Data trend integration display analysis method and system based on large model

Abstract

The present invention provides a data trend integration, display and analysis method and system based on a big model, which belongs to the field of data processing technology, and specifically includes: according to the data volume of different potential processing data in the associated business types and the data volume of business data that does not need advance data processing, when it is determined that there is no associated business type whose data processing difficulty coefficient does not meet the requirements, historical call data of different associated business types are obtained, and the advance data processing method of the potential processing data is determined in combination with the data processing difficulty coefficients of different associated business types; when the calling user performs call processing of the business type, the business data and the big model are used to perform integrated display processing of the data trends of different business types; whether it is necessary to perform advance data processing on the business data of the business type is determined by the data processing situation of the integrated display processing, thereby improving the efficiency of the integrated display analysis of the data trend.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to a method and system for integrating, displaying and analyzing data trends based on a large model. Background Art

[0002] Each department of the company will have different degrees of data needs. Due to data security and technical considerations, not everyone can directly obtain the data they want. The existing working model is: business personnel initiate demand, development docking, scheduling, and completion of development. The entire process takes a long time, consumes manpower and material resources, and causes business personnel to wait for a long time.

[0003] In order to improve the efficiency and effect of data analysis, in the patent application CN202010739323.8 "Data Analysis Method, Device, Computer Equipment and Storage Medium", according to the task request sent by the user device, the task type associated with the task request is queried to determine the object to be analyzed corresponding to the task request, so as to achieve unified and effective management of different user types. However, the above technical solution has the following problems:

[0004] In the process of data analysis and processing, such as the trend analysis of non-performing loan rates, credit application data, and collection rates, due to the differences in the types of data involved, there are certain differences in the difficulty of analyzing and processing different business types. If it is not possible to determine whether it is necessary to pre-process business data of different data types based on the difficulty of data processing of different business types, it may lead to the data processing time of the large model being difficult to meet the requirements when integrating and displaying data trends.

[0005] In response to the above technical problems, the present invention provides a method and system for integrating, displaying and analyzing data trends based on a large model. Summary of the invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] According to one aspect of the present invention, a method for integrating, displaying and analyzing data trends based on a large model is provided.

[0008] A data trend integration, display and analysis method based on a large model, specifically comprising:

[0009] S1 determines the data volume of business data of a specific data type, and determines potential processing data in the business data based on the change in the data volume;

[0010] S2 takes the business type corresponding to the potential processing data as the associated business type, and according to the different data volumes of the potential processing data in the associated business type and the data volumes of the business data that do not need to be processed in advance, when it is determined that there is no associated business type whose data processing difficulty coefficient does not meet the requirements, proceeds to the next step;

[0011] S3 obtains historical call data of different associated business types, and determines the advance data processing method of the potential processing data in combination with the data processing difficulty coefficients of different associated business types;

[0012] S4 When the calling user performs a business type call processing, the business data and the big model are used to integrate and display the data trends of different business types, and the data processing situation of the integrated display processing is used to determine whether the business data of the business type needs to be processed in advance.

[0013] The beneficial effects of the present invention are:

[0014] The advance data processing method of potential processing data is determined based on the historical call data and data processing difficulty coefficients of different associated business types. This takes into account the differences in the impact of different associated business types on calls due to differences in call data when there are abnormal call delays. At the same time, by further combining the data processing difficulty coefficients of the associated business types, a comprehensive evaluation of the differences in the probabilities of abnormal call delays of different associated business types is achieved, which also lays the foundation for further targeted determination of the advance data processing method of potential processing data.

[0015] Business data and large models are used to integrate and display data trends of different business types, so that data trends of different business types can be integrated and displayed in real time and targeted based on user needs. This not only reduces the difficulty of data analysis and processing, but also improves the accuracy and intuitiveness of data analysis and processing through intuitive display and processing.

[0016] A further technical solution is that the data volume of the business data of the data type is determined according to the parsing result of the storage data of the business data of the data type.

[0017] A further technical solution is that the data volume change includes the new data volume of the business data on different dates.

