An item data analysis method and device, electronic equipment and storage medium

Abstract

Embodiments of the present disclosure disclose a project data analysis method and device, electronic equipment and storage medium, wherein the method comprises: obtaining an analysis target; obtaining initial data set information; determining an analysis strategy for the analysis target according to the current data set information in a loop; in response to the type of the analysis strategy belonging to data query, querying a data set according to the analysis strategy, and updating the data set information according to the data set; in response to the type of the analysis strategy belonging to data organization, merging the data set, and updating the data set information according to the merged data set; and in response to the type of the analysis strategy belonging to data summary, determining a first analysis result according to the current data set information, and ending the loop. The data analysis effect for the project can be improved, and the project management efficiency is improved.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a project data analysis method, apparatus, electronic device, and storage medium. Background Technology

[0002] In today's data-driven environment, the importance of intelligent data reports in project management processes is becoming increasingly prominent. Currently, the data retrieval logic in the process of analyzing and generating data reports is simplistic, resulting in low accuracy and success rates, failing to meet the needs of in-depth analysis, and ultimately leading to poor project data analysis results and impacting project management efficiency. Summary of the Invention

[0003] This disclosure provides a project data analysis method, apparatus, electronic device, and storage medium, which can improve the data analysis effect for projects and enhance project management efficiency.

[0004] In a first aspect, embodiments of this disclosure provide a project data analysis method, including:

[0005] Obtain the analysis target;

[0006] Obtain initial dataset information;

[0007] The loop determines the analysis strategy for the analysis objective based on the current dataset information.

[0008] In response to the analysis strategy being a data query, the dataset is queried according to the analysis strategy, and the dataset information is updated based on the dataset.

[0009] In response to the analysis strategy being of the type of data organization, the datasets are merged, and the dataset information is updated based on the merged datasets;

[0010] In response to the analysis strategy being of the type of data summary, a first analysis result is determined based on the current dataset information, and the loop ends.

[0011] Secondly, embodiments of this disclosure also provide a project data analysis apparatus, comprising:

[0012] The first acquisition module is used to acquire the analysis target;

[0013] The second acquisition module is used to acquire initial dataset information;

[0014] The decision module is used to cyclically determine the analysis strategy for the analysis target based on the current dataset information;

[0015] The query module is used to respond to the fact that the analysis strategy is a data query, query the dataset according to the analysis strategy, and update the dataset information according to the dataset.

[0016] An organization module is used to merge the datasets in response to the analysis strategy being of the type of data organization, and to update the dataset information based on the merged datasets;

[0017] The analysis module is used to determine a first analysis result based on the current dataset information in response to the analysis strategy being of the type of data summary, and then end the loop.

[0018] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0019] One or more processors;

[0020] Storage device for storing one or more programs.

[0021] When the one or more programs are executed by the one or more processors, the one or more processors implement the project data analysis method as described in any embodiment of this disclosure.

[0022] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the project data analysis method as described in any of the embodiments of this disclosure.

[0023] Fifthly, this disclosure also provides a computer program product, characterized in that the computer program product includes a computer program, which, when executed by a processor, implements the project data analysis method as described in any of the embodiments of this disclosure.

[0024] In the technical solution of this disclosure embodiment, an analysis target can be obtained; initial dataset information can be obtained; an analysis strategy for the analysis target can be determined cyclically based on the current dataset information; in response to the analysis strategy being a data query, the dataset is queried according to the analysis strategy, and the dataset information is updated according to the dataset; in response to the analysis strategy being a data organization, the dataset is merged, and the dataset information is updated according to the merged dataset; in response to the analysis strategy being a data summary, a first analysis result is determined based on the current dataset information, and the loop ends.

