Multi-dimensional index state-based verbal skill generation method, system, equipment and medium

Abstract

The invention discloses a verbal skill generation method, system and device based on a multi-dimensional index state and a medium, and the method comprises the steps: calculating state values of evaluation indexes of multiple dimensions according to application data and associated historical data of a to-be-evaluated business scheme; comparing the state value of the evaluation index of each dimension with a threshold pre-configured for the evaluation index of each dimension, and determining the state level of the evaluation index of each dimension; according to a preset linkage rule, performing linkage combination analysis on the state levels of the evaluation indexes of the multiple dimensions to generate a comprehensive evaluation result; based on the comprehensive evaluation result, matching a corresponding evaluation verbal skill template from a preset verbal skill rule base; and according to service information in the application data, filling variables in the evaluation verbal skill template, and generating a final evaluation verbal skill of the to-be-evaluated service scheme. According to the method, multi-dimensional index linkage analysis and differentiation evaluation content automatic generation are realized, and evaluation result pertinence, operability and risk early warning capability are improved.

Description

Technical Field

[0001] This invention relates to the field of data processing and intelligent speech generation technology, and in particular to a speech generation method, system, device and medium based on multi-dimensional indicator states. Background Technology

[0002] In the field of life insurance business plan management, traditional evaluation results mainly rely on subjective human feedback, making it difficult to automatically generate evaluation opinions based on preset templates. Existing technologies generally use single-dimensional evaluation indicators, failing to construct complex evaluation systems to achieve differentiated content generation, resulting in significant deficiencies in the relevance and guidance of the evaluation results. Specifically, existing technologies have the following objective shortcomings: 1) The evaluation indicators are isolated from each other and lack the necessary linkage analysis mechanism. It is impossible to cross-compare and link multiple sets of core indicators such as the monthly cumulative application for production and the threshold of the ratio of the planned production to the threshold of the cumulative deviation of the previous year and the threshold of the deviation value of the plan, which seriously restricts the ability to identify risks.

[0003] 2) The evaluation results are output in a rigid manner, often relying on manual adjustments or fixed templates for a single dimension. This makes it impossible to dynamically generate differentiated evaluation content based on different combinations of results from key indicator groups, resulting in poor operability and scenario adaptability of the evaluation results, which makes it difficult to meet diversified management needs.

[0004] 3) The existing system lacks dynamic configuration capabilities and cannot flexibly adjust the combination of evaluation indicators and the logic of speech generation according to business changes, resulting in significant lack of system adaptability.

[0005] 4) Due to the lack of a multi-dimensional indicator linkage analysis and dynamic evaluation mechanism, the risk warning capability is weak, making it difficult to detect potential risks in the implementation process of the plan in a timely manner, and unable to provide timely and effective early warning support for management decisions.

[0006] Therefore, there is an urgent need to provide a technical solution to address the above problems. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides a method, system, device, and medium for generating rhetoric based on multi-dimensional indicator states.

[0008] Firstly, the present invention provides a method for generating rhetoric based on multi-dimensional indicator states, the technical solution of which is as follows: Obtain application data and related historical data for the business proposals to be evaluated; Based on the application data and the associated historical data, the status values ​​of multiple dimensions of evaluation indicators are calculated. The multiple dimensions of evaluation indicators include at least production indicators, deviation indicators and progress indicators. The status value of the evaluation indicator for each dimension is compared with the pre-configured threshold for the evaluation indicator for each dimension to determine the status level of the evaluation indicator for each dimension. According to the preset linkage rules, the status levels of the evaluation indicators of the multiple dimensions are analyzed by linkage combination to generate a comprehensive evaluation result of the business solution to be evaluated. The preset linkage rules are used to define the mapping relationship between the status level combinations of different dimension indicators and different comprehensive evaluation results. Based on the comprehensive evaluation results, the corresponding evaluation script template is matched from the preset script rule library; Based on the business information in the application data, the variables in the evaluation script template are filled in to generate the final evaluation script for the business plan to be evaluated.

[0009] The beneficial effects of the speech generation method based on multi-dimensional indicator states of the present invention are as follows: The method of this invention obtains business plan application data and associated historical data, calculates the status values ​​of multi-dimensional evaluation indicators such as production, deviation, and progress, and determines the status level. Based on preset linkage rules, it performs combined analysis on the status levels of multi-dimensional indicators to generate a comprehensive evaluation result. It matches templates from a preset script rule library and fills in variables to generate the final evaluation script. This solves the problems of traditional evaluation relying on subjective human feedback, isolated evaluation indicators lacking linkage, rigid output methods unable to dynamically generate differentiated content, and lack of dynamic configuration capabilities. It realizes multi-dimensional indicator linkage analysis and automatic generation of differentiated evaluation content, improving the relevance, operability, and risk warning capabilities of the evaluation results.

[0010] Based on the above scheme, the speech generation method based on multi-dimensional indicator status of the present invention can be further improved as follows.

[0011] In one optional approach, the step of obtaining the application data and associated historical data of the business solution to be evaluated includes: Obtain the application data of the business plan to be evaluated, wherein the application data includes plan identifier, plan type, channel information, budget project information and cost information; Based on the scheme identifier, the channel information, and the scheme type, the associated historical data of the business scheme to be evaluated is obtained from the historical business data source.

[0012] The advantages of adopting the above optional methods are: further clarifying the specific content scope of application data and associated historical data, and achieving accurate extraction of historical data through scheme identification, channel information and scheme type, providing a complete and accurate data foundation for multi-dimensional indicator calculation.

