number with the corresponding business opportunity number, procurement terminal identifier, and supplier information; Each quotation record stored in the standardized commodity quotation database is associated with a lifecycle status identifier.

[0016] Furthermore, in step S4, when it is determined that the intelligent inquiry task will not be initiated, the process of generating the draft solution is as follows: Based on the demand summary in the business opportunity data object, the server uses natural language processing technology to parse the demand intent and, in conjunction with budget constraints, intelligently retrieves and recommends product data from the standardized product price database to generate a preset number of draft solutions.

[0017] Furthermore, in step S4, when it is determined that the intelligent inquiry task is to be initiated, the process of generating the draft solution is as follows: The server parses the demand list in the business opportunity data object, performs multi-attribute matching between the demand list and the product entries in the standardized product quotation library, and filters out a set of candidate products with a matching degree higher than a preset matching degree threshold. Based on the current business opportunity type, budget, and key product categories, similar solution templates are retrieved from the historical successful solution database using vectorization technology to obtain product data from the similar solution templates. Based on the product data in the candidate product set and similar solution templates, the server automatically generates or combines at least one solution draft and displays it visually on the interface of the business terminal.

[0018] Furthermore, in step S6, the operational decision analysis model is specifically used for: Opportunity conversion funnel analysis: Count the number of opportunities at each status transition node, calculate the conversion rate and drop-off points to evaluate the effectiveness of opportunity conversion; the status transition nodes include at least registered, processing, solution generated, completed, and uncompleted. Root cause analysis of non-sales failures: Based on natural language processing technology, the text of reasons for non-sales failures recorded in the business terminal is analyzed, and combined with key events in the operation log, the reasons for non-sales failures are automatically classified into internal or external factors through a classification model to assess the root causes of non-sales failures. Multi-dimensional performance calculation: Through a multi-dimensional evaluation sub-model, the related roles of salesperson terminals, business terminals, and procurement terminals are evaluated, including at least the amount of business opportunities contributed, solution quality, inquiry response speed, and quotation accuracy, in order to assess the performance of related roles.

[0019] Furthermore, it also includes: Step S7: The server starts a monitoring process for each business opportunity instance in the intelligent inquiry task. The monitoring process dynamically calculates the expected completion time of each stage of the inquiry task based on the expected timeliness of the core parameters set of the inquiry. The actual progress of the task is compared with the expected completion time in real time. When the deviation exceeds the allowable range, a graded warning message is automatically sent to the corresponding procurement terminal, and the warning event is recorded in the business opportunity full-link digital archive. Step S8: The server periodically scans the standardized commodity quotation database. For quotation data records that have exceeded their validity period, the server automatically marks their lifecycle status as invalid and reduces their priority or excludes them in subsequent solution recommendations and quotation matching.

[0020] Secondly, this invention provides a business opportunity end-to-end intelligent inquiry and collaborative decision-making system, comprising the following modules: The opportunity creation request receiving module is used by the server to receive opportunity creation requests initiated by business terminals. The opportunity creation request carries customer demand information collected and uploaded by the salesperson's terminal. The server decrypts and verifies the opportunity creation request to obtain the customer demand information, parses the customer demand information to extract key elements and generate a structured opportunity data object, and assigns a globally unique opportunity number for storage. The intelligent inquiry task start judgment module is used by the server to determine whether to start the intelligent inquiry task based on the demand clarity score in the business opportunity data object and the matching score of matching the demand clarity score with the standardized product quotation library. The inquiry module is used to: if the server determines that the intelligent inquiry task does not need to be initiated, proceed to the solution draft generation module; if it determines that the intelligent inquiry task needs to be initiated, obtain the core parameter set of the inquiry set by the business terminal, call the intelligent order dispatch engine, dynamically allocate the inquiry task to the optimal purchasing terminal, and push the task notification of the inquiry task to that purchasing terminal; the server receives the original quotation data of the supplier submitted by the purchasing terminal, preprocesses the original quotation data of the supplier to generate quotation data records, and synchronously updates them to the standardized commodity quotation database, establishing an association index between the quotation data records and the business opportunity number; The scheme draft generation module is used by the server to obtain product data based on the business opportunity data object and the standardized product quotation library to generate at least one scheme draft; The quotation document generation module is used by the server to create and manage a set of solutions for the same business opportunity, and to add the draft solutions as initial solution instances to the solution set; the business terminal performs independent visual combination and pricing adjustment for each solution instance in the solution set; the server responds to the instructions of the business terminal and generates a standardized quotation document from one or more selected solution instances. The visualization analysis report generation module is used by the server to continuously record operation events, status change information, and data flow information of various business terminals, salesperson terminals, and purchasing terminals related to business opportunities, forming a complete digital archive of the entire business opportunity chain. The decision analysis model is run to analyze the digital archive of the entire business opportunity chain and automatically generate a visualization analysis report for evaluating the conversion efficiency of business opportunities, the root causes of non-sales, and the performance of related roles.

[0021] Furthermore, in the business opportunity creation request receiving module, the business opportunity data object carries at least the business opportunity number, business opportunity type, requirement content, requirement clarity score, customer information, and budget; the requirement content includes a requirement summary and a requirement list; The calculation process for the demand clarity score is as follows: The required content is input into a pre-trained requirement classification model to obtain an initial clarity probability value; the structuring degree and completeness of the required content are scored based on a preset rule set to obtain an auxiliary score value; the initial clarity probability value and the auxiliary score value are weighted and fused to obtain the final clarity score.

[0022] Furthermore, in the intelligent inquiry task initiation judgment module, the judgment of whether to initiate the intelligent inquiry task specifically involves: If the requirement clarity score is higher than a preset first threshold and the matching score is higher than a preset second threshold, then it is determined that the intelligent inquiry task will not be started. If the requirement clarity score is lower than the first threshold, or the matching score is lower than the second threshold, then the intelligent inquiry task is initiated.

[0023] Furthermore, in the inquiry module, the step of calling the intelligent dispatch engine to dynamically allocate inquiry tasks to the optimal procurement terminal specifically involves: Calculate the semantic similarity between the core parameter set of the inquiry and the pre-configured domain of expertise tag set of each procurement terminal to obtain the parameter matching score; Obtain the number of incomplete inquiry tasks and the historical average task processing time for each procurement terminal, and calculate the current load factor for each procurement terminal. Based on the predefined weights, the parameter matching score and load coefficient are combined to calculate the overall priority value of each purchasing terminal for the current inquiry task, and the purchasing terminal with the highest overall priority value is selected as the target terminal. Based on the target terminal and the comprehensive priority value, the dispatch result is generated and pushed to the business terminal for confirmation. Based on the confirmation signal from the business terminal, the task details of the inquiry task are packaged into a task notification and pushed to the target terminal.

[0024] Furthermore, in the inquiry module, the preprocessing of the supplier's original quotation data to generate quotation data records specifically involves: After performing a pre-defined mandatory field integrity check on the supplier's original quotation data, the supplier's original quotation data from different data sources and with different formats are mapped to a predefined unified data model to perform format standard conversion. Then, natural language processing is performed on the product names and specifications in the supplier's original quotation data to convert them into standard terms for semantic normalization. This completes the preprocessing of the supplier's original quotation data and generates quotation data records that conform to predetermined standards. Generate a globally unique version number for the quoted data record, and associate the version number with the corresponding business opportunity number, procurement terminal identifier, and supplier information; Each quotation record stored in the standardized commodity quotation database is associated with a lifecycle status identifier.