[0025] By iteratively determining the next analysis strategy based on the current dataset information, this system can perform dataset queries when the current dataset is insufficient to analyze the target; merge related datasets when they need to be combined; and analyze the target based on the current dataset when it is sufficient. This enables multiple, dynamic data retrieval and merging, improving data retrieval accuracy and success rate, enhancing the effectiveness of project data analysis, and improving project management efficiency. Furthermore, it can deepen data queries when there is a need for in-depth data analysis, further improving the overall effectiveness of project data analysis. Attached Figure Description

[0026] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0027] Figure 1 A flowchart illustrating a project data analysis method provided in an embodiment of this disclosure;

[0028] Figure 2 This is a schematic diagram of the process of querying a dataset in a project data analysis method provided in this embodiment of the disclosure;

[0029] Figure 3 This is a schematic block diagram of the data flow of a project data analysis method provided in an embodiment of the present disclosure;

[0030] Figure 4 This is a schematic block diagram of the data flow of a project data analysis method provided in an embodiment of the present disclosure;

[0031] Figure 5 This is a schematic diagram of the structure of a project data analysis device provided in an embodiment of the present disclosure;

[0032] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0033] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0034] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0035] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0036] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0037] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0038] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0039] Figure 1 This is a flowchart illustrating a project data analysis method provided in an embodiment of this disclosure. This disclosure is applicable to data analysis of projects, such as the generation of intelligent data reports. The method can be executed by a project data analysis device, which can be implemented in software and / or hardware and can be configured in an electronic device, such as a computer device.

[0040] like Figure 1 As shown, the project data analysis method provided in this embodiment may include:

[0041] S110. Obtain the analysis target.

[0042] In this embodiment of the disclosure, the analysis objective can refer to the data analysis objective of the project and can be represented in text form. For example, the analysis objective can include content such as "comparison of total input for each project," "comparison of per capita output for each project," and "input trends for each project." The analysis objective can be received from user input via a preset interface, or it can be automatically generated based on preset information. Automatically generating the analysis objective based on preset information may include, for example, generating the analysis objective based on the data report topic.

[0043] S120. Obtain the initial dataset information.

[0044] In this embodiment of the disclosure, dataset information may include, but is not limited to, datasets, dataset status, and relationships between datasets. A dataset can refer to a collection of data and can be represented in the form of a data table. The dataset status can include normal and abnormal, and can be determined based on the data within the dataset. For example, if there is missing or abnormal data within the dataset, the dataset status can be determined to be abnormal; if the data within the dataset is complete and normal, the dataset status can be determined to be normal. The relationships between datasets can include related and unrelated relationships. If datasets are related, it can be considered that there is a need to merge them; if datasets are unrelated, it can be considered that there is no need to merge them.

[0045] The initial dataset information can be empty. The initial dataset information can be obtained through existing initialization statements. The dataset information can be updated based on subsequent operations.

[0046] S130. Based on the current dataset information, determine the analysis strategy for the analysis target.

[0047] In this embodiment of the disclosure, the next action (i.e., analysis strategy) can be determined cyclically based on the current dataset information for the analysis target. The types of analysis strategies can include data querying, data organization, and data summarization. The analysis strategy determined based on the current dataset information typically includes one type.

[0048] The analysis strategy can be represented in text form and may include the type of analysis strategy, specific analysis actions, and the reasons for determining the analysis strategy. For example, an analysis strategy might include content such as "perform data queries by project dimension, including but not limited to: ×× data; the current dataset is empty and has no preceding analysis steps, so it is necessary to prioritize obtaining basic data to support the analysis objectives." As the example shows, in the first loop, the current dataset information is the initial dataset information, such as being empty. At this time, the typically determined analysis strategy is data querying to obtain basic data to support the analysis objectives.

[0049] This involves determining the next analysis strategy based on the current dataset information, either through preset rules and templates or by using a completed neural network model. By dynamically determining the analysis strategy, the system can supplement the dataset when it is insufficient to analyze the target; merge datasets when they are correlated to aid in project data analysis; and analyze the target when the dataset is sufficient to obtain the initial analysis results. Furthermore, it allows for dataset queries to investigate anomalies in the current dataset, or to retrieve necessary detailed data by querying key points of interest within existing datasets. By enhancing the depth of data queries when there are anomalies or points of interest in the dataset, and supporting in-depth data analysis, the effectiveness of project data analysis can be further improved.

[0050] In some alternative implementations, after determining the analysis strategy for the analysis target, the process may further include: determining the verification result of the analysis strategy based on the current dataset information and the analysis strategy; and, in response to a successful verification result, performing subsequent steps according to the type of the analysis strategy.