[0018] A further technical solution is that the method for determining the potential processing data in the business data is:

[0019] Determine, according to the data volume of the business data of the data type, a threshold value of the amount of new data of the business data of the data type on different dates;

[0020] Determine the amount of new data of the business data on different dates based on the data change of the business data, and use the new data amount threshold to determine the date when the amount of new data is greater than the new data amount threshold, and use it as the data amount change date;

[0021] Whether the business data is potential processing data is determined according to the number of data volume change dates.

[0022] A further technical solution is that the newly added data volume threshold is determined according to a preset data volume threshold corresponding to the data volume of the business data of the data type.

[0023] A further technical solution is to determine whether it is necessary to perform advance data processing on the business data of the business type, specifically including:

[0024] Based on the data processing status of the business type in the integrated display processing, determining the data processing duration of the business type in different integrated display processing times;

[0025] The number of integrated display processing times for which the data processing time does not meet the requirements is taken as the number of delayed processing times, and whether it is necessary to perform early data processing on the business data of the business type is determined based on the number of delayed processing times.

[0026] A further technical solution is to determine whether it is necessary to perform advance data processing on the service data of the service type according to the number of delayed processing times, specifically including:

[0027] When the number of delayed processing times is greater than a preset delay number threshold, it is determined that advance data processing is required for the service data of the service type.

[0028] A further technical solution is that, when it is necessary to perform advance data processing on the service data of the service type, all the service data in the service type are processed in advance.

[0029] On the other hand, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned large-model-based data trend integration, display and analysis method when running the computer program.

[0030] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0033] Figure 1 It is a flow chart of a data trend integration display and analysis method based on a large model;

[0034] Figure 2 is a flow chart of a method for determining potential processing data in business data;

[0035] Figure 3 is a flow chart of a method for determining a data processing difficulty coefficient associated with a business type;

[0036] Figure 4 is a flow chart of a method for determining an advance data processing manner of potentially processing data;

[0037] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0038] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0039] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0040] The big model represents an opportunity for an industrial revolution, which will greatly improve productivity and production efficiency. As a new generation of productivity tools, the big model has unprecedented understanding, reasoning and planning capabilities. From the company's perspective, each department of the company will have different degrees of data needs. Based on data security and technical considerations, not everyone can directly obtain the desired data, so the company's current working model is: business personnel initiate demand, development docking, scheduling, and completion of development. The entire process takes a long time and consumes manpower and material resources. In order to solve this problem, reduce the waiting time of business personnel, and save developers redundant work, we develop and deploy a private general big model. By combining the intelligent body framework with the company's digital business, we build an internal data integration system for the company. This system directly displays a page to business personnel, and business personnel can obtain the desired data by entering natural language on the page. For example: "Count the loan status of each product in the past year, and require the results to include product name, number of loans, average loan amount, maximum loan amount, and minimum loan amount." The result will not only display the data, but also display the trend of change and text analysis in the form of charts. In addition, database query statements can be generated based on the description. By packaging the big model into a digital human and communicating with the "soulful" digital human, the difficulty of using the big model can be reduced, making AI a digital employee of the enterprise.

[0041] 1. Data visualization: Generating charts can transform complex data into a visual form, making the data easier to understand and interpret. Charts can help companies intuitively present data trends, relationships, and statistical indicators, thereby providing in-depth insights into business issues. Through data visualization, decision makers can more quickly identify problems, develop strategies, and share information with the team.

[0042] 2. Decision support: The big model can provide strong support for decision makers by analyzing data and generating relevant reports. By monitoring and analyzing key indicators, decision makers can timely discover changes in business conditions, market trends, and customer needs in order to make accurate decisions. SQL query statements can be used to extract the required information from huge data sets, providing decision makers with accurate and real-time data support.

[0043] 3. Discover business opportunities: Big models can identify potential business opportunities by analyzing massive amounts of data. By mining the connections and trends between data, companies can discover new market demands, product innovations, or efficiency improvement opportunities. The generated charts and analysis reports can help companies discover business insights hidden behind the data and gain competitive advantages from them.