[0025] Furthermore, in the scheme draft generation module, when it is determined that the intelligent inquiry task will not be initiated, the specific process of generating the scheme draft is as follows: Based on the demand summary in the business opportunity data object, the server uses natural language processing technology to parse the demand intent and, in conjunction with budget constraints, intelligently retrieves and recommends product data from the standardized product price database to generate a preset number of draft solutions.

[0026] Furthermore, in the scheme draft generation module, when it is determined that the intelligent inquiry task will be initiated, the specific process of generating the scheme draft is as follows: The server parses the demand list in the business opportunity data object, performs multi-attribute matching between the demand list and the product entries in the standardized product quotation library, and filters out a set of candidate products with a matching degree higher than a preset matching degree threshold. Based on the current business opportunity type, budget, and key product categories, similar solution templates are retrieved from the historical successful solution database using vectorization technology to obtain product data from the similar solution templates. Based on the product data in the candidate product set and similar solution templates, the server automatically generates or combines at least one solution draft and displays it visually on the interface of the business terminal.

[0027] Furthermore, in the visualization analysis report generation module, the running decision analysis model is specifically used for: Opportunity conversion funnel analysis: Count the number of opportunities at each status transition node, calculate the conversion rate and drop-off points to evaluate the effectiveness of opportunity conversion; the status transition nodes include at least registered, processing, solution generated, completed, and uncompleted. Root cause analysis of non-sales failures: Based on natural language processing technology, the text of reasons for non-sales failures recorded in the business terminal is analyzed, and combined with key events in the operation log, the reasons for non-sales failures are automatically classified into internal or external factors through a classification model to assess the root causes of non-sales failures. Multi-dimensional performance calculation: Through a multi-dimensional evaluation sub-model, the related roles of salesperson terminals, business terminals, and procurement terminals are evaluated, including at least the amount of business opportunities contributed, solution quality, inquiry response speed, and quotation accuracy, in order to assess the performance of related roles.

[0028] Furthermore, it also includes: The intelligent monitoring module for inquiry progress is used by the server to start a monitoring process for each business opportunity instance in the intelligent inquiry task. The monitoring process dynamically calculates the expected completion time of each stage of the inquiry task based on the expected timeliness of the core parameters set of the inquiry. The actual progress of the task is compared with the expected completion time in real time. When the deviation exceeds the allowable range, a graded warning message is automatically sent to the corresponding procurement terminal, and the warning event is recorded in the business opportunity full-link digital archive. The dynamic maintenance module for the quotation database is used by the server to periodically scan the standardized commodity quotation database. For quotation data records that have exceeded their validity period, the system automatically marks their lifecycle status as invalid and reduces their priority or excludes them in subsequent solution recommendations and quotation matching.

[0029] The advantages of this invention are: 1. By digitizing and data-driven the entire business opportunity process, a collaborative decision-making system with a server as the intelligent hub was built. An intelligent order dispatch engine was used to achieve precise and dynamic allocation of inquiry tasks, improving resource matching accuracy. By automatically generating draft solutions based on a standardized product library, the speed of responding to customer needs was significantly accelerated. Throughout the process, the operations and data flow of all roles on the unified platform were synchronized and fully recorded in real time, forming a complete digital archive of the entire business opportunity chain. This completely eliminated information silos, greatly improved cross-role collaboration efficiency, and provided a data foundation for running decision analysis models, thereby automatically generating in-depth insight reports. Ultimately, this greatly improved the collaborative efficiency, resource matching accuracy, customer demand response speed, and data-driven decision-making capabilities of the entire business opportunity chain management.

[0030] 2. By using a unified platform centered on servers, all aspects of the business opportunity chain are brought online, standardized, and automated, thereby systematically improving management efficiency. Specifically, the intelligent order dispatch engine dynamically matches the optimal procurement personnel, improving the accuracy of resource matching; the automatic draft generation function based on a standardized product library and historical solutions significantly accelerates the response speed to customer needs; online processes and real-time data synchronization fundamentally improve the collaborative efficiency of cross-role collaboration; and by building a full-chain digital archive and running a decision analysis model, scattered data is transformed into quantifiable conversion funnels, root cause analysis, and performance reports, ultimately strengthening data-driven decision-making capabilities and forming a complete closed loop from execution to optimization feedback.

[0031] 3. By centrally processing the entire process from opportunity creation and quotation task allocation to solution generation and decision analysis through the server, the business terminal, salesperson terminal, and procurement terminal are tightly connected to form an end-to-end digital workflow. This integration eliminates information silos and manual transmission links common in traditional opportunity management, ensuring that data is synchronized and stored consistently in real time at each stage. For example, all operations are associated with a globally unique opportunity number, making opportunity status, quotation data, and user operations traceable throughout the process. This not only reduces human error and communication costs but also provides enterprises with a complete business view, enhances cross-departmental collaboration efficiency, and aligns with the trend of digital transformation in modern enterprises.

[0032] 4. By combining demand clarity and matching scores, the system intelligently determines whether to initiate a price inquiry task, avoiding unnecessary inquiry processes and optimizing resource utilization. When a price inquiry is needed, the intelligent dispatch engine dynamically calculates the parameter matching degree and load coefficient of the procurement terminal and automatically assigns the task to the optimal personnel. This data- and algorithm-based automated decision-making replaces traditional manual dispatching, significantly shortening task allocation time and improving processing efficiency and accuracy. At the same time, this reduces the waste of human resources, ensures that high-value business opportunities are prioritized, and enhances the company's market competitiveness and customer satisfaction.

[0033] 5. By defining a detailed preprocessing procedure for supplier raw quotation data, including format standardization, semantic normalization, and integrity verification, heterogeneous data is transformed into quotation data records with a unified structure and associated with lifecycle status identifiers. This process not only improves the accuracy and consistency of quotation data but also makes the standardized commodity quotation library a reliable resource pool, providing a high-quality data foundation for subsequent solution generation. Through intelligent retrieval and matching, the server can quickly generate solution drafts, reducing manual search and organization time, improving the efficiency of solution development, and accumulating structured data for long-term data analysis and model training, with the potential for continuous improvement.

[0034] 6. By allowing business terminals to independently and visually combine and adjust pricing for a set of solutions, and generating standardized quotation documents from selected solutions, this design combines the advantages of automated generation and human intervention: the server automatically generates initial solution drafts based on rules and algorithms, while users can make personalized modifications through an intuitive interface, achieving rapid customization; this not only accelerates the design process of quotation solutions, but also improves the applicability and customer matching of solutions, while maintaining a standardized document format, facilitating internal approval and external delivery; this collaborative tool enhances user engagement, reduces training costs, and improves overall business agility.

[0035] 7. By continuously recording all operational events, status changes, and data flow, a digital archive of the entire business opportunity chain is formed, and a decision analysis model is run to generate a visual analysis report, realizing comprehensive monitoring and in-depth analysis of the business process. For example, efficiency can be evaluated through the business opportunity conversion funnel, root cause analysis of non-converted transactions can be carried out, and multi-dimensional performance calculation can be performed. This provides enterprise managers with real-time and accurate business insights, helping to identify bottlenecks, optimize processes, and improve team performance.

[0036] 8. By calculating dynamic time points based on expected timeliness and detecting deviations, early warning messages are automatically sent to the procurement terminal, enabling real-time tracking and proactive management of inquiry tasks. This ensures timely progress of tasks and avoids lost business opportunities due to delays. At the same time, early warning events are recorded in digital archives, providing a basis for subsequent analysis. This monitoring mechanism improves the transparency and controllability of projects, reduces the burden of manual supervision, helps companies respond to risks in a timely manner, and enhances customer trust and contract performance capabilities.