[0013] In one alternative approach, the step of calculating the status values ​​of multiple dimensions of evaluation indicators based on the application data and the associated historical data includes: Based on the budget project information, the expense information, and the input and output data in the associated historical data, calculate the status value of the input-output indicator; Based on the comparison between the application data and the execution data of the current statistical period and the historical benchmark data in the associated historical data, the status value of the deviation index is calculated; Based on the cost information, the budget execution data in the associated historical data, and the business progress data, the status value of the progress indicator is calculated.

[0014] The advantages of adopting the above optional methods are: further refining the calculation basis of production indicators, deviation indicators and schedule indicators, respectively, and calculating status values ​​based on budget project information, cost information, historical input and output data, comparison of execution data with benchmark data and business progress data, so that the indicators reflect the business status more accurately.

[0015] In one alternative approach, the step of comparing the state value of each dimension's evaluation indicator with a pre-configured threshold for each dimension's evaluation indicator to determine the state level of each dimension's evaluation indicator includes: Obtain multiple pre-configured threshold levels for the evaluation metrics of each dimension; The status value of the production commissioning indicator is compared with multiple threshold levels configured for the production commissioning indicator to determine the status level of the production commissioning indicator; The state value of the deviation indicator is compared with multiple threshold levels configured for the deviation indicator to determine the state level of the deviation indicator; The status value of the progress indicator is compared with multiple threshold levels configured for the progress indicator to determine the status level of the progress indicator.

[0016] The beneficial effects of adopting the above optional method are as follows: by further adopting a multi-level threshold comparison mechanism, the status values ​​of production indicators, deviation indicators, and progress indicators are compared with the corresponding preset thresholds, so as to realize the refined classification and judgment of indicator status and provide accurate level input for subsequent linkage analysis.

[0017] In one optional approach, the step of performing a combined analysis of the status levels of the multiple dimensions of evaluation indicators according to preset linkage rules to generate a comprehensive evaluation result for the business solution to be evaluated includes: According to the preset linkage rules, the status level of the production launch indicator, the status level of the deviation indicator, and the status level of the progress indicator are combined into a status level combination; Based on the state level combination, a preset mapping table between the state level combination and the comprehensive evaluation result is queried to determine the comprehensive evaluation result of the business solution to be evaluated.

[0018] The beneficial effects of adopting the above optional method are as follows: further use the preset linkage rules to combine the status levels of the three-dimensional indicators into a status level combination, and determine the comprehensive evaluation result by querying the mapping relationship table, so as to realize the rule-based and standardized judgment of multi-indicator linkage in complex business scenarios.

[0019] In one optional approach, the step of matching the corresponding evaluation script template from a preset script rule base based on the comprehensive evaluation result includes: Based on the comprehensive evaluation results, query the preset dialogue rule library; Based on the preset mapping relationship between the comprehensive evaluation results and evaluation script templates stored in the preset script rule base, the evaluation script template corresponding to the comprehensive evaluation result is obtained.

[0020] The advantages of adopting the above optional method are: further querying the preset script rule library based on the comprehensive evaluation results, automatically matching the corresponding evaluation script template using the preset mapping relationship, realizing the rapid association between the evaluation results and the output content, and improving the automation of script generation.

[0021] In one optional approach, the business information includes: basic scheme information, financial limit information, and business organization information; the step of filling in the variables in the evaluation script template based on the business information in the application data to generate the final evaluation script for the business scheme to be evaluated includes: Extract the basic information of the business plan to be evaluated, financial information, and business organization information from the application data; Fill the corresponding variable positions in the evaluation script template with the basic information of the plan, the financial limit information, and the business organization information; Based on the filled-in evaluation script template, the final evaluation script for the business solution to be evaluated is generated.

[0022] The beneficial effects of adopting the above optional methods are: further extracting basic information of the plan, financial quota information and business organization information from the application data, filling specific business elements into the variable positions of the evaluation script template, so that the final generated script fits the actual business scenario and enhances the relevance of the evaluation content.

[0023] Secondly, this invention provides a speech generation system based on multi-dimensional indicator states, the technical solution of which is as follows: The acquisition module is used to acquire application data and associated historical data of the business solutions to be evaluated; The calculation module is used to calculate the status values ​​of multiple evaluation indicators based on the application data and the associated historical data. The multiple evaluation indicators include at least production indicators, deviation indicators and progress indicators. The comparison module is used to compare the status value of the evaluation indicator for each dimension with the pre-configured threshold for the evaluation indicator for each dimension, and determine the status level of the evaluation indicator for each dimension. The analysis module is used to perform a combined analysis of the status levels of the evaluation indicators of the multiple dimensions according to the preset linkage rules, and generate a comprehensive evaluation result of the business solution to be evaluated. The preset linkage rules are used to define the mapping relationship between the status level combinations of different dimension indicators and different comprehensive evaluation results. The matching module is used to match the corresponding evaluation script template from the preset script rule library based on the comprehensive evaluation result; The generation module is used to fill in the variables in the evaluation script template according to the business information in the application data, and generate the final evaluation script for the business plan to be evaluated.

[0024] The beneficial effects of the speech generation system based on multi-dimensional indicator states of the present invention are as follows: The system of this invention obtains business plan application data and associated historical data, calculates the status values ​​of multi-dimensional evaluation indicators such as production, deviation, and progress, and determines the status level. Based on preset linkage rules, it performs combined analysis on the status levels of multi-dimensional indicators to generate a comprehensive evaluation result. It matches templates from a preset script rule library and fills in variables to generate the final evaluation script. This solves the problems of traditional evaluation relying on subjective human feedback, isolated evaluation indicators lacking linkage, rigid output methods unable to dynamically generate differentiated content, and lack of dynamic configuration capabilities. It realizes multi-dimensional indicator linkage analysis and automatic generation of differentiated evaluation content, improving the pertinence, operability, and risk warning capabilities of the evaluation results.