[0044] 4. Monitoring performance: By using large models to generate charts and execute SQL query statements, the company's performance can be monitored and evaluated in real time. By tracking and analyzing key business indicators, companies can promptly identify problems, formulate improvement measures, and evaluate the completion of performance goals. This helps companies achieve continuous improvement and optimize business processes.

[0045] In short, using big models to generate charts, analysis, and SQL query statements can provide powerful data analysis and decision support capabilities, helping companies better understand data, discover business opportunities, monitor performance, and make accurate decisions. This helps companies improve efficiency, reduce risks, and succeed in a highly competitive market environment.

[0046] In the process of analyzing and processing data trends of business types such as bad debt rate, trend analysis of credit application data, and collection rate, business data of different data types are processed in advance according to the data processing difficulty of different business types, thereby improving the data processing timeliness of the large model when integrating and displaying data trends.

[0047] Potentially processed data: business data whose data volume accounts for 0.05-0.1% of all business data.

[0048] Associated business type: The business type that needs to be called to potentially process data when processing data.

[0049] Data processing difficulty coefficient of associated business types: It is determined based on the total data ratio of different potential processing data and business data that does not require advance data processing in the associated business types. When the total data ratio is 0.6, the data processing difficulty coefficient of the associated business type is 0.6, and data processing difficulty coefficients greater than 0.7 are regarded as associated business types that do not meet the requirements.

[0050] Advance data processing method for potential processing data: Determine the weight coefficients of different related business types based on the proportion of employees who have call permissions for the related business types, and determine the comprehensive difficulty coefficient in combination with the weight of the data processing difficulty coefficient. Determine the advance data processing method for potential processing data based on the range of the comprehensive difficulty coefficient.

[0051] Determine whether it is necessary to perform advance data processing on the business data of the business type through the data processing situation of the integrated display processing: based on the data processing situation of the business type in the integrated display processing, determine the data processing duration of the business type at different integrated display processing times, and use the integrated display processing times for which the data processing time does not meet the requirements as the delayed processing times, and determine whether it is necessary to perform advance data processing on the business data of the business type based on the delayed processing times.

[0052] System implementation process:

[0053] User queries a question -> LangChain formats the user question according to the prompt module -> LangChain generates processing steps according to the configured chains -> executes step by step according to the generated steps -> submits the question and embedded context to the big model to generate an answer -> returns the result to the user.

[0054] Specific implementation process:

[0055] Step 1: Preprocessing of user query questions. When a user initiates a query, LangChain obtains the configuration and user data tags, generates processing steps, and formats the user questions. The user data tags here refer to adding specific tags to database information in combination with the company's business scenarios. Filtering out key information through data tags can greatly reduce the data passed to the LLM (large model), effectively improve the processing speed, and achieve the purpose of reducing costs and increasing efficiency.

[0056] Step 2: Accurately identify and process user questions. LLM further extracts key indicators based on user data tags and questions, accurately locates the scope of questions and related information. Langchain then loads the context (context refers to database-related information) based on the extracted key data tags. Specifically, key indicator extraction includes word segmentation, stop word removal, stem extraction, part-of-speech tagging, synonym replacement, abbreviation and abbreviation mapping, vocabulary processing to prevent model misjudgment, and other steps to resolve user questions to the greatest extent possible.

[0057] Step 3: Generate SQL query statements. Give the above processed standard query questions and loaded context to the big model, and the big model generates SQL. Langchain queries the database based on SQL to obtain relevant data.

[0058] Step 4: Result display. If data analysis is required, LLM is further called to generate a report based on the context and the queried data and displayed on the web. If data analysis is not required, Python is used to process the queried data to generate a dynamic table. Finally, the web displays the SQL statement and related data charts.