[0051] The feasibility and rationality of the analysis strategy can be verified using a completed neural network model (e.g., a language model). For example, prompt words for the language model can be constructed based on the current dataset information and the analysis strategy, allowing the language model to output whether the analysis strategy is feasible and necessary. When the analysis strategy is feasible and rational, the verification result is considered passed. Subsequent steps can then be executed according to the strategy type. When the analysis strategy is not feasible and / or not rational, the verification result is considered failed. In this case, the analysis strategy can be regenerated and verified until it passes, allowing subsequent steps to be executed according to the strategy type.

[0052] Among these optional implementation methods, verifying the analysis strategy can ensure its feasibility and rationality, which helps to improve the effectiveness of project data analysis.

[0053] S141. The response to the analysis strategy is a data query, which queries the dataset according to the analysis strategy and updates the dataset information accordingly.

[0054] When the analysis strategy falls under the category of data query, the dataset can be queried based on the specific analysis actions within the strategy. For example, a dataset can be queried based on the query parameters carried over to the analysis action. Furthermore, the dataset information can be updated based on the retrieved dataset. For instance, the retrieved dataset can be added to the dataset information set. Alternatively, the dataset status and / or inter-dataset relationships in the dataset information can be updated based on the retrieved dataset.

[0055] In response to updates to the dataset information, the loop can proceed to the next iteration, where the analysis strategy for the analysis objective is determined again based on the current dataset information (i.e., the updated dataset information). An upper limit can be preset for the number of data query rounds to constrain the total time consumed in the project's data analysis process.

[0056] S142. The response to the analysis strategy belongs to data organization, which merges the datasets and updates the dataset information based on the merged dataset.

[0057] When the analysis strategy falls under the category of data organization, dataset merging can be performed based on the specific analysis actions within the strategy. This dataset merging can include: writing code statements that can be executed in an in-memory database engine, such as Structured Query Language (SQL) code, based on the datasets and specific merging operations given in the analysis actions; and running the code statements through the in-memory database engine to achieve the association and merging of datasets.

[0058] In response to dataset merging, the dataset information can be updated based on the merged dataset. For example, existing datasets in the dataset information can be updated based on the merged dataset. Similarly, the dataset status and / or inter-dataset relationships in the dataset information can be updated based on the merged dataset. Likewise, in response to the update of the dataset information, the next loop can begin, and the analysis strategy for the analysis objective can be determined again based on the current dataset information (i.e., the updated dataset information).

[0059] In this embodiment of the disclosure, steps S141 and S142 can be executed intermittently. For example, after executing step S141, if the queried dataset is related to an existing dataset, the determined next analysis strategy can be a data organization type, and step S142 can then be executed; after executing step S142, if the dataset is still insufficient to analyze the analysis target, the determined next analysis strategy can be a data query type, and step S141 can then be executed. Typically, step S142 can be executed intermittently during multiple rounds of executing step S141.

[0060] S143. In response to the analysis strategy being of the type of data summary, determine the first analysis result based on the current dataset information and end the loop.

[0061] When the dataset is sufficient to analyze the target, or when the upper limit of data query rounds is reached, the determined analysis strategy can be a data summarization type. In this case, based on the specific analysis actions in the analysis strategy, the dataset in the current dataset information can be analyzed and summarized to obtain the first analysis result. For example, the dataset can be analyzed and summarized based on the analysis target carried in the analysis action. The loop can end upon obtaining the first analysis result of the analysis target.

[0062] In some optional implementations, updating the dataset information based on the dataset may include: analyzing the dataset to obtain a second analysis result; and updating the dataset information based on the dataset and the second analysis result.

[0063] The dataset can be analyzed along a first preset dimension to obtain a second analysis result. This first preset dimension may include, for example, a query result dimension and an analysis target dimension. Analyzing the dataset along the query result dimension may include: analyzing the completeness of the currently queried dataset, identifying failed parts of the query, and analyzing the reasons for the failures. Analyzing the dataset along the analysis target dimension may include: a brief analysis of the analysis target based on the currently queried dataset.