[0025] Thirdly, the technical solution of an electronic device according to the present invention is as follows: It includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the speech generation method based on multidimensional indicator states of the present invention.

[0026] Fourthly, the technical solution of a computer-readable storage medium provided by the present invention is as follows: The computer-readable storage medium stores instructions that, when read, cause the computer-readable storage medium to perform the steps of the speech generation method based on multidimensional indicator states of the present invention.

[0027] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0028] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating an embodiment of a speech generation method based on multi-dimensional indicator states according to the present invention. Figure 2 This is one of the schematic diagrams illustrating the principle. Figure 3 This is the second schematic diagram of the principle; Figure 4 This is the third schematic diagram of the principle; Figure 5 This is the fourth schematic diagram of the principle; Figure 6 This is a schematic diagram of an embodiment of the speech generation system based on multi-dimensional indicator states according to the present invention; Figure 7 This is a schematic diagram of an embodiment of an electronic device according to the present invention. Detailed Implementation

[0029] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0030] Figure 1 This diagram illustrates a flowchart of an embodiment of a multi-dimensional indicator state-based dialogue generation method provided by the present invention. This method can be executed by electronic devices such as terminal devices or servers. The terminal device can be any fixed or mobile terminal, such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, or wearable device. The server can be a single server or a server cluster consisting of multiple servers. Any electronic device can implement the multi-dimensional indicator state-based dialogue generation method by having its processor call computer-readable instructions stored in its memory. Figure 1 As shown, it includes the following steps: S1. Obtain the application data and related historical data of the business plan to be evaluated.

[0031] The business plan to be evaluated refers to a life insurance business activity plan that requires management review and risk analysis; for example, a branch of a life insurance company plans to launch a "Special Marketing Expense Incentive Program for High-End Customers" in the third quarter. Application data refers to a structured set of data describing the basic information and resource planning of the business plan to be evaluated; for example, the application data for the "Special Marketing Expense Incentive Program for High-End Customers" includes the program identifier "SX202407001", program type "expense incentive", channel information "bancassurance channel", budget item information "business promotion fee", and expense information "total expense of 1 million yuan". Related historical data refers to historical execution and result data from previous periods that are related to the business plan to be evaluated in terms of business dimensions; for example, historical investment data of 850,000 yuan, historical premium output data of 1 million yuan, and expense usage progress data for the same branch, channel, and type of program as the "Special Marketing Expense Incentive Program for High-End Customers" in the third quarter of the previous year.

[0032] S2. Based on the application data and the associated historical data, calculate the status values ​​of multiple dimensions of evaluation indicators, wherein the multiple dimensions of evaluation indicators include at least production indicators, deviation indicators and progress indicators.

[0033] The multi-dimensional evaluation indicators refer to a set of parameters constructed from different business perspectives to quantitatively assess the status of a plan. For example, the three evaluation indicators used to evaluate the "High-End Customer Special Marketing Expense Incentive Plan" are the return on investment indicator (ROI) measuring the efficiency of expense utilization, the deviation indicator assessing the stability of execution, and the progress indicator monitoring the matching degree of the pace. The status value refers to the specific numerical result of the evaluation indicator obtained through calculation. For example, the current ROI status value for the "High-End Customer Special Marketing Expense Incentive Plan" is calculated to be 0.85, the deviation status value is 0.05, and the progress status value is 0.08. The ROI indicator refers to an indicator used to measure the efficiency relationship between the plan's resource input and business output. For example, the ROI status value of 0.85 for the "High-End Customer Special Marketing Expense Incentive Plan" is calculated by dividing the current cumulative expense input of 850,000 yuan by the cumulative premium income of 1 million yuan generated during the same period. Deviation indicators refer to metrics that reflect the degree of deviation between the actual implementation of a plan and historical benchmarks or expected targets. For example, the deviation indicator for the "High-End Customer Special Marketing Expense Incentive Plan," with a state value of 0.05, is obtained by calculating the deviation rate between the current cumulative investment and the cumulative investment in the same period of the previous year. Progress indicators refer to metrics that measure the coordination and matching degree between the progress of resource consumption and the progress of business target achievement. For example, the progress indicator for the "High-End Customer Special Marketing Expense Incentive Plan," with a state value of 0.08, is obtained by calculating the difference between the current expense usage progress of 70% and the current premium target achievement progress of 62%.

[0034] S3. Compare the status value of the evaluation indicator for each dimension with the pre-configured threshold for the evaluation indicator for each dimension, and determine the status level of the evaluation indicator for each dimension.

[0035] The pre-configured thresholds refer to the set of critical values ​​pre-set for various evaluation indicators to divide different state intervals. For example, the pre-configured thresholds for the production launch indicator include a warning value of 0.9 and a prohibition value of 1.0; the thresholds for the deviation indicator include a prompt value of 0.03 and a warning value of 0.08; and the thresholds for the schedule indicator include a warning value of 0.05. The state level refers to the qualitative evaluation level determined based on whether the state value of the evaluation indicator falls within the pre-configured threshold range. For example, if the production launch indicator state value of 0.85 is lower than the warning value of 0.9, the state level of the production launch indicator is determined to be "Level A"; if the deviation indicator state value of 0.05 is higher than the prompt value of 0.03 but lower than the warning value of 0.08, the state level of the deviation indicator is determined to be "Level B"; and if the schedule indicator state value of 0.08 is higher than the warning value of 0.05, the state level of the schedule indicator is determined to be "Level C".

[0036] S4. According to the preset linkage rules, perform linkage combination analysis on the status levels of the multiple dimensions of evaluation indicators to generate a comprehensive evaluation result of the business solution to be evaluated. The preset linkage rules are used to define the mapping relationship between the status level combinations of different dimension indicators and different comprehensive evaluation results.