[0059] Embodiment 1 To solve the above problem, according to one aspect of the present invention, Figure 1 As shown, a first aspect is provided, and the present invention provides a data trend integration display analysis method based on a large model, specifically comprising:

[0060] S1 determines the data volume of business data of a specific data type, and determines potential processing data in the business data based on the change in the data volume;

[0061] S2 takes the business type corresponding to the potential processing data as the associated business type, and according to the different data volumes of the potential processing data in the associated business type and the data volumes of the business data that do not need to be processed in advance, when it is determined that there is no associated business type whose data processing difficulty coefficient does not meet the requirements, proceeds to the next step;

[0062] S3 obtains historical call data of different associated business types, and determines the advance data processing method of the potential processing data in combination with the data processing difficulty coefficients of different associated business types;

[0063] S4 When the calling user performs a business type call processing, the business data and the big model are used to integrate and display the data trends of different business types, and the data processing situation of the integrated display processing is used to determine whether the business data of the business type needs to be processed in advance.

[0064] Optionally, the data volume of the business data of the data type is determined according to a parsing result of the storage data of the business data of the data type.

[0065] Furthermore, the data volume change includes the new data volume of the business data on different dates.

[0066] Specifically, Figure 2 As shown, the method for determining the potential processing data in the business data is:

[0067] Determine, according to the data volume of the business data of the data type, a threshold value of the amount of new data of the business data of the data type on different dates;

[0068] Determine the amount of new data of the business data on different dates based on the data change of the business data, and use the new data amount threshold to determine the date when the amount of new data is greater than the new data amount threshold, and use it as the data amount change date;

[0069] Whether the business data is potential processing data is determined according to the number of data volume change dates.

[0070] Furthermore, the newly added data volume threshold is determined according to a preset data volume threshold corresponding to the data volume of the business data of the data type.

[0071] Optionally, determining whether the business data is potential processing data according to the number of the data volume change dates specifically includes: when the number of the data volume change dates is within a preset number interval, determining that the business data is potential processing data;

[0072] When the number of the data volume change dates is not within a preset quantity range, it is determined that the business data does not belong to potential processing data.

[0073] It should be noted that, when the business data is potential processing data, it is determined that the business data is business data that potentially requires advance data processing.

[0074] Furthermore, when the business data does not belong to potential processing data, when the number of data volume change dates of the business data is greater than the number of preset change dates, it is determined that the business data belongs to business data that requires advance data processing; when the number of data volume change dates of the business data is not greater than the number of preset change dates, it is determined that the business data belongs to business data that does not require advance data processing.

[0075] In another embodiment, the method for determining the potential processing data in the business data is:

[0076] Acquire the data volume of the business data of the data type;

[0077] Determine the amount of new data of the business data on different dates based on the data change of the business data, and determine the date of data amount change on the date based on the ratio of the amount of new data to the amount of data;

[0078] Whether the business data is potential processing data is determined according to the number of data volume change dates.

[0079] Furthermore, the data volume change date is a date when the ratio of the newly added data volume to the data volume is greater than a preset data volume ratio.

[0080] Optionally, the method for determining the potential processing data in the business data is:

[0081] S11 obtains the data volume of the business data of the data type, and determines the data volume complexity coefficient of the business data according to the data volume of the business data of the data type;

[0082] Optionally, the above step S11 includes the following contents:

[0083] S111 obtains the data volume of the business data of the data type. When the data volume of the business data of the data type is greater than the preset data volume, it is determined that the business data belongs to the business data of advance data processing. When the data volume of the business data of the data type is not greater than the preset data volume, the process proceeds to step S112.

[0084] S112: when the data volume of the business data of the data type is within the preset data volume range, the process proceeds to step S113; when the data volume of the business data of the data type is not within the preset data volume range, the business data is determined to be business data that does not require advance data processing;

[0085] S113 determines the data volume complexity coefficient of the business data according to the data volume of the business data of the data type, and proceeds to step S12.

[0086] S12: determining the amount of new data of the business data on different dates based on the data change of the business data, and determining the data amount change abnormality coefficient of the business data based on the ratio of the amount of new data on different dates to the data amount;

[0087] Optionally, the above step S12 includes the following contents:

[0088] S121 obtains the data volume complexity coefficient of the service data. When the data volume complexity coefficient of the service data is within the preset coefficient interval, the process proceeds to step S122. When the data volume complexity coefficient of the service data is not within the preset coefficient interval, the process proceeds to step S125.