[0037] 9. By regularly scanning the standardized commodity price database, expired prices are automatically marked as invalid and their priorities are adjusted, ensuring the real-time nature and accuracy of price data. This avoids decision-making errors caused by using outdated information, such as incorrect pricing or solution recommendations. Automated management reduces manual maintenance costs, improves the availability of the price database, and supports more refined data governance by associating lifecycle status identifiers.

[0038] 10. By calculating the clarification score of requirements and combining it with a pre-trained requirements classification model and rule set for weighted fusion, the accuracy of understanding customer needs is improved. During solution generation, the server intelligently recommends product data and solution templates based on natural language processing, multi-attribute matching, and vectorized retrieval technologies. The application of these intelligent components enables the system to more accurately parse fuzzy requirements and match the best resources, thereby generating solution drafts that better meet customer expectations, improving business opportunity conversion rates and customer satisfaction, and demonstrating the innovative integration of artificial intelligence technology into traditional business processes. Attached Figure Description

[0039] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0040] Figure 1 This is a flowchart of a business opportunity intelligent inquiry and collaborative decision-making method for the entire business opportunity chain according to the present invention.

[0041] Figure 2 This is a schematic diagram of the structure of a business opportunity end-to-end intelligent inquiry and collaborative decision-making system according to the present invention. Detailed Implementation

[0042] The overall concept of the technical solution in this application embodiment is as follows: Using a server as the intelligent hub, it integrates business terminals, salesperson terminals, and procurement terminals, achieving full-link management of business opportunities through data-driven and collaborative automation. Starting from receiving a business opportunity creation request and parsing customer needs to generate structured data, it intelligently determines whether to initiate a price inquiry task based on the clarity and matching scores of the requirements. If initiated, it uses an intelligent dispatch engine to dynamically allocate tasks to the optimal procurement terminal, processes the quotations, updates the standardized product price database, generates a draft solution, and outputs a price document through visual adjustments on the business terminal. Simultaneously, the entire process is recorded to form a digital archive. Finally, a decision analysis model is run to generate a visual report, thereby improving collaborative efficiency, resource matching accuracy, and decision-making capabilities.

[0043] To ensure the stable operation of the system of this invention, the following hardware and software environment can be configured in specific implementations: Hardware environment: The server adopts industrial-grade standards, with a configuration of no less than 16 CPU cores, 64GB of memory, and 1TB of hard disk capacity to ensure high-concurrency data processing capabilities; the terminal is a regular office PC, with a configuration of no less than 4 CPU cores and 8GB of memory, supporting multiple terminals (such as salesperson terminals, business terminals, and purchasing terminals) to operate online simultaneously, avoiding performance bottlenecks.

[0044] Software environment: The preferred operating system for the server is Linux Debian 12 or later, and the terminal supports Windows 10 or later; the database uses MySQL 8.0 for structured data storage (such as business opportunity information database and standardized product price database), and is equipped with Redis to cache frequently accessed data and task queues to improve response speed; the front-end interactive interface is built on the Vue 3.0 framework to ensure smooth user operation and cross-platform compatibility.

[0045] This environment is designed to balance scalability and security, and can be adapted to the business opportunity management needs of businesses from small to large.

[0046] When deploying the system for the first time, the following initial configurations need to be completed to lay the foundation for subsequent intelligent processes: 1. Role and Permission Configuration: Administrators can enter information about salespersons (customer needs coordination and solution delivery), business personnel (business opportunity registration, solution setup, inquiry initiation), and procurement personnel (supplier coordination, quotation entry, result feedback) through the interactive interface, and assign exclusive role permissions (for example, business personnel can only initiate inquiries, and procurement personnel can only enter quotations) to ensure business process compliance and data security.

[0047] 2. Order dispatch rule configuration: Preset intelligent order dispatch algorithm parameters in the intelligent core layer, including category-purchasing personnel matching relationship matrix, workload threshold (such as the upper limit of the number of uncompleted tasks), response cycle threshold (such as the maximum processing time for inquiry tasks), and reserve a manual adjustment interface to adapt to the dynamic needs of enterprises.

[0048] 3. Initialization of the quotation database: Import the company's existing product quotation data through the data access layer, clean and organize it according to standardized formats (such as product name, specifications, quotation amount, supplier information, validity period) to build an initial standardized product quotation database, providing a data foundation for subsequent intelligent retrieval and reuse.

[0049] 4. Template Configuration: Export table templates and data statistics report templates from preset schemes in the interaction layer, supporting custom fields (such as business opportunity type, budget range) and formats (such as PDF or Excel) to improve user operation convenience.

[0050] Please refer to Figures 1 to 2 As shown, a preferred embodiment of the intelligent inquiry and collaborative decision-making method for the entire business opportunity chain of the present invention includes the following steps: Step S1: The server receives a business opportunity creation request initiated by a business terminal. The business opportunity creation request carries customer demand information collected and uploaded by the salesperson's terminal. The server decrypts and verifies the business opportunity creation request to obtain the customer demand information, parses the customer demand information to extract key elements and generate a structured business opportunity data object, and assigns a globally unique business opportunity number for storage. The business opportunity creation request carries encrypted information, a timestamp, and a hash value. The encrypted information is obtained by encrypting customer demand information using the SM4 algorithm, and the hash value is obtained by hashing the encrypted information and the timestamp. When the server receives the business opportunity creation request, it parses the encrypted information, timestamp, and hash value. First, it performs integrity verification using the hash value, then performs timeliness verification using the timestamp, and finally decrypts the encrypted information into customer demand information using the SM4 algorithm. By adopting triple security measures, the security of customer demand information transmission is effectively improved. Step S2: The server determines whether to initiate an intelligent inquiry task based on the demand clarity score in the business opportunity data object and the matching score obtained by matching the demand clarity score with the standardized commodity quotation database. The standardized commodity quotation database centrally stores the enterprise's existing commodity quotations and new procurement quotations, and records data such as commodity information, quotation amount, supplier, and validity period in a unified format, supporting multi-condition retrieval and real-time updates. Step S3: If the server determines that the intelligent inquiry task does not need to be started, proceed to step S4; if it determines that the intelligent inquiry task needs to be started, obtain the core parameter set of the inquiry set by the business terminal, call the intelligent order dispatch engine, dynamically allocate the inquiry task to the optimal purchasing terminal, and push the task notification of the inquiry task to the purchasing terminal; the server receives the original quotation data of the supplier submitted by the purchasing terminal, preprocesses the original quotation data of the supplier to generate quotation data records, and synchronously updates them to the standardized commodity quotation database, and establishes an association index between the quotation data records and the business opportunity number; Step S4: The server obtains product data based on the business opportunity data object and the standardized product price library to generate at least one draft solution. Step S5: The server creates and manages a set of solutions for the same business opportunity, and adds the solution draft as an initial solution instance to the solution set; the business terminal performs independent visual combination and pricing adjustment for each solution instance in the solution set; the server responds to the instructions of the business terminal and generates a standardized quotation solution document from one or more selected solution instances. The solution collection management and visual adjustment mechanism cleverly balances automation and human intervention. Server-generated solution drafts serve as a high-quality starting point, while business personnel can flexibly perform 'visual combination and pricing adjustments' through an intuitive interface. This collaborative model of 'machine intelligence initial screening, human intelligence refinement' ensures both the efficiency of solution generation and the preservation of business personnel's professional judgment in handling complex business scenarios, ultimately generating standardized quotation documents. This design not only enhances the customization level of individual solutions, but the generated standardized documents also facilitate subsequent data analysis, forming a closed business loop.