[0037] Among them, the preset linkage rule refers to a predefined logical rule used to link and integrate the status levels of multiple evaluation indicators to arrive at a unified conclusion. For example, a preset linkage rule stipulates that when the status levels of the production indicator, deviation indicator, and progress indicator are combined as A, B, and C respectively, the corresponding comprehensive evaluation result is "Class B result". Linkage combination analysis refers to the process of comprehensively linking and judging the status levels of multiple independent evaluation indicators based on the preset linkage rule. For example, the linkage combination analysis process for the "High-end Customer Special Marketing Expense Incentive Program" involves taking the three status levels—production indicator A, deviation indicator B, and progress indicator C—as a whole input and analyzing them according to the rule. The comprehensive evaluation result refers to the general qualitative evaluation conclusion of the overall status of the program obtained through linkage combination analysis. For example, based on the status level combination of A, B, and C, by querying the linkage rule, the comprehensive evaluation result of the "High-end Customer Special Marketing Expense Incentive Program" is determined to be "Class B result". A status level combination refers to a combination sequence formed by arranging the status levels of multiple evaluation indicators in a specific order; for example, the status level combination of the "high-end customer special marketing expense incentive plan" is "production indicator A level, deviation indicator B level, and progress indicator C level", which can be abbreviated as "ABC".

[0038] S5. Based on the comprehensive evaluation results, match the corresponding evaluation script template from the preset script rule library.

[0039] The pre-set script rule base refers to a data set that stores evaluation text templates containing variable placeholders corresponding to different comprehensive evaluation results. For example, the script rule base stores an evaluation script template associated with "Category B result," which reads, "The current production efficiency of [Solution Name] is acceptable, but attention should be paid to situations where the cost execution progress is faster than the business progress." An evaluation script template refers to a pre-set evaluation text framework containing one or more variable placeholders. For example, the evaluation script template matching Category B result is: "[Solution Name] involves [number of solution types] solution types, with a total amount of [total amount]. According to the assessment, under the [Channel Name] channel, the cost investment progress is relatively fast; it is recommended to pay attention to the catch-up situation of business targets." S6. Based on the business information in the application data, fill in the variables in the evaluation script template to generate the final evaluation script for the business plan to be evaluated.

[0040] The business information refers to the relevant information extracted from the application data and used to populate the variables in the evaluation script template to form specific evaluation content. For example, the business information extracted from the application data for the "High-end Customer Special Marketing Expense Incentive Program" includes the basic program information "High-end Customer Special Marketing Expense Incentive Program," the financial limit information "1 million yuan," and the business organization information "bank-insurance channel." The variables in the evaluation script template refer to the placeholder identifiers reserved in the script template that will be replaced by specific business information. For example, the variables in the evaluation script template include [program name], [number of program types], [total amount], and [channel name]. The final evaluation script refers to the complete textual evaluation opinion generated after filling the business information into the variable positions in the evaluation script template; for example, the final evaluation script generated after filling is: "'High-end Customer Special Marketing Expense Incentive Program' involves 1 program type with a total amount of 1 million yuan. According to the assessment, the expense investment progress under the bank-insurance channel is relatively fast, and it is recommended to pay attention to the catch-up of business targets." The technical solution of this embodiment obtains business plan application data and associated historical data, calculates the status values ​​of multi-dimensional evaluation indicators such as production, deviation, and progress, and determines the status level. Based on preset linkage rules, it performs combined analysis on the status levels of multi-dimensional indicators to generate a comprehensive evaluation result. It matches templates from a preset script rule library and fills in variables to generate the final evaluation script. This solves the problems of traditional evaluation relying on subjective human feedback, isolated evaluation indicators lacking linkage, rigid output methods unable to dynamically generate differentiated content, and lack of dynamic configuration capabilities. It realizes multi-dimensional indicator linkage analysis and automatic generation of differentiated evaluation content, improving the pertinence, operability, and risk warning capabilities of the evaluation results.

[0041] In one alternative approach, S1 specifically includes: Obtain the application data of the business plan to be evaluated. The application data includes the plan identifier, plan type, channel information, budget project information, and cost information.

[0042] The program identifier refers to a code that uniquely identifies a business program instance; for example, the program identifier for the "High-End Customer Special Marketing Expense Incentive Program" is "SX202407001". The program type refers to the category information that classifies the business program according to certain business characteristics; for example, the type of the "High-End Customer Special Marketing Expense Incentive Program" is a "Expense Incentive" program. Channel information refers to the sales or business development channels associated with the business program; for example, the channel information specified for the "High-End Customer Special Marketing Expense Incentive Program" is "Bancassurance Channel". Budget item information refers to the budget accounting item information to which the business program expenses belong; for example, the budget item information corresponding to the expenses of the "High-End Customer Special Marketing Expense Incentive Program" is "Business Promotion Fee". Expense information refers to the amount of capital investment involved in the business program; for example, the expense information applied for by the "High-End Customer Special Marketing Expense Incentive Program" is a total expense of RMB 1 million.

[0043] Based on the scheme identifier, the channel information, and the scheme type, the associated historical data of the business scheme to be evaluated is obtained from the historical business data source.

[0044] Among the above-mentioned optional methods, the specific content scope of the application data and associated historical data is further clarified. Historical data can be accurately extracted through scheme identification, channel information and scheme type, providing a complete and accurate data foundation for multi-dimensional indicator calculation.

[0045] In one alternative approach, S2 specifically includes: Based on the budget project information, the expense information, and the input and output data in the associated historical data, the status value of the production index is calculated.