[0089] S122 determines the amount of new data of the business data on different dates based on the data change of the business data, and when there is a date with an amount of new data greater than a preset threshold of the amount of new data, proceeds to step S123; when there is no date with an amount of new data greater than the preset threshold of the amount of new data, proceeds to step S124;

[0090] S123: When the number of dates when the amount of newly added data is greater than the preset data amount threshold does not meet the requirement, it is determined that the business data belongs to business data processed in advance; when the number of dates when the amount of newly added data is greater than the preset data amount threshold meets the requirement, the process proceeds to step S124;

[0091] S124 determines the data change coefficients of different dates based on the amount of newly added data on different dates and the ratio of the amount of newly added data to the amount of data. When the number of dates that do not meet the requirements for the data change coefficient is greater than the number of preset change dates, it is determined that the business data belongs to business data processed in advance. When the number of dates that do not meet the requirements for the data change coefficient is not greater than the number of preset change dates, the process proceeds to step S125.

[0092] S125 determines the data volume change abnormal coefficient of the business data based on the new data volume on different dates and the ratio of the new data volume to the data volume. When the sum of the data volume change abnormal coefficient and the data volume complexity coefficient does not meet the requirements, it is determined that the business data belongs to business data processed in advance. When the sum of the data volume change abnormal coefficient and the data volume complexity coefficient meets the requirements, proceed to step S13.

[0093] S13 determines the comprehensive complexity coefficient of the business data according to the data volume change abnormal coefficient and the data volume complexity coefficient, and uses the comprehensive complexity coefficient to determine whether the business data is potential processing data.

[0094] It should be noted that the associated business type is a business type that needs to call the potential processing data when making a business call.

[0095] Specifically, Figure 3 As shown, the method for determining the data processing difficulty coefficient of the associated business type is:

[0096] Determine the total amount of data of different data types based on the data type of the potential processing data and the data type of the business data that does not require advance data processing;

[0097] According to the total amount of data of different data types, the data types of interest are sorted out among the data types, and the data processing difficulty coefficient of the associated business type is determined using the number of the data types of interest.

[0098] Furthermore, the concerned data type is a data type whose total amount of data is greater than a preset total amount of data.

[0099] Optionally, the data processing difficulty coefficient of the associated business type is determined according to a preset processing difficulty corresponding to the number of the concerned data types.

[0100] In another embodiment, the method for determining the data processing difficulty coefficient of the associated business type is:

[0101] Determine the total amount of data of different data types based on the data type of the potential processing data and the data type of the business data that does not require advance data processing;

[0102] Determine the data volume proportional factors of different data types according to the ratio of the total data volume of different data types to the total data volume corresponding to the associated service type;

[0103] The data processing difficulty coefficient of the associated business type is determined based on the data volume proportional factors of different data types.

[0104] Further, determining the data processing difficulty coefficient of the associated business type based on the data volume ratio factors of different data types specifically includes:

[0105] The data type of interest is determined by the data volume proportional factors of different data types, and the data processing difficulty coefficient of the associated business type is determined by using the weight of the data volume proportional factors of the data type of interest.

[0106] Furthermore, the historical call data includes the personnel who have the calling authority for the associated business type and the historical call times of the personnel who have the calling authority for the associated business type.

[0107] Specifically, Figure 4As shown, the method for determining the advance data processing mode of the potential processing data is:

[0108] Using historical call data of different associated business types, determine the personnel with call authority for the associated business type and use them as the call authority personnel;

[0109] Determine the weight coefficients of different associated business types according to the number of personnel with call authority, and determine the correction difficulty coefficients of different associated business types in combination with the data processing difficulty coefficients of different associated business types;

[0110] The difficulty coefficient evaluation amount of the potential processing data is determined based on the modified difficulty coefficients of different associated business types, and the advance data processing method of the potential processing data is determined according to the difficulty coefficient evaluation amount.

[0111] Furthermore, the advance data processing method of the potential processing data includes no advance data processing and advance data processing.