[0051] Step S6: The server continuously records operation events, status change information, and data flow information of various business terminals, salesperson terminals, and purchasing terminals related to the business opportunity, forming a complete digital archive of the entire business opportunity chain; the decision analysis model is run to analyze the digital archive of the entire business opportunity chain, and automatically generates a visual analysis report for evaluating the conversion efficiency of the business opportunity, the root causes of non-sales, and the performance of related roles.

[0052] The entire business opportunity chain covers the complete business process from business opportunity demand registration, solution design / inquiry initiation, intelligent order dispatch, supplier quotation, solution combination export, transaction / non-transaction records, and data statistical analysis.

[0053] In step S1, the business opportunity data object carries at least the business opportunity number, business opportunity type (classified by business attributes into bidding, supply, online platform ordering, and offline price comparison inquiry, used to distinguish business opportunity processing priority and process adaptation rules), demand content, demand clarity score, customer information, project description, and budget; the demand content includes a demand summary and a demand list; the core fields of the price inquiry in the demand summary include brand, category, product name, supply requirements, timeliness requirements, image gallery, and online platform reference link; The calculation process for the demand clarity score is as follows: The required content is input into a pre-trained requirement classification model to obtain an initial clarity probability value; the structuring degree and completeness of the required content are scored based on a preset rule set to obtain an auxiliary score value; the initial clarity probability value and the auxiliary score value are weighted and fused to obtain the final clarity score.

[0054] The salesperson terminal supports two methods: manual input by salespersons and document upload (Excel / Word). It can import customer demand information, budget range, product list and other data, and automatically complete format verification and deduplication.

[0055] The procurement terminal supports procurement personnel in entering and maintaining data such as basic supplier information, cooperation qualifications, main product categories, and quotation cycle, providing support for price matching.

[0056] The server connects to mainstream e-commerce and procurement platforms, and can automatically capture parameters and pricing information corresponding to product reference links to assist in the input of inquiry requirements and the construction of solutions.

[0057] The server's data storage layer stores: Business opportunity database: Stores full-chain data such as business opportunity registration information, progress, and transaction / non-transaction results; Standardized Commodity Price Database: Stores basic commodity information, price data, and supplier information, and supports multi-dimensional retrieval; Supplier database: Stores data such as supplier qualifications, cooperation records, and quotation history; Full-process operation log library: Retains the operation traces of each role (entry, modification, export, etc.), including the operator, operation time, and operation content, to ensure data traceability; Decision Analysis Dataset: This dataset aggregates business opportunity statistics, performance data, and root cause analysis data to support the generation of decision dashboards and reports.

[0058] This invention transforms previously unstructured, manually interpreted customer demand information into structured business opportunity data objects that are machine-recognizable and computable. This transformation forms the data foundation of the invention. It not only provides a unified input format for subsequent intelligent decision-making, but more importantly, by introducing a quantitative indicator—demand clarity score—it transforms the ambiguity of demand, which traditionally relied on the subjective experience of business personnel, into an objective and measurable technical parameter. This provides a data-driven basis for the crucial decision of whether to initiate a price inquiry, thereby achieving intelligentization at the source of the process.

[0059] In step S2, determining whether to initiate the intelligent price inquiry task specifically involves: If the requirement clarity score is higher than a preset first threshold and the matching score is higher than a preset second threshold, then it is determined that the intelligent inquiry task will not be started. If the requirement clarity score is lower than the first threshold, or the matching score is lower than the second threshold, then the intelligent inquiry task is initiated.

[0060] The dual threshold judgment mechanism (demand clarity score & matching score) is one of the core innovations of this invention. It simulates the decision-making logic of experienced business professionals, but achieves automation and precision through algorithms. When the demand is clear and a highly matching product exists in the historical quotation database, the system intelligently 'skips' unnecessary inquiry steps and directly enters the solution generation stage, greatly shortening the response cycle and avoiding the ineffective consumption of human resources. Conversely, it precisely triggers the inquiry process when the demand is unclear. This dynamic and adaptive decision-making logic effectively solves the problems of 'insufficient intelligence in the inquiry process' and 'slow response speed' in the background technology, realizing on-demand allocation and optimization of resource input.

[0061] In step S3, the step of calling the intelligent order dispatch engine to dynamically allocate the inquiry task to the optimal procurement terminal specifically involves: Calculate the semantic similarity between the core parameter set of the inquiry and the pre-configured domain of expertise tag set of each procurement terminal to obtain the parameter matching score; Obtain the number of incomplete inquiry tasks and the historical average task processing time for each procurement terminal, and calculate the current load factor for each procurement terminal. Based on the predefined weights, the parameter matching score and load coefficient are combined to calculate the overall priority value of each purchasing terminal for the current inquiry task, and the purchasing terminal with the highest overall priority value is selected as the target terminal. Based on the target terminal and the comprehensive priority value, the dispatch result is generated and pushed to the business terminal for confirmation. Based on the confirmation signal from the business terminal, the task details of the inquiry task are packaged into a task notification and pushed to the target terminal.

[0062] The intelligent task dispatch engine is not simply a task rotation or random allocation, but a multi-factor optimization model that comprehensively considers professional competence matching (semantic similarity) and real-time workload (current load coefficient). Through predefined weights and comprehensive priority calculations, it ensures that each inquiry task is dynamically assigned to the 'most suitable' rather than the 'first available' purchasing personnel (purchasing terminals). This allocation strategy significantly improves the initial processing success rate and response efficiency of inquiry tasks, fundamentally solving the problems of 'matching errors' and 'uneven task allocation' caused by traditional manual task dispatch, and transforming human resources into intelligently schedulable 'computing power' resources.

[0063] In step S3, the preprocessing of the supplier's original quotation data to generate quotation data records specifically involves: After performing a pre-defined mandatory field integrity check on the supplier's original quotation data, the supplier's original quotation data from different data sources and with different formats are mapped to a predefined unified data model to perform format standard conversion. Then, natural language processing is performed on the product names and specifications in the supplier's original quotation data to convert them into standard terms for semantic normalization. This completes the preprocessing of the supplier's original quotation data and generates quotation data records that conform to predetermined standards. Generate a globally unique version number for the quoted data record, and associate the version number with the corresponding business opportunity number, procurement terminal identifier, and supplier information; Each quotation record stored in the standardized commodity quotation database is associated with a lifecycle status identifier.

[0064] Standardized preprocessing of supplier raw quotation data is a key step in building high-quality data assets in this solution. Through format standardization and semantic normalization, the system "cleans" the raw data, which comes from diverse sources and has widely varying formats, into standardized data records with a unified format and clear semantics. This process not only provides reliable data for the generation of immediate solutions, but more importantly, each quotation data record is associated with business opportunity number, supplier, and other information, and given a lifecycle status identifier. This allows historical quotation data to be accumulated and reused, completely changing the predicament of quotation data becoming an information silo after "one-time use" in the traditional model. This lays a solid foundation for building a "standardized commodity quotation database," a core enterprise knowledge base, and directly addresses the pain point of "low standardization of commodity data management."

[0065] In step S4, when it is determined that the intelligent price inquiry task will not be initiated, the process of generating the draft solution is as follows: Based on the demand summary in the business opportunity data object, the server uses natural language processing technology to parse the demand intent and, in conjunction with budget constraints, intelligently retrieves and recommends product data from the standardized product price database to generate a preset number of draft solutions.

[0066] In step S4, when it is determined that the intelligent inquiry task will be initiated, the process of generating the draft solution is as follows: The server parses the demand list in the business opportunity data object, performs multi-attribute matching between the demand list and the product entries in the standardized product quotation library, and filters out a set of candidate products with a matching degree higher than a preset matching degree threshold. Based on the current business opportunity type, budget, and key product categories, similar solution templates are retrieved from the historical successful solution database using vectorization technology to obtain product data from the similar solution templates. Based on the product data in the candidate product set and similar solution templates, the server automatically generates or combines at least one solution draft and displays it visually on the interface of the business terminal.