[0046] Among them, input and output data refers to the historical or current resource consumption and business results values ​​on which the input and output indicators are based; for example, the input and output data used in the calculation include the current cumulative cost input of 850,000 yuan and the current cumulative premium output of 1 million yuan.

[0047] Based on the comparison between the application data and the execution data and historical benchmark data of the current statistical period in the associated historical data, the state value of the deviation index is calculated.

[0048] The execution data for the current statistical period refers to the actual business data that occurred within the current calculation period of the scheme to be evaluated; for example, the execution data for the "High-end Customer Special Marketing Expense Incentive Scheme" during the current statistical period (from the third quarter of this year to the present) is an investment of 850,000 yuan. Historical benchmark data refers to the historical business data of the corresponding period used for comparative analysis; for example, the historical benchmark data used for deviation calculation is the expense investment data of 800,000 yuan for the same period of the third quarter of the previous year.

[0049] Based on the cost information, the budget execution data in the associated historical data, and the business progress data, the status value of the progress indicator is calculated.

[0050] Budget execution data refers to data reflecting the usage of funds under budget items; for example, under the "Business Promotion Fee" budget item of the "High-End Customer Special Marketing Expense Incentive Program," a total of 600,000 yuan of the budget has been used so far this year. Business progress data refers to data reflecting the achievement of business targets; for example, the premium income target associated with the "High-End Customer Special Marketing Expense Incentive Program" has actually been achieved to date, totaling 800,000 yuan.

[0051] Among the above-mentioned optional methods, the calculation basis for production indicators, deviation indicators and progress indicators is further refined. The status values ​​are calculated based on budget project information, cost information, historical input and output data, comparison of execution data with benchmark data and business progress data, so that the indicators can reflect the business status more accurately.

[0052] In one alternative approach, S3 specifically includes: Obtain multiple pre-configured threshold levels for the evaluation metrics of each dimension.

[0053] The status value of the production commissioning indicator is compared with multiple threshold levels configured for the production commissioning indicator to determine the status level of the production commissioning indicator.

[0054] The status level of the production commissioning indicator refers to the qualitative level of the indicator determined by comparing the status value of the production commissioning indicator with the threshold. For example, since the status value of the production commissioning indicator is 0.85, which is lower than the warning value of 0.9, the status level of the production commissioning indicator is determined to be "Level A".

[0055] The status value of the deviation indicator is compared with multiple threshold levels configured for the deviation indicator to determine the status level of the deviation indicator.

[0056] The status level of the deviation indicator refers to the qualitative level of the indicator determined by comparing the status value of the deviation indicator with the threshold. For example, since the status value of the deviation indicator is 0.05, which is between the prompt value of 0.03 and the warning value of 0.08, the status level of the deviation indicator is determined to be "Level B".

[0057] The status value of the progress indicator is compared with multiple threshold levels configured for the progress indicator to determine the status level of the progress indicator.

[0058] The status level of the progress indicator refers to the qualitative level of the indicator determined by comparing the status value of the progress indicator with the threshold. For example, since the status value of the progress indicator is 0.08, which is higher than the warning value of 0.05, the status level of the progress indicator is determined to be "Level C".

[0059] Among the above-mentioned optional methods, a multi-level threshold comparison mechanism is further adopted to compare the status values ​​of production indicators, deviation indicators, and progress indicators with the corresponding preset thresholds, so as to realize the refined classification and judgment of indicator status and provide accurate level input for subsequent linkage analysis.

[0060] In one alternative approach, S4 specifically includes: According to the preset linkage rules, the status level of the production launch indicator, the status level of the deviation indicator, and the status level of the progress indicator are combined into a status level combination.

[0061] Based on the state level combination, a preset mapping table between the state level combination and the comprehensive evaluation result is queried to determine the comprehensive evaluation result of the business solution to be evaluated.

[0062] The mapping table refers to a data table that stores the one-to-one correspondence between state level combinations and comprehensive evaluation results. For example, there is a record in the preset mapping table that indicates that the comprehensive evaluation result corresponding to the state level combination "ABC" is "Class B result".

[0063] In the above-mentioned optional methods, the three-dimensional indicator status levels are further combined into a status level combination by using preset linkage rules, and the comprehensive evaluation result is determined by querying the mapping relationship table, so as to realize the rule-based and standardized judgment of multi-indicator linkage in complex business scenarios.

[0064] In one alternative approach, S5 specifically includes: The preset dialogue rule library is queried based on the comprehensive evaluation results.

[0065] Based on the preset mapping relationship between the comprehensive evaluation results and evaluation script templates stored in the preset script rule base, the evaluation script template corresponding to the comprehensive evaluation result is obtained.

[0066] Among them, the preset mapping relationship refers to the corresponding association between the comprehensive evaluation results and the evaluation script templates stored in the preset script rule base; for example, the script rule base presets the mapping relationship between "Class B result" and a specific evaluation script template.

[0067] In the above-mentioned optional methods, a preset script rule library is further queried based on the comprehensive evaluation results, and the corresponding evaluation script template is automatically matched using the preset mapping relationship to realize the rapid association between the evaluation results and the output content, thereby improving the automation level of script generation.

[0068] In one optional approach, the business information includes: basic solution information, financial limit information, and business organization information; S6 specifically includes: Extract the basic information of the business plan to be evaluated, financial information, and business organization information from the application data.

[0069] The basic information of the plan refers to information describing the core attributes of the business plan; for example, the basic information extracted from the application data includes the plan name "High-end Customer Special Marketing Expense Incentive Plan" and the plan type "Expense Incentive". The financial quota information refers to information describing the scale of funds involved in the business plan and its budget composition; for example, the extracted financial quota information includes the overall plan amount "1 million yuan" and the budget item "Business Promotion Fee". The business organization information refers to information describing the organizations or channels involved in the execution of the business plan; for example, the extracted business organization information includes the channel "Bank Insurance Channel" and the applying department "Marketing Department".