[0112] Optionally, the method for determining the advance data processing mode of the potential processing data is:

[0113] Obtain the data processing difficulty coefficients of different associated business types. When there is an associated business type whose data processing difficulty coefficient is greater than the preset difficulty coefficient:

[0114] then determining that the advance data processing method of the potential processing data is advance data processing;

[0115] When there is no associated business type whose data processing difficulty coefficient is greater than the preset difficulty coefficient:

[0116] The average values ​​of the data processing difficulty coefficients of different associated business types are determined by using the data processing difficulty coefficients of different associated business types. When the average values ​​of the data processing difficulty coefficients of different associated business types are within a preset coefficient range:

[0117] Acquire the number of associated business types, and when the number of the associated business types is within a preset business number range, determine that the advance data processing mode of the potential processing data is that no advance data processing is required;

[0118] When the number of the associated service types is not within the preset service number range:

[0119] Using historical call data of different associated business types, determine the personnel with call authority for the associated business type, and use them as call authority personnel. When the total number of call authority personnel is within a preset personnel number range, determine that the advance data processing method of the potential processing data does not require advance data processing.

[0120] When the total number of personnel with the call authority is not within the preset personnel number range or the average value of the data processing difficulty coefficients of different associated business types is not within the preset coefficient range:

[0121] Using historical call data of different associated business types, determine the personnel with call authority for the associated business type and use them as the call authority personnel;

[0122] Determine the weight coefficients of different associated business types according to the number of personnel with call authority, and determine the correction difficulty coefficients of different associated business types in combination with the data processing difficulty coefficients of different associated business types;

[0123] The difficulty coefficient evaluation amount of the potential processing data is determined based on the modified difficulty coefficients of different associated business types, and the advance data processing method of the potential processing data is determined according to the difficulty coefficient evaluation amount.

[0124] Furthermore, business data and big models are used to integrate and display data trends of different business types, including:

[0125] Taking the business data as a basis, the big model is used to analyze the data trends of the business type according to the data analysis requirements of the matching business type, and the data trends are integrated and displayed based on the analysis results of the data trends.

[0126] It should also be noted that determining whether to perform advance data processing on the business data of a business type specifically includes:

[0127] Based on the data processing status of the business type in the integrated display processing, determining the data processing duration of the business type in different integrated display processing times;

[0128] The number of integrated display processing times for which the data processing time does not meet the requirements is taken as the number of delayed processing times, and whether it is necessary to perform early data processing on the business data of the business type is determined based on the number of delayed processing times.

[0129] Optionally, determining whether it is necessary to perform advance data processing on the service data of the service type according to the number of delayed processing times specifically includes:

[0130] When the number of delayed processing times is greater than a preset delay number threshold, it is determined that advance data processing is required for the service data of the service type.

[0131] Further, when it is necessary to perform advance data processing on the service data of the service type, advance data processing is performed on all the service data in the service type.

[0132] Example 2 On the other hand, if Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned method of data trend integration, display and analysis based on a large model when running the computer program.

[0133] Optionally, the method for determining the data processing difficulty coefficient of the associated business type is:

[0134] Acquiring the amount of potential processing data in the associated business type, and when the amount of potential processing data of the associated business type does not meet the requirement, determining that the data processing difficulty coefficient of the associated business type does not meet the requirement;

[0135] When the amount of potentially processed data of the associated business type meets the requirement:

[0136] Determining the total amount of potential processing data based on the amount of different potential processing data in the associated business type, and when the total amount of potential processing data does not meet the requirement, determining that the data processing difficulty coefficient of the associated business type does not meet the requirement;

[0137] When the total amount of the potential processed data meets the requirement,

[0138] Determine the potential data processing complexity coefficient of the associated business type based on the number of potential processed data and the data volume of different potential processed data; when the potential data processing complexity coefficient of the associated business type does not meet the requirement, determine that the data processing difficulty coefficient of the associated business type does not meet the requirement;

[0139] When the potential data processing complexity coefficient of the associated business type meets the requirements:

[0140] Determine the total amount of processed data based on the data type of the potential processed data and the data type of the business data that does not require advance data processing, and when the total amount of processed data does not meet the requirement, determine that the data processing difficulty coefficient of the associated business type does not meet the requirement;

[0141] When the total amount of processed data meets the requirements:

[0142] Determine the data volume proportional factors of different data types according to the ratio of the total data volume of different data types to the total data volume corresponding to the associated service type;

[0143] The data processing difficulty coefficient of the associated business type is determined based on the data volume proportional factors of different data types and the total amount of processed data.