[0067] The draft solution generation mechanism triggers two differentiated intelligent generation paths based on different judgment results. For business opportunities with high clarity and high matching degree, the system acts as an 'intelligent assistant,' using NLP technology to analyze intent and quickly combine solutions, achieving a response time within seconds. For business opportunities requiring price inquiries, it combines multi-attribute matching and vectorized retrieval of historical solution templates to generate more valuable draft solutions. This scenario-based, intelligent solution generation capability frees business personnel from the manual screening of massive amounts of product information, allowing them to focus on optimizing the value of solutions and communicating with customers. Essentially, it partially automates and automates the experience-based solution creation work, significantly improving 'solution generation flexibility' and 'response speed.'

[0068] In step S6, the operational decision analysis model is specifically used for: Opportunity conversion funnel analysis: Count the number of opportunities at each status transition node, calculate the conversion rate and drop-off points to evaluate the effectiveness of opportunity conversion; the status transition nodes include at least registered, processing, solution generated, completed, and uncompleted. Unsuccessful sales root cause analysis: Based on natural language processing technology, the analysis of text recording the reasons for unsuccessful sales in business terminals, combined with key events in the operation log, automatically classifies the reasons for unsuccessful sales into internal factors (solution defects, inquiry delays, excessively high prices) or external factors (changes in customer needs, competition from competitors) through a classification model to assess the root causes of unsuccessful sales. Multi-dimensional performance calculation: Through a multi-dimensional evaluation sub-model, the related roles of salesperson terminals, business terminals, and procurement terminals are evaluated, including at least the amount of business opportunities contributed, solution quality, inquiry response speed, and quotation accuracy, in order to assess the performance of related roles.

[0069] The business opportunity full-link digital archive and decision analysis model represents the advancement of this invention from 'process automation' to 'intelligent decision-making'. It is not simply an operation log record, but rather an organic linking of discrete operations, states, and data throughout the entire link, forming a traceable and analyzable data chain. Based on this, the decision analysis model performs business opportunity conversion funnel analysis, root cause analysis of non-sales (automatic attribution through NLP technology), and multi-dimensional performance calculation, transforming tacit knowledge previously buried in the minds of various personnel or scattered in various places into quantifiable and reusable explicit strategic assets for the enterprise. This directly solves the fundamental problem of 'lack of full-link data traceability and analysis capabilities, resulting in weak decision support,' providing enterprise managers with unprecedented data-driven decision insights.

[0070] Also includes: Step S7: The server starts a monitoring process for each business opportunity instance in the intelligent inquiry task. The monitoring process dynamically calculates the expected completion time of each stage of the inquiry task based on the expected timeliness of the core parameters set of the inquiry. The actual progress of the task is compared with the expected completion time in real time. When the deviation exceeds the allowable range, a graded warning message is automatically sent to the corresponding procurement terminal, and the warning event is recorded in the business opportunity full-link digital archive. Step S8: The server periodically scans the standardized commodity quotation database. For quotation data records that have exceeded their validity period, the server automatically marks their lifecycle status as invalid and reduces their priority or excludes them in subsequent solution recommendations and quotation matching.

[0071] The introduced proactive monitoring and early warning mechanisms based on expected timeliness, along with automated lifecycle management of quotation data, together constitute the system's 'intelligent operation and maintenance' layer. These ensure the smooth operation of business processes and the 'freshness' of data assets. The monitoring process shifts from 'post-event remediation' to 'in-process intervention,' effectively reducing the risk of lost business opportunities due to delays. Automated marking of invalid quotations ensures the accuracy and reliability of the system's recommendations. These automated operation and maintenance features further reduce the system's reliance on manual management, enhancing the overall robustness and reliability of the system.

[0072] A preferred embodiment of the intelligent inquiry and collaborative decision-making system for the entire business opportunity chain of the present invention includes the following modules: The opportunity creation request receiving module is used by the server to receive opportunity creation requests initiated by business terminals. The opportunity creation request carries customer demand information collected and uploaded by the salesperson's terminal. The server decrypts and verifies the opportunity creation request to obtain the customer demand information, parses the customer demand information to extract key elements and generate a structured opportunity data object, and assigns a globally unique opportunity number for storage. The business opportunity creation request carries encrypted information, a timestamp, and a hash value. The encrypted information is obtained by encrypting customer demand information using the SM4 algorithm, and the hash value is obtained by hashing the encrypted information and the timestamp. When the server receives the business opportunity creation request, it parses the encrypted information, timestamp, and hash value. First, it performs integrity verification using the hash value, then performs timeliness verification using the timestamp, and finally decrypts the encrypted information into customer demand information using the SM4 algorithm. By adopting triple security measures, the security of customer demand information transmission is effectively improved. The intelligent inquiry task initiation judgment module is used by the server to determine whether to initiate the intelligent inquiry task based on the demand clarity score in the business opportunity data object and the matching score of matching the demand clarity score with the standardized commodity quotation library. The standardized commodity quotation library is a resource library that centrally stores the company's existing commodity quotations and new procurement quotations. It records data such as commodity information, quotation amount, supplier, and validity period in a unified format and supports multi-condition retrieval and real-time updates. The inquiry module is used to: if the server determines that the intelligent inquiry task does not need to be initiated, proceed to the solution draft generation module; if it determines that the intelligent inquiry task needs to be initiated, obtain the core parameter set of the inquiry set by the business terminal, call the intelligent order dispatch engine, dynamically allocate the inquiry task to the optimal purchasing terminal, and push the task notification of the inquiry task to that purchasing terminal; the server receives the original quotation data of the supplier submitted by the purchasing terminal, preprocesses the original quotation data of the supplier to generate quotation data records, and synchronously updates them to the standardized commodity quotation database, establishing an association index between the quotation data records and the business opportunity number; The scheme draft generation module is used by the server to obtain product data based on the business opportunity data object and the standardized product quotation library to generate at least one scheme draft; The quotation document generation module is used by the server to create and manage a set of solutions for the same business opportunity, and to add the draft solutions as initial solution instances to the solution set; the business terminal performs independent visual combination and pricing adjustment for each solution instance in the solution set; the server responds to the instructions of the business terminal and generates a standardized quotation document from one or more selected solution instances. The solution collection management and visual adjustment mechanism cleverly balances automation and human intervention. Server-generated solution drafts serve as a high-quality starting point, while business personnel can flexibly perform 'visual combination and pricing adjustments' through an intuitive interface. This collaborative model of 'machine intelligence initial screening, human intelligence refinement' ensures both the efficiency of solution generation and the preservation of business personnel's professional judgment in handling complex business scenarios, ultimately generating standardized quotation documents. This design not only enhances the customization level of individual solutions, but the generated standardized documents also facilitate subsequent data analysis, forming a closed business loop.

[0073] The visualization analysis report generation module is used by the server to continuously record operation events, status change information, and data flow information of various business terminals, salesperson terminals, and purchasing terminals related to business opportunities, forming a complete digital archive of the entire business opportunity chain. The decision analysis model is run to analyze the digital archive of the entire business opportunity chain and automatically generate a visualization analysis report for evaluating the conversion efficiency of business opportunities, the root causes of non-sales, and the performance of related roles.

[0074] The entire business opportunity chain covers the complete business process from business opportunity demand registration, solution design / inquiry initiation, intelligent order dispatch, supplier quotation, solution combination export, transaction / non-transaction records, and data statistical analysis.