[0070] Fill the corresponding variable positions in the evaluation script template with the basic information of the plan, the financial limit information, and the business organization information.

[0071] Among them, variable position refers to the specific text position where the variable placeholder is located in the evaluation script template; for example, in the template text "[Solution Name] involves...", the position of the string "[Solution Name]" is a variable position.

[0072] Based on the filled-in evaluation script template, the final evaluation script for the business solution to be evaluated is generated.

[0073] The filled evaluation script template refers to the complete text formed by substituting specific business information into all variable positions of the evaluation script template, without any placeholders. For example, after substituting "Special Marketing Expense Incentive Program for High-end Customers" into the [Program Name] variable position of the template, this part of the text becomes "Special Marketing Expense Incentive Program for High-end Customers involves...".

[0074] Among the above-mentioned optional methods, basic information on the plan, financial quota information, and business organization information are further extracted from the application data. Specific business elements are then filled into the variable positions of the evaluation script template, so that the final generated script fits the actual business scenario and enhances the relevance of the evaluation content.

[0075] In the technical solution of this embodiment, it should be noted that: The foundation for generating evaluation scripts lies in various flexibly configurable thresholds. Threshold configuration is achieved through a dedicated configuration menu, with functions including creating, deleting, importing, and exporting. Available filtering criteria cover fields such as account set, company, period range, channel, scheme type I, scheme type II, and status. Data permissions are controlled based on user roles, and numerical units and decimal places are typically standardized to four decimal places. Specifically, it includes multiple independent threshold configuration entry points, such as the "Scheme Deviation Value Threshold Configuration" menu for setting deviation judgment standards, the "Progress Threshold Configuration" menu for setting progress matching standards, the "Scheme Previous Year's Average Threshold Configuration" menu for providing historical reference benchmarks, and the "Historical Cumulative Deviation Reference Value Configuration" menu. These pre-configured thresholds form the benchmark for subsequent indicator status level determination.

[0076] The ABCDE calculation logic for scheme evaluation is the core processing step in script generation. For example... Figure 2 As shown, when a single application form is submitted, the data is split and calculated based on the combination of "company, channel, and application type I" and the corresponding minimum statistical period. This process triggers the generation of four evaluation results: A, B, C, and D. Figure 3 This further illustrates the process of determining the correlation between these multi-dimensional indicators. Meanwhile, as... Figure 4 As shown, this embodiment will also split the data based on the combination of "organization, channel, budget project" and match the minimum statistical period, which will trigger the generation of Class E evaluation results.

[0077] The specific evaluation indicators and calculation rules used in the calculation process are clearly defined in Table 1. Key indicators include: Cumulative applications for production in the current month (CA), which involves the K value (cumulative applications for input in the current month) and the L value (cumulative applications for output in the current month) in the underlying data 1; Production assignment of the organization (CB), which is directly derived from the scheme production ratio threshold setting table; Average value of the same period last year (CC), which is derived from the scheme historical average threshold configuration table; Cumulative applications for production from January to present (CD), which involves the B value (cumulative applications for input in the current year) and the C value (cumulative applications for output in the current year) in the underlying data 1; Production in the same period last year (CE), which is derived from the D value in the underlying data 2; Cumulative deviation of the previous year (CF), which is derived from the newly added indicator Z; Current year expense usage progress (CG), which is calculated based on the total budget and balance under the three dimensions of company, channel, and budget project; Premium progress (CH), which is calculated based on the cumulative minimum monthly actual premium and the annual premium target. The status value calculation of these indicators depends on the underlying data.

[0078] Table 1: The underlying data used in the calculation of the above indicators comes from a structured general basic data table. As shown in Table 2, the general basic table defines the core filtering dimensions and a series of calculation labels. The filtering dimensions include organization, channel, year, and scheme type I and scheme type II. The calculation labels cover multiple fields from A to Z, corresponding to fields such as annual cumulative application count (A), annual cumulative application input (B), annual cumulative application output (C), annual cumulative application production (D), as well as various fulfillment data, deviation data, and historical data. For example, label M corresponds to the cumulative application production for the current month, calculated using K / L; label D corresponds to the annual cumulative application production, calculated using B / C; and label Z corresponds to the monthly summation average of the annual production deviation. This table is the original data source for calculating the status values ​​of each indicator in Table 1.

[0079] Table 2: After completing the indicator calculation and status level determination, the multi-dimensional evaluation results are mapped to specific evaluation statements using predefined rules. For example... Figure 5 The ABCDE dialogue matching rule table shown allows business parties to define and edit the table, listing evaluation dialogue templates corresponding to various combinations of indicator status levels, ensuring the differentiation and targeting of the output content.

[0080] The generation of the final script requires referencing a large amount of specific business numerical data and textual information. Table 3, the script assignment table for scheme evaluation, details the numerical values, codes, and their sources required for script generation. These values ​​are categorized into indicator values ​​(e.g., CA, CB, CC), process values ​​(e.g., CB1, CB2), document values ​​(e.g., DA, DB), value lists (e.g., DH, DE), and script result matching values ​​(e.g., DI, DJ, DK). For example, DA represents the processed department name of this scheme, DD represents the total amount of this scheme and requires unit conversion based on the amount, and DI represents the combined ABCDE script content. This table clarifies the display format and requirements of these values ​​in the final script.