[0144] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0145] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0146] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A data trend integration display and analysis method based on a large model, characterized in that: Specifically include: Determine the data volume of business data of a specific data type, and determine potential processing data in the business data based on changes in the data volume; The business type corresponding to the potential processing data is used as the associated business type, and when it is determined that there is no associated business type whose data processing difficulty coefficient does not meet the requirements according to the different data amounts of the potential processing data in the associated business type and the data amount of the business data that does not need to be processed in advance, the next step is entered; Acquire historical call data of different associated business types, and determine the advance data processing method of the potential processing data in combination with the data processing difficulty coefficients of different associated business types; When the calling user performs a business type call processing, the business data and the big model are used to integrate and display the data trends of different business types, and the data processing status of the integrated display processing is used to determine whether the business data of the business type needs to be processed in advance; The advance data processing method of the potential processing data includes no advance data processing and advance data processing; Determine whether advance data processing is required for the business data of the business type, including: Based on the data processing status of the business type in the integrated display processing, determining the data processing duration of the business type in different integrated display processing times; The number of integrated display processing times for which the data processing duration does not meet the requirements is taken as the number of delayed processing times. When the number of delayed processing times is greater than the preset delay number threshold, it is determined that advance data processing is required for the business data of the business type.

2. The data trend integration display and analysis method based on a large model as claimed in claim 1, characterized in that: The data volume of the business data of the data type is determined according to the parsing result of the storage data of the business data of the data type.

3. The data trend integration display and analysis method based on a large model as claimed in claim 1 is characterized in that: The data volume change includes the new data volume of the business data on different dates.

4. The data trend integration display and analysis method based on a large model as claimed in claim 1 is characterized in that: The method for determining the potential processing data in the business data is: Determine, according to the data volume of the business data of the data type, a threshold value of the amount of new data of the business data of the data type on different dates; Determine the amount of new data of the business data on different dates based on the data change of the business data, and use the new data amount threshold to determine the date when the amount of new data is greater than the new data amount threshold, and use it as the data amount change date; Whether the business data is potential processing data is determined according to the number of data volume change dates.

5. The data trend integration display and analysis method based on a large model as claimed in claim 4 is characterized in that: The newly added data volume threshold is determined according to a preset data volume threshold corresponding to the data volume of the business data of the data type.

6. The data trend integration display and analysis method based on a large model as claimed in claim 4 is characterized in that: Determining whether the business data is potential processing data according to the number of data volume change dates specifically includes: When the number of the data volume change dates is within a preset number range, the business data is determined to be potential processing data; When the number of the data volume change dates is not within a preset quantity range, it is determined that the business data does not belong to potential processing data.

7. The data trend integration display and analysis method based on a large model as claimed in claim 1 is characterized in that: When the business data is potential processing data, it is determined that the business data is business data that potentially needs to be processed in advance.

8. The data trend integration display and analysis method based on a large model as claimed in claim 1, characterized in that: The method for determining the advance data processing mode of the potential processing data is: Using historical call data of different associated business types, determine the personnel with call authority for the associated business type and use them as the call authority personnel; Determine the weight coefficients of different associated business types according to the number of personnel with call authority, and determine the correction difficulty coefficients of different associated business types in combination with the data processing difficulty coefficients of different associated business types; The difficulty coefficient evaluation amount of the potential processing data is determined based on the modified difficulty coefficients of different associated business types, and the advance data processing method of the potential processing data is determined according to the difficulty coefficient evaluation amount.

9. A computer system comprising: A memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, a method for integrating, displaying and analyzing data trends based on a large model as described in any one of claims 1 to 8 is executed.

Images