[0064] Updating the dataset information based on the second analysis result can include: updating the dataset status in the dataset information based on the second analysis result of the query result dimension; and storing the second analysis result of the analysis target dimension in the dataset information. Correspondingly, determining the first analysis result based on the current dataset information can include: analyzing and summarizing the dataset and the second analysis result in the current dataset information according to the analysis target to obtain the first analysis result.

[0065] Among these optional implementation methods, analyzing the dataset and updating the dataset information based on the second analysis results can provide a reference for determining the next round of analysis strategies, which helps to improve the rationality of the analysis strategies and thus improve the effectiveness of project data analysis.

[0066] In some optional implementations, updating the dataset information based on the merged dataset may include: analyzing the merged dataset to obtain a third analysis result; and updating the dataset information based on the merged dataset and the third analysis result.

[0067] The merged dataset can be analyzed in a second preset dimension to obtain a third analysis result. This second preset dimension may include, for example, a merge result dimension and an analysis target dimension. Analyzing the dataset in the merge result dimension may include: determining whether the merge was successful, identifying the failed parts, and analyzing the reasons for the failure. Analyzing the dataset in the analysis target dimension may include: a brief analysis of the analysis target based on the currently merged dataset.

[0068] Updating the dataset information based on the third analysis results can include: updating the dataset status in the dataset information based on the third analysis results of the merged result dimension; and storing the third analysis results of the analysis target dimension in the dataset information. Correspondingly, determining the first analysis result based on the current dataset information can include: analyzing and summarizing the dataset and the third analysis results in the current dataset information according to the analysis target to obtain the first analysis result.

[0069] Among these optional implementation methods, analyzing the merged dataset and updating the dataset information based on the third analysis results can provide a reference for determining the next round of analysis strategies, which is conducive to improving the rationality of the analysis strategies and thus improving the effectiveness of project data analysis.

[0070] In the technical solution of this disclosure embodiment, an analysis target can be obtained; initial dataset information can be obtained; an analysis strategy for the analysis target can be determined cyclically based on the current dataset information; in response to the analysis strategy being a data query, the dataset is queried according to the analysis strategy, and the dataset information is updated according to the dataset; in response to the analysis strategy being a data organization, the dataset is merged, and the dataset information is updated according to the merged dataset; in response to the analysis strategy being a data summary, a first analysis result is determined based on the current dataset information, and the loop ends.

[0071] By iteratively determining the next analysis strategy based on the current dataset information, this system can perform dataset queries when the current dataset is insufficient to analyze the target; merge related datasets when they need to be combined; and analyze the target based on the current dataset when it is sufficient. This enables multiple, dynamic data retrieval and merging, improving data retrieval accuracy and success rate, enhancing the effectiveness of project data analysis, and improving project management efficiency. Furthermore, it can deepen data queries when there is a need for in-depth data analysis, further improving the overall effectiveness of project data analysis.

[0072] This embodiment can be combined with various optional solutions in the project data analysis method provided in the above embodiments. The project data analysis method provided in this embodiment details the dataset query process.

[0073] Figure 2 This is a schematic diagram illustrating the process of querying a dataset in a project data analysis method provided in this embodiment of the disclosure. Figure 2 As shown, the project data analysis method provided in this embodiment, querying the dataset according to the analysis strategy, may include:

[0074] S210. Determine the data query target based on the analysis strategy.

[0075] In this embodiment, the query target can be represented in text form. Existing text processing algorithms can be used to eliminate interference from irrelevant semantics in the analysis strategy and extract information relevant to the data query from the analysis strategy to obtain a simplified data query target.

[0076] For example, suppose the analysis strategy includes the following: "Query data by project dimension, including but not limited to: ×× data; the current dataset is empty and there are no preceding analysis steps, so we need to prioritize obtaining the basic data supporting the analysis objectives." Then, the data query objective translated from the analysis strategy could include "obtain ×× data for each project." The query data item "×× data" in the query objective can be the same as or different from the query data item "×× data" in the analysis strategy. For instance, based on the query data items included in the analysis strategy, related project field transformations and expansions can be performed to obtain the query data items in the query objective.

[0077] S220. Determine the query plan based on the data query target.

[0078] In this embodiment, the query target can be represented in text form. A query plan containing at least one query step can be generated based on factors such as the dependencies between query data items in the query target.