[0075] In the business opportunity creation request receiving module, the business opportunity data object carries at least the business opportunity number, business opportunity type (categorized by business attributes into bidding, supply, online platform ordering, and offline price comparison inquiry, used to distinguish business opportunity processing priority and process adaptation rules), requirement content, requirement clarity score, customer information, project description, and budget; the requirement content includes a requirement summary and a requirement list; the core fields of the price inquiry in the requirement summary include brand, category, product name, supply requirements, timeliness requirements, image gallery, and online platform reference link; The calculation process for the demand clarity score is as follows: The required content is input into a pre-trained requirement classification model to obtain an initial clarity probability value; the structuring degree and completeness of the required content are scored based on a preset rule set to obtain an auxiliary score value; the initial clarity probability value and the auxiliary score value are weighted and fused to obtain the final clarity score.

[0076] The salesperson terminal supports two methods: manual input by salespersons and document upload (Excel / Word). It can import customer demand information, budget range, product list and other data, and automatically complete format verification and deduplication.

[0077] The procurement terminal supports procurement personnel in entering and maintaining data such as basic supplier information, cooperation qualifications, main product categories, and quotation cycle, providing support for price matching.

[0078] The server connects to mainstream e-commerce and procurement platforms, and can automatically capture parameters and pricing information corresponding to product reference links to assist in the input of inquiry requirements and the construction of solutions.

[0079] The server's data storage layer stores: Business opportunity database: Stores full-chain data such as business opportunity registration information, progress, and transaction / non-transaction results; Standardized Commodity Price Database: Stores basic commodity information, price data, and supplier information, and supports multi-dimensional retrieval; Supplier database: Stores data such as supplier qualifications, cooperation records, and quotation history; Full-process operation log library: Retains the operation traces of each role (entry, modification, export, etc.), including the operator, operation time, and operation content, to ensure data traceability; Decision Analysis Dataset: This dataset aggregates business opportunity statistics, performance data, and root cause analysis data to support the generation of decision dashboards and reports.

[0080] This invention transforms previously unstructured, manually interpreted customer demand information into structured business opportunity data objects that are machine-recognizable and computable. This transformation forms the data foundation of the invention. It not only provides a unified input format for subsequent intelligent decision-making, but more importantly, by introducing a quantitative indicator—demand clarity score—it transforms the ambiguity of demand, which traditionally relied on the subjective experience of business personnel, into an objective and measurable technical parameter. This provides a data-driven basis for the crucial decision of whether to initiate a price inquiry, thereby achieving intelligentization at the source of the process.

[0081] In the intelligent inquiry task activation judgment module, the specific steps of determining whether to activate the intelligent inquiry task are as follows: If the requirement clarity score is higher than a preset first threshold and the matching score is higher than a preset second threshold, then it is determined that the intelligent inquiry task will not be started. If the requirement clarity score is lower than the first threshold, or the matching score is lower than the second threshold, then the intelligent inquiry task is initiated.

[0082] The dual threshold judgment mechanism (demand clarity score & matching score) is one of the core innovations of this invention. It simulates the decision-making logic of experienced business professionals, but achieves automation and precision through algorithms. When the demand is clear and a highly matching product exists in the historical quotation database, the system intelligently 'skips' unnecessary inquiry steps and directly enters the solution generation stage, greatly shortening the response cycle and avoiding the ineffective consumption of human resources. Conversely, it precisely triggers the inquiry process when the demand is unclear. This dynamic and adaptive decision-making logic effectively solves the problems of 'insufficient intelligence in the inquiry process' and 'slow response speed' in the background technology, realizing on-demand allocation and optimization of resource input.

[0083] In the inquiry module, the step of calling the intelligent order dispatch engine to dynamically allocate inquiry tasks to the optimal procurement terminal specifically involves: Calculate the semantic similarity between the core parameter set of the inquiry and the pre-configured domain of expertise tag set of each procurement terminal to obtain the parameter matching score; Obtain the number of incomplete inquiry tasks and the historical average task processing time for each procurement terminal, and calculate the current load factor for each procurement terminal. Based on the predefined weights, the parameter matching score and load coefficient are combined to calculate the overall priority value of each purchasing terminal for the current inquiry task, and the purchasing terminal with the highest overall priority value is selected as the target terminal. Based on the target terminal and the comprehensive priority value, the dispatch result is generated and pushed to the business terminal for confirmation. Based on the confirmation signal from the business terminal, the task details of the inquiry task are packaged into a task notification and pushed to the target terminal.

[0084] The intelligent task dispatch engine is not simply a task rotation or random allocation, but a multi-factor optimization model that comprehensively considers professional competence matching (semantic similarity) and real-time workload (current load coefficient). Through predefined weights and comprehensive priority calculations, it ensures that each inquiry task is dynamically assigned to the 'most suitable' rather than the 'first available' purchasing personnel (purchasing terminals). This allocation strategy significantly improves the initial processing success rate and response efficiency of inquiry tasks, fundamentally solving the problems of 'matching errors' and 'uneven task allocation' caused by traditional manual task dispatch, and transforming human resources into intelligently schedulable 'computing power' resources.

[0085] In the inquiry module, the preprocessing of the supplier's original quotation data to generate quotation data records specifically involves: After performing a pre-defined mandatory field integrity check on the supplier's original quotation data, the supplier's original quotation data from different data sources and with different formats are mapped to a predefined unified data model to perform format standard conversion. Then, natural language processing is performed on the product names and specifications in the supplier's original quotation data to convert them into standard terms for semantic normalization. This completes the preprocessing of the supplier's original quotation data and generates quotation data records that conform to predetermined standards. Generate a globally unique version number for the quoted data record, and associate the version number with the corresponding business opportunity number, procurement terminal identifier, and supplier information; Each quotation record stored in the standardized commodity quotation database is associated with a lifecycle status identifier.

[0086] Standardized preprocessing of supplier raw quotation data is a key step in building high-quality data assets in this solution. Through format standardization and semantic normalization, the system "cleans" the raw data, which comes from diverse sources and has widely varying formats, into standardized data records with a unified format and clear semantics. This process not only provides reliable data for the generation of immediate solutions, but more importantly, each quotation data record is associated with business opportunity number, supplier, and other information, and given a lifecycle status identifier. This allows historical quotation data to be accumulated and reused, completely changing the predicament of quotation data becoming an information silo after "one-time use" in the traditional model. This lays a solid foundation for building a "standardized commodity quotation database," a core enterprise knowledge base, and directly addresses the pain point of "low standardization of commodity data management."

[0087] In the draft solution generation module, when it is determined that the intelligent inquiry task will not be initiated, the specific process of generating the draft solution is as follows: Based on the demand summary in the business opportunity data object, the server uses natural language processing technology to parse the demand intent and, in conjunction with budget constraints, intelligently retrieves and recommends product data from the standardized product price database to generate a preset number of draft solutions.

[0088] In the aforementioned draft solution generation module, when it is determined that an intelligent inquiry task will be initiated, the specific process for generating the draft solution is as follows: The server parses the demand list in the business opportunity data object, performs multi-attribute matching between the demand list and the product entries in the standardized product quotation library, and filters out a set of candidate products with a matching degree higher than a preset matching degree threshold. Based on the current business opportunity type, budget, and key product categories, similar solution templates are retrieved from the historical successful solution database using vectorization technology to obtain product data from the similar solution templates. Based on the product data in the candidate product set and similar solution templates, the server automatically generates or combines at least one solution draft and displays it visually on the interface of the business terminal.