[0081] Table 3:

[0082] The final presentation of the script follows a structured logic of combination and assembly. Table 4 details the presentation rules, examples, and internal judgment logic of the solution evaluation script. The presentation content is divided into two main sections: "Basic Solution Information" and "Solution Evaluation." The Basic Solution Information section displays the solution department, name, number of solution types involved, and total amount. The Solution Evaluation section unfolds hierarchically according to company, channel, budget item, and solution type I. For multi-channel scenarios, the evaluation content is presented sequentially by channel; for multiple budget items, the budget balance of each item is listed; for multiple solution types I, the "Production and Deviation Aspects" evaluation script for each type is displayed separately (referencing the ABCD combination result DJ), and the "Cost and Progress Aspects" evaluation of all relevant items is combined and displayed (referencing the E result DK). The script assembly rules, font styles, monetary unit conversions, and conditional display logic (e.g., only displaying items with abnormal progress) are all clearly defined in the rules, thus generating a final evaluation script text that is clearly structured, informationally complete, and highly targeted.

[0083] Table 4: Figure 6 This diagram illustrates the structure of an embodiment of a speech generation system 200 based on multi-dimensional indicator states provided by the present invention. Figure 6 As shown, the speech generation system 200 based on multi-dimensional indicator states includes: The acquisition module 201 is used to acquire the application data and associated historical data of the business plan to be evaluated; The calculation module 202 is used to calculate the status values ​​of multiple dimensions of evaluation indicators based on the application data and the associated historical data. The multiple dimensions of evaluation indicators include at least production indicators, deviation indicators and progress indicators. The comparison module 203 is used to compare the status value of the evaluation index of each dimension with the pre-configured threshold of the evaluation index of each dimension, and determine the status level of the evaluation index of each dimension respectively. Analysis module 204 is used to perform a linkage combination analysis on the status levels of the evaluation indicators of the multiple dimensions according to the preset linkage rules, and generate a comprehensive evaluation result of the business solution to be evaluated. The preset linkage rules are used to define the mapping relationship between the status level combinations of different dimension indicators and different comprehensive evaluation results. Matching module 205 is used to match the corresponding evaluation script template from the preset script rule library based on the comprehensive evaluation result; The generation module 206 is used to fill in the variables in the evaluation script template according to the business information in the application data, and generate the final evaluation script for the business plan to be evaluated.

[0084] In one alternative embodiment, the acquisition module 201 is specifically used for: Obtain the application data of the business plan to be evaluated, wherein the application data includes plan identifier, plan type, channel information, budget project information and cost information; Based on the scheme identifier, the channel information, and the scheme type, the associated historical data of the business scheme to be evaluated is obtained from the historical business data source.

[0085] In an alternative embodiment, the computing module 202 is specifically used for: Based on the budget project information, the expense information, and the input and output data in the associated historical data, calculate the status value of the input-output indicator; Based on the comparison between the application data and the execution data of the current statistical period and the historical benchmark data in the associated historical data, the status value of the deviation index is calculated; Based on the cost information, the budget execution data in the associated historical data, and the business progress data, the status value of the progress indicator is calculated.

[0086] In an alternative embodiment, the comparison module 203 is specifically used for: Obtain multiple pre-configured threshold levels for the evaluation metrics of each dimension; The status value of the production commissioning indicator is compared with multiple threshold levels configured for the production commissioning indicator to determine the status level of the production commissioning indicator; The state value of the deviation indicator is compared with multiple threshold levels configured for the deviation indicator to determine the state level of the deviation indicator; The status value of the progress indicator is compared with multiple threshold levels configured for the progress indicator to determine the status level of the progress indicator.

[0087] In an alternative embodiment, the analysis module 204 is specifically used for: According to the preset linkage rules, the status level of the production launch indicator, the status level of the deviation indicator, and the status level of the progress indicator are combined into a status level combination; Based on the state level combination, a preset mapping table between the state level combination and the comprehensive evaluation result is queried to determine the comprehensive evaluation result of the business solution to be evaluated.

[0088] In an alternative embodiment, the matching module 205 is specifically used for: Based on the comprehensive evaluation results, query the preset dialogue rule library; Based on the preset mapping relationship between the comprehensive evaluation results and evaluation script templates stored in the preset script rule base, the evaluation script template corresponding to the comprehensive evaluation result is obtained.

[0089] In one optional approach, the business information includes: basic scheme information, financial limit information, and business organization information; the generation module 206 is specifically used for: Extract the basic information of the business plan to be evaluated, financial information, and business organization information from the application data; Fill the corresponding variable positions in the evaluation script template with the basic information of the plan, the financial limit information, and the business organization information; Based on the filled-in evaluation script template, the final evaluation script for the business solution to be evaluated is generated.

[0090] It should be noted that the beneficial effects of the multi-dimensional indicator state-based speech generation system 200 provided in the above embodiments are the same as those of the multi-dimensional indicator state-based speech generation method described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0091] The multi-dimensional indicator state-based speech generation system 200 of the present invention can be a computer program (including program code) running on a computer device. For example, the multi-dimensional indicator state-based speech generation system 200 of the present invention is an application software that can be used to execute the corresponding steps in the multi-dimensional indicator state-based speech generation method of the present invention.

[0092] In some embodiments, the speech generation system 200 based on multi-dimensional indicator states of the present invention can be implemented in a combination of hardware and software. As an example, the speech generation system 200 based on multi-dimensional indicator states of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the speech generation method based on multi-dimensional indicator states of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0093] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0094] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned methods for generating speech based on multi-dimensional indicator states. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the speech generation method based on multi-dimensional indicator states shown in any embodiment of the present invention by calling the computer program.

[0095] In one alternative embodiment, an electronic device is provided, such as Figure 7 As shown, Figure 7 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0096] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0097] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0098] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0099] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0100] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0101] It should be noted that, Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0102] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned speech generation methods based on multi-dimensional indicator states.

[0103] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0104] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned speech generation method based on multi-dimensional indicator states.