[0079] S230. Following the query steps in the query plan, execute the data query operations sequentially to obtain the dataset.

[0080] In this embodiment, the query data items can be queried sequentially according to the query steps, and the results obtained from each query step can be summarized and processed to obtain the dataset for this round of query.

[0081] In some implementations, the query plan may include query tools corresponding to the query steps. These query tools can be user-built or externally integrated tools for data querying, and the query logic can be developed by the business side. These query tools may include, but are not limited to: data overview query tools, data distribution query tools, and data detail query tools. Specifically, the data overview query tool may have the ability to perform statistical analysis of the source data using a third preset dimension; the data distribution query tool may have the ability to determine the data distribution using a fourth preset dimension; and the data detail query tool may have the ability to query details using a fifth preset dimension as a parameter condition.

[0082] Accordingly, performing a data query operation may include: extracting query parameters from the data query target; and executing the data query operation based on the query parameters using a query tool. The query parameter items in the data query target may include query parameters, such as data fields. The query tool can be invoked based on the query parameters to execute the data query operation.

[0083] The amount of data queried can be controlled through query tools. For example, for detailed data queries with uncontrollable data volume, the data volume can be limited using query tools. This avoids excessively long datasets, greatly reducing the possibility of analytical illusions and improving the effectiveness of project data analysis.

[0084] Among these implementation methods, using tools to query data can reduce the requirements for understanding the business data model in the project data analysis process, which helps to improve the success rate and accuracy of data retrieval.

[0085] In some implementations, before performing a data query operation based on query parameters using a query tool, the following may also be included: deploying the query tool in response to the query tool not being included in a preset tool library.

[0086] In these implementations, if the query tools required for the query plan are not included in the pre-defined tool library, a prompt message containing the missing toolset can be generated. This prompt message can be sent to a pre-defined terminal to alert relevant users to supplement the missing tools. The query tools can then be deployed based on user actions, enabling continuous iteration and capability enhancement. Furthermore, the query tools can be plug-in tools, which can be added or removed according to specific application scenarios.

[0087] The technical solution of this disclosure provides a detailed description of the dataset query process. By translating the analysis strategy into the query target, irrelevant semantic interference can be eliminated; by formulating and executing a step-by-step query plan based on the query target, dataset querying can be achieved. Using tools for data querying reduces the understanding requirements of the business data model in the project data analysis process, helping to improve the success rate and accuracy of data retrieval. The project data analysis method provided in this disclosure belongs to the same disclosed concept as the project data analysis method provided in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and the same technical features have the same beneficial effects in this embodiment and the above embodiments.

[0088] This embodiment can be combined with the various optional solutions in the project data analysis method provided in the above embodiments. The project data analysis method provided in this embodiment supplements the project data analysis process.

[0089] Figure 3 This is a schematic block diagram of the data flow for a project data analysis method provided in an embodiment of this disclosure. Figure 3 As shown, the project data analysis method provided in this embodiment may include:

[0090] First, the analysis target can be determined based on the first content in the dialogue; where the first content refers to the content input by the user in the dialogue.

[0091] In this embodiment, an interactive dialogue can be used to clarify and follow up on the user's project data analysis needs. The dialogue content can include first content input by the user, or second content automatically generated based on the first content to clarify the project data analysis needs. Existing natural language processing algorithms can be used to determine the analysis objectives of the project data analysis based on the first content.

[0092] The analysis objectives may include at least two ( Figure 3 This includes analysis objectives 1-n. By breaking down the user's project data analysis needs into at least two analysis objectives, the length of the dataset for each analysis objective can be effectively controlled, greatly reducing the possibility of analysis illusion and improving the effectiveness of project data analysis.

[0093] Next, for each analysis objective, the following steps can be performed in parallel:

[0094] Obtain initial dataset information; Loop through the current dataset information to determine the analysis strategy for the analysis objective; If the analysis strategy is data query, query the dataset according to the analysis strategy and update the dataset information accordingly; If the analysis strategy is data organization, merge the datasets and update the dataset information accordingly; If the analysis strategy is data summarization, determine the first analysis result based on the current dataset information and end the loop.