[0089] The draft solution generation mechanism triggers two differentiated intelligent generation paths based on different judgment results. For business opportunities with high clarity and high matching degree, the system acts as an 'intelligent assistant,' using NLP technology to analyze intent and quickly combine solutions, achieving a response time within seconds. For business opportunities requiring price inquiries, it combines multi-attribute matching and vectorized retrieval of historical solution templates to generate more valuable draft solutions. This scenario-based, intelligent solution generation capability frees business personnel from the manual screening of massive amounts of product information, allowing them to focus on optimizing the value of solutions and communicating with customers. Essentially, it partially automates and automates the experience-based solution creation work, significantly improving 'solution generation flexibility' and 'response speed.'

[0090] In the visualization analysis report generation module, the operational decision analysis model is specifically used for: Opportunity conversion funnel analysis: Count the number of opportunities at each status transition node, calculate the conversion rate and drop-off points to evaluate the effectiveness of opportunity conversion; the status transition nodes include at least registered, processing, solution generated, completed, and uncompleted. Unsuccessful sales root cause analysis: Based on natural language processing technology, the analysis of text recording the reasons for unsuccessful sales in business terminals, combined with key events in the operation log, automatically classifies the reasons for unsuccessful sales into internal factors (solution defects, inquiry delays, excessively high prices) or external factors (changes in customer needs, competition from competitors) through a classification model to assess the root causes of unsuccessful sales. Multi-dimensional performance calculation: Through a multi-dimensional evaluation sub-model, the related roles of salesperson terminals, business terminals, and procurement terminals are evaluated, including at least the amount of business opportunities contributed, solution quality, inquiry response speed, and quotation accuracy, in order to assess the performance of related roles.

[0091] The business opportunity full-link digital archive and decision analysis model represents the advancement of this invention from 'process automation' to 'intelligent decision-making'. It is not simply an operation log record, but rather an organic linking of discrete operations, states, and data throughout the entire link, forming a traceable and analyzable data chain. Based on this, the decision analysis model performs business opportunity conversion funnel analysis, root cause analysis of non-sales (automatic attribution through NLP technology), and multi-dimensional performance calculation, transforming tacit knowledge previously buried in the minds of various personnel or scattered in various places into quantifiable and reusable explicit strategic assets for the enterprise. This directly solves the fundamental problem of 'lack of full-link data traceability and analysis capabilities, resulting in weak decision support,' providing enterprise managers with unprecedented data-driven decision insights.

[0092] Also includes: The intelligent monitoring module for inquiry progress is used by the server to start a monitoring process for each business opportunity instance in the intelligent inquiry task. The monitoring process dynamically calculates the expected completion time of each stage of the inquiry task based on the expected timeliness of the core parameters set of the inquiry. The actual progress of the task is compared with the expected completion time in real time. When the deviation exceeds the allowable range, a graded warning message is automatically sent to the corresponding procurement terminal, and the warning event is recorded in the business opportunity full-link digital archive. The dynamic maintenance module for the quotation database is used by the server to periodically scan the standardized commodity quotation database. For quotation data records that have exceeded their validity period, the system automatically marks their lifecycle status as invalid and reduces their priority or excludes them in subsequent solution recommendations and quotation matching.

[0093] The introduced proactive monitoring and early warning mechanisms based on expected timeliness, along with automated lifecycle management of quotation data, together constitute the system's 'intelligent operation and maintenance' layer. These ensure the smooth operation of business processes and the 'freshness' of data assets. The monitoring process shifts from 'post-event remediation' to 'in-process intervention,' effectively reducing the risk of lost business opportunities due to delays. Automated marking of invalid quotations ensures the accuracy and reliability of the system's recommendations. These automated operation and maintenance features further reduce the system's reliance on manual management, enhancing the overall robustness and reliability of the system.

[0094] To facilitate understanding of the present invention, the following examples are provided: 1. Demand Input: Salespersons collect vague demands such as "100 computers, budget of 1 million, and timeframe of 15 days" in their terminals and submit them to the business terminal; the business terminal inputs the business opportunity type (offline price comparison inquiry), project description, customer information, fills in the core fields of the inquiry (category: computers, budget: 1 million, timeframe: 15 days), and initiates a business opportunity creation request; 2. Intelligent order dispatch: Based on the "computer" category, the system automatically matches the purchasing terminals of personnel who are proficient in purchasing digital products and pushes task notifications for inquiry tasks. 3. Procurement Inquiry: The procurement terminal connects with 3 suppliers to obtain quotations for different brands and models of computers, enters the information into the system (including product information, quotation, and delivery cycle), and submits feedback results; 4. Quotation Database Update: The system automatically synchronizes the original quotation data of 3 newly added suppliers to the standardized commodity quotation database in a standardized format, and marks the validity period as 30 days; 5. Solution Setup: The business terminal receives quotation feedback, combines two solution groups (Solution 1: High-end brand computers, Solution 2: Cost-effective brand computers), optimizes and adjusts them, and then exports a standardized spreadsheet. 6. Data Recording and Analysis: The system retains a complete record of all operations. If a deal is not ultimately closed (reason: customer budget adjustment), it is automatically categorized under external reasons statistics and a visual analysis report is generated.

[0095] Performance testing and effect verification: The following results were obtained by simulating 1000 different types of business opportunity data: Collaboration efficiency: Inquiry and order dispatch response time ≤ 5 seconds, quotation result synchronization delay ≤ 3 seconds, improving efficiency by 65% ​​compared to traditional offline mode; Data reuse rate: The rate of repeated inquiries for similar business opportunities decreased from 80% to 15%, and procurement efficiency increased by 50%; Solution design cycle: The solution design cycle for vague requirements has been shortened from an average of 2 days to 4 hours, significantly improving customer response efficiency; Data traceability and analysis: The time to pinpoint the reasons for non-sales is ≤10 minutes, and the accuracy rate of performance data statistics reaches 99.8%, meeting the needs of enterprise decision-making.

[0096] While specific embodiments of the present invention have been described above, those skilled in the art should understand that the specific embodiments described are merely illustrative and not intended to limit the scope of the present invention. Equivalent modifications and variations made by those skilled in the art in accordance with the spirit of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent price inquiry and collaborative decision-making across the entire business opportunity chain, characterized in that: Includes the following steps: Step S1: The server receives a business opportunity creation request initiated by a business terminal. The business opportunity creation request carries customer demand information collected and uploaded by the salesperson's terminal. The server decrypts and verifies the business opportunity creation request to obtain the customer demand information, parses the customer demand information to extract key elements and generate a structured business opportunity data object, and assigns a globally unique business opportunity number for storage. Step S2: The server determines whether to start the intelligent inquiry task based on the demand clarity score in the business opportunity data object and the matching score of matching the demand clarity score with the standardized product quotation database. Step S3: If the server determines that the intelligent inquiry task does not need to be started, then proceed to step S4; if it determines that the intelligent inquiry task needs to be started, then obtain the core parameter set of the inquiry set set by the business terminal, call the intelligent order dispatch engine, dynamically allocate the inquiry task to the optimal purchasing terminal, and push the task notification of the inquiry task to the purchasing terminal. The server receives the original quotation data from suppliers submitted by the procurement terminal, preprocesses the original quotation data to generate quotation data records, and synchronously updates them to the standardized commodity quotation database, establishing an association index between the quotation data records and the business opportunity number; Step S4: The server obtains product data based on the business opportunity data object and the standardized product price library to generate at least one draft solution. Step S5: The server creates and manages a solution set for the same business opportunity, and adds the solution draft as the initial solution instance to the solution set; the business terminal performs independent visual combination and pricing adjustment for each solution instance in the solution set; In response to instructions from the business terminal, the server generates a standardized quotation document from one or more selected instance solutions. Step S6: The server continuously records the operation events, status change information, and data flow information of each business terminal, salesperson terminal, and purchasing terminal related to the business opportunity, forming a complete digital archive of the entire business opportunity chain. The decision analysis model analyzes the entire digital profile of the business opportunity and automatically generates a visual analysis report to evaluate the conversion efficiency of the business opportunity, the root causes of non-sales, and the performance of related roles.

2. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S1, the business opportunity data object carries at least the business opportunity number, business opportunity type, requirement content, requirement clarity score, customer information, and budget; the requirement content includes a requirement summary and a requirement list; The calculation process for the demand clarity score is as follows: The required content is input into a pre-trained requirement classification model to obtain an initial clarity probability value; An auxiliary score is obtained by evaluating the structure and completeness of the required content based on a preset set of rules. The initial clarity probability value and the auxiliary score value are weighted and fused to obtain the final clarity score.

3. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S2, determining whether to initiate the intelligent price inquiry task specifically involves: If the requirement clarity score is higher than a preset first threshold and the matching score is higher than a preset second threshold, then it is determined that the intelligent inquiry task will not be started. If the requirement clarity score is lower than the first threshold, or the matching score is lower than the second threshold, then the intelligent inquiry task is initiated.

4. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S3, the step of calling the intelligent order dispatch engine to dynamically allocate the inquiry task to the optimal procurement terminal specifically involves: Calculate the semantic similarity between the core parameter set of the inquiry and the pre-configured domain of expertise tag set of each procurement terminal to obtain the parameter matching score; Obtain the number of incomplete inquiry tasks and the historical average task processing time for each procurement terminal, and calculate the current load factor for each procurement terminal. Based on the predefined weights, the parameter matching score and load coefficient are combined to calculate the overall priority value of each purchasing terminal for the current inquiry task, and the purchasing terminal with the highest overall priority value is selected as the target terminal. Based on the target terminal and the comprehensive priority value, the dispatch result is generated and pushed to the business terminal for confirmation. Based on the confirmation signal from the business terminal, the task details of the inquiry task are packaged into a task notification and pushed to the target terminal.

5. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S3, the preprocessing of the supplier's original quotation data to generate quotation data records specifically involves: After performing a pre-defined mandatory field integrity check on the supplier's original quotation data, the supplier's original quotation data from different data sources and with different formats are mapped to a predefined unified data model to perform format standard conversion. Then, natural language processing is performed on the product names and specifications in the supplier's original quotation data to convert them into standard terms for semantic normalization. This completes the preprocessing of the supplier's original quotation data and generates quotation data records that conform to predetermined standards. Generate a globally unique version number for the quoted data record, and associate the version number with the corresponding business opportunity number, procurement terminal identifier, and supplier information; Each quotation record stored in the standardized commodity quotation database is associated with a lifecycle status identifier.

6. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S4, when it is determined that the intelligent price inquiry task will not be initiated, the process of generating the draft solution is as follows: Based on the demand summary in the business opportunity data object, the server uses natural language processing technology to parse the demand intent and, in conjunction with budget constraints, intelligently retrieves and recommends product data from the standardized product price database to generate a preset number of draft solutions.

7. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S4, when it is determined that the intelligent inquiry task is to be initiated, the process of generating the draft solution is as follows: The server parses the demand list in the business opportunity data object, performs multi-attribute matching between the demand list and the product entries in the standardized product quotation library, and filters out a set of candidate products with a matching degree higher than a preset matching degree threshold. Based on the current business opportunity type, budget, and key product categories, similar solution templates are retrieved from the historical successful solution database using vectorization technology to obtain product data from the similar solution templates. Based on the product data in the candidate product set and similar solution templates, the server automatically generates or combines at least one solution draft and displays it visually on the interface of the business terminal.

8. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: In step S6, the operational decision analysis model is specifically used for: Opportunity conversion funnel analysis: Count the number of opportunities at each status transition node, calculate the conversion rate and drop-off points to evaluate the effectiveness of opportunity conversion; the status transition nodes include at least registered, processing, solution generated, completed, and uncompleted. Root cause analysis of non-sales failures: Based on natural language processing technology, the text of reasons for non-sales failures recorded in the business terminal is analyzed, and combined with key events in the operation log, the reasons for non-sales failures are automatically classified into internal or external factors through a classification model to assess the root causes of non-sales failures. Multi-dimensional performance calculation: Through a multi-dimensional evaluation sub-model, the related roles of salesperson terminals, business terminals, and procurement terminals are evaluated, including at least the amount of business opportunities contributed, solution quality, inquiry response speed, and quotation accuracy, in order to assess the performance of related roles.

9. The intelligent inquiry and collaborative decision-making method for the entire business opportunity chain as described in claim 1, characterized in that: Also includes: Step S7: The server starts a monitoring process for each business opportunity instance in the intelligent inquiry task. The monitoring process dynamically calculates the expected completion time of each stage of the inquiry task based on the expected timeliness of the core parameters set of the inquiry. The actual progress of the task is compared with the expected completion time in real time. When the deviation exceeds the allowable range, a graded warning message is automatically sent to the corresponding procurement terminal, and the warning event is recorded in the business opportunity full-link digital archive. Step S8: The server periodically scans the standardized commodity quotation database. For quotation data records that have exceeded their validity period, the server automatically marks their lifecycle status as invalid and reduces their priority or excludes them in subsequent solution recommendations and quotation matching.

10. A business opportunity end-to-end intelligent inquiry and collaborative decision-making system, characterized in that: Includes the following modules: The opportunity creation request receiving module is used by the server to receive opportunity creation requests initiated by business terminals. The opportunity creation request carries customer demand information collected and uploaded by the salesperson's terminal. The server decrypts and verifies the opportunity creation request to obtain the customer demand information, parses the customer demand information to extract key elements and generate a structured opportunity data object, and assigns a globally unique opportunity number for storage. The intelligent inquiry task start judgment module is used by the server to determine whether to start the intelligent inquiry task based on the demand clarity score in the business opportunity data object and the matching score of matching the demand clarity score with the standardized product quotation library. The inquiry module is used by the server to enter the solution draft generation module if it determines that the intelligent inquiry task does not need to be started. If it is determined that the intelligent inquiry task needs to be initiated, the core parameter set of the inquiry set by the business terminal is obtained, the intelligent order dispatch engine is called, the inquiry task is dynamically assigned to the optimal procurement terminal, and the task notification of the inquiry task is pushed to the procurement terminal. The server receives the original quotation data from suppliers submitted by the procurement terminal, preprocesses the original quotation data to generate quotation data records, and synchronously updates them to the standardized commodity quotation database, establishing an association index between the quotation data records and the business opportunity number; The scheme draft generation module is used by the server to obtain product data based on the business opportunity data object and the standardized product quotation library to generate at least one scheme draft; The quotation document generation module is used by the server to create and manage a set of plans for the same business opportunity, and to add the draft plan as the initial plan instance to the plan set; the business terminal performs independent visual combination and pricing adjustment for each plan instance in the plan set; In response to instructions from the business terminal, the server generates a standardized quotation document from one or more selected instance solutions. The visualization analysis report generation module is used by the server to continuously record the operation events, status change information and data flow information of various business terminals, salesperson terminals and purchasing terminals related to business opportunities, forming a complete digital archive of the entire business opportunity chain. The decision analysis model analyzes the entire digital profile of the business opportunity and automatically generates a visual analysis report to evaluate the conversion efficiency of the business opportunity, the root causes of non-sales, and the performance of related roles.

Images