[0105] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0107] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0108] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0109] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0110] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0111] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0112] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for generating dialogue based on multi-dimensional indicator states, characterized in that, include: Obtain application data and related historical data for the business proposals to be evaluated; Based on the application data and the associated historical data, the status values ​​of multiple dimensions of evaluation indicators are calculated. The multiple dimensions of evaluation indicators include at least production indicators, deviation indicators and progress indicators. The status value of the evaluation indicator for each dimension is compared with the pre-configured threshold for the evaluation indicator for each dimension to determine the status level of the evaluation indicator for each dimension. According to the preset linkage rules, the status levels of the evaluation indicators of the multiple dimensions are analyzed by linkage combination to generate a comprehensive evaluation result of the business solution to be evaluated. The preset linkage rules are used to define the mapping relationship between the status level combinations of different dimension indicators and different comprehensive evaluation results. Based on the comprehensive evaluation results, the corresponding evaluation script template is matched from the preset script rule library; Based on the business information in the application data, the variables in the evaluation script template are filled in to generate the final evaluation script for the business plan to be evaluated.

2. The speech generation method based on multi-dimensional indicator states according to claim 1, characterized in that, The steps for obtaining the application data and associated historical data of the business plan to be evaluated include: Obtain the application data of the business plan to be evaluated, wherein the application data includes plan identifier, plan type, channel information, budget project information and cost information; Based on the scheme identifier, the channel information, and the scheme type, the associated historical data of the business scheme to be evaluated is obtained from the historical business data source.

3. The speech generation method based on multi-dimensional indicator states according to claim 2, characterized in that, The step of calculating the status values ​​of multiple evaluation indicators based on the application data and the associated historical data includes: Based on the budget project information, the expense information, and the input and output data in the associated historical data, calculate the status value of the input-output indicator; Based on the comparison between the application data and the execution data of the current statistical period and the historical benchmark data in the associated historical data, the status value of the deviation index is calculated; Based on the cost information, the budget execution data in the associated historical data, and the business progress data, the status value of the progress indicator is calculated.

4. The speech generation method based on multi-dimensional indicator states according to claim 3, characterized in that, The step of comparing the state value of the evaluation indicator for each dimension with the pre-configured threshold for each dimension's evaluation indicator to determine the state level of each dimension's evaluation indicator includes: Obtain multiple pre-configured threshold levels for the evaluation metrics of each dimension; The status value of the production commissioning indicator is compared with multiple threshold levels configured for the production commissioning indicator to determine the status level of the production commissioning indicator; The state value of the deviation indicator is compared with multiple threshold levels configured for the deviation indicator to determine the state level of the deviation indicator; The status value of the progress indicator is compared with multiple threshold levels configured for the progress indicator to determine the status level of the progress indicator.

5. The speech generation method based on multi-dimensional indicator states according to claim 4, characterized in that, The step of performing a combined analysis of the status levels of the multiple evaluation indicators according to preset linkage rules to generate a comprehensive evaluation result for the business solution to be evaluated includes: According to the preset linkage rules, the status level of the production launch indicator, the status level of the deviation indicator, and the status level of the progress indicator are combined into a status level combination; Based on the state level combination, a preset mapping table between the state level combination and the comprehensive evaluation result is queried to determine the comprehensive evaluation result of the business solution to be evaluated.

6. The speech generation method based on multi-dimensional indicator states according to any one of claims 1 to 5, characterized in that, The step of matching the corresponding evaluation script template from the preset script rule base based on the comprehensive evaluation result includes: Based on the comprehensive evaluation results, query the preset script rule library; Based on the preset mapping relationship between the comprehensive evaluation results and evaluation script templates stored in the preset script rule base, the evaluation script template corresponding to the comprehensive evaluation result is obtained.

7. The speech generation method based on multi-dimensional indicator states according to claim 6, characterized in that, The business information includes: basic plan information, financial limit information, and business organization information; the step of filling in the variables in the evaluation script template based on the business information in the application data to generate the final evaluation script for the business plan to be evaluated includes: Extract the basic information of the business plan to be evaluated, financial information, and business organization information from the application data; Fill the corresponding variable positions in the evaluation script template with the basic information of the plan, the financial limit information, and the business organization information; Based on the filled-in evaluation script template, the final evaluation script for the business solution to be evaluated is generated.

8. A script generation system based on multi-dimensional indicator states, characterized in that, include: The acquisition module is used to acquire application data and associated historical data of the business solutions to be evaluated; The calculation module is used to calculate the status values ​​of multiple evaluation indicators based on the application data and the associated historical data. The multiple evaluation indicators include at least production indicators, deviation indicators and progress indicators. The comparison module is used to compare the status value of the evaluation indicator for each dimension with the pre-configured threshold for the evaluation indicator for each dimension, and determine the status level of the evaluation indicator for each dimension respectively. The analysis module is used to perform a combined analysis of the status levels of the evaluation indicators of the multiple dimensions according to the preset linkage rules, and generate a comprehensive evaluation result of the business solution to be evaluated. The preset linkage rules are used to define the mapping relationship between the status level combinations of different dimension indicators and different comprehensive evaluation results. The matching module is used to match the corresponding evaluation script template from the preset script rule library based on the comprehensive evaluation result; The generation module is used to fill in the variables in the evaluation script template according to the business information in the application data, and generate the final evaluation script for the business plan to be evaluated.

9. An electronic device, characterized in that, The electronic device includes a processor coupled to a memory, the memory storing at least one computer program, which is loaded and executed by the processor to enable the electronic device to implement the speech generation method based on multidimensional indicator states as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which, when executed by a processor, implements the speech generation method based on multidimensional indicator states as described in any one of claims 1 to 7.

Images