[0095] Finally, the results of each first analysis can be analyzed ( Figure 3 The process involves analyzing the first set of analytical results (1-n) to obtain the fourth analytical result. The first set of analytical results may include datasets and visualizations. The fourth analytical result is then derived by summarizing and analyzing each of the first set of analytical results. This fourth analytical result can be presented in the form of a data report.

[0096] like Figure 3 As shown, the dataset can be analyzed to obtain a second analysis result; the dataset information can be updated based on the dataset and the second analysis result; the merged dataset can be analyzed to obtain a third analysis result; and the dataset information can be updated based on the merged dataset and the third analysis result.

[0097] like Figure 3 As shown, the project data analysis method may further include: determining strategy guidance information based on the first content. This strategy guidance information can be represented in text form and can be used to characterize user-specific project data analysis needs. For example, the strategy guidance information may include content such as "focus on exploring the causes of abnormal data" or "focus on exploring data details." The strategy guidance information can be determined based on the first content using existing natural language processing algorithms.

[0098] Accordingly, the loop determines the analysis strategy for the analysis target based on the current dataset information. This can include: looping to determine the analysis strategy for the analysis target based on the current dataset information and strategy guidance information. By injecting strategy guidance information, it is possible to support the determination of analysis strategies based on the user's specific project data analysis needs, thereby improving the user experience.

[0099] The technical solution of this disclosure supplements the project data analysis process. One or at least two analysis objectives can be defined through multi-round dialogue with the user. When there are two or more analysis objectives, each objective can be analyzed in parallel to obtain a first analysis result. Based on this, further analysis can be performed according to each first analysis result to obtain a fourth analysis result. By breaking down the analysis objectives and analyzing them one by one, the length of the analysis data can be effectively controlled, greatly avoiding the phenomenon of analysis illusion. Furthermore, strategy guidance information can be determined through dialogue with the user, and analysis strategies can be generated by combining this information, which helps meet the user's specific project data analysis needs and improves the user experience.

[0100] The project data analysis method provided in this embodiment belongs to the same concept as the project data analysis method provided in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and the same technical features have the same beneficial effects in this embodiment and the above embodiments.

[0101] This embodiment can be combined with the various optional solutions in the project data analysis method provided in the above embodiments. The project data analysis method provided in this embodiment can realize project data analysis based on multiple agents.

[0102] In this embodiment of the disclosure, the analysis strategy is determined by the first intelligent agent module; the dataset is queried based on the second intelligent agent module; the dataset is merged based on the third intelligent agent module; and the first analysis result is determined based on the fourth intelligent agent module.

[0103] Among them, the intelligent agent modules with different prefixes such as "first" and "second" can be composed of at least one intelligent agent. Here, an intelligent agent can be understood as an entity that relies on a neural network model and has autonomy, interactivity, and certain intelligent behavior capabilities; for example, it can be a software entity.

[0104] In this embodiment, the first intelligent agent module can iteratively determine the analysis strategy for the analysis target based on the current dataset information. If the analysis strategy is a data query, the second intelligent agent module can query the dataset according to the analysis strategy. If the analysis strategy is a data organization, the third intelligent agent module can merge the dataset. If the analysis strategy is a data summary, the fourth intelligent agent module can determine the first analysis result based on the current dataset information.

[0105] In this embodiment of the disclosure, by having multiple agent modules execute corresponding steps respectively, the understanding of business data by the traditional model can be decoupled, the requirements for model coding capabilities can be reduced, and agents can be constructed based on a general language model, thereby reducing model training costs and project data analysis costs.

[0106] For example, Figure 4 This is a schematic block diagram of the data flow for a project data analysis method provided in an embodiment of this disclosure. Figure 4 As shown, the project data analysis method provided in this embodiment may include:

[0107] First, an intelligent agent can be designed using a framework to determine the analysis target and strategy guidance information based on the first content in the dialogue; where the first content refers to the user input in the dialogue.

[0108] The framework design agent (Planner) can engage in interactive dialogue with the user and automatically generate second content based on the user's initial input to clarify the project's data analysis needs. The framework design agent can determine strategy guidance information and at least one analysis objective based on the first content. Furthermore, the framework design agent can generate other information based on the first content, such as the report topic, specific questions, and analysis approach for the project data analysis report.

[0109] For example, the output of the framework-designed agent may include the following:

[0110] Report Title: Comparative Analysis of Human Resource Input for Various Projects;

[0111] Specific issues: Identify differences in human resource input across projects, pinpoint key areas for resource allocation, and assess the rationality of the input;

[0112] Analysis objectives and approach:

[0113] Analysis Objective 1: Comparison of total project input; Approach: 1. Aggregate the estimated total working hours of all work items by project; 2. Calculate the number of roles and total tasks for each project; 3. Generate a project input ranking list, and query data items can include total working hours, number of tasks, and number of participants, etc.

[0114] Analysis Objective 2: Per Capita Input-Output Ratio; Approach: 1. Calculate the average working hours per person for the project. Query data items may include total working hours and number of participants; 2. Analyze the relationship between the requirement completion rate and per capita input; 3. Compare the node flow efficiency of high-input projects;

[0115] Analysis Objective 3: Input Trend Analysis; Approach: 1. Statistically analyze the distribution of working hours for each project on a weekly basis; 2. Identify the time characteristics of projects with consistently high input; 3. Analyze the correlation between abnormal input fluctuations and project stages.

[0116] In particular, when determining the analysis strategy in a loop, the analysis strategy can be determined by combining the ideas corresponding to the analysis target, which can further improve the rationality of the analysis strategy.

[0117] In this embodiment of the disclosure, the framework design agent and subsequent agents can generate relevant content based on prompt word technology. The prompt words for different agents may contain different content items, and these content items may include, but are not limited to, roles, goals, skills, workflows, task descriptions, strategies, constraints, and output formats, etc., which are not exhaustively listed here.

[0118] Then, the first intelligent agent module can execute the following steps in parallel for each analysis target: obtain initial dataset information; and cyclically determine the analysis strategy for the analysis target based on the current dataset information and strategy guidance information.

[0119] Figure 4 In this framework, the first intelligent agent module may include a decision-making intelligent agent (Reasoner). This decision-making intelligent agent, for each analytical objective and its underlying approach, iteratively determines and validates an analytical strategy based on the current dataset information and policy guidance. The type of analytical strategy may include data querying, data organization, and data summarization, among others.

[0120] For example, the output of the decision-making agent may include the following:

[0121] Analysis begins: Analysis objective 1: Comparison of total project input; Approach: 1. Aggregate the estimated total working hours of all work items by project; 2. Calculate the number of participating roles and total tasks for each project; 3. Generate a project input ranking list, and query data items can include total working hours, number of tasks, and number of participants, etc.

[0122] Current dataset: empty;

[0123] Strategy round: 1;

[0124] Based on the current dataset information, determine the analysis strategy...

[0125] Analysis strategy:

[0126] Data queries can be performed by project dimension, including but not limited to: ×× data; if the current dataset is empty and there are no preceding analysis steps, the basic data that supports the analysis objectives should be obtained first.

[0127] Analysis strategy validation in progress...

[0128] Verification result:

[0129] The current dataset is empty and lacks preliminary analysis steps, while the analysis target requires data querying by project dimension. Therefore, it is reasonable and necessary to prioritize obtaining the basic data that supports the analysis target.

[0130] Since the type of analysis strategy is data query, the second intelligent agent module can query the dataset according to the analysis strategy and update the dataset information accordingly.

[0131] Figure 4 In this module, the second intelligent agent module may include a data query agent, a query planner, a query execution agent, and a query summarizer.

[0132] Specifically, a data query agent can determine the data query target based on the analysis strategy; a query plan agent can determine the query plan based on the data query target; and a query execution agent can sequentially execute the data query operations according to the query steps in the query plan to obtain the dataset. A query summary agent can then analyze the dataset to obtain a second analysis result; and update the dataset information based on the dataset and the second analysis result.

[0133] Among them, the query execution agent can be executed through the query tool ( Figure 4 This can include tools 1-n, which perform data query operations based on the query parameters. These tools can include user-built tools (such as...). Figure 4 The tools in the middle (n) can also include externally accessed tools (such as...) Figure 4 (Tools 1-2 in the document). By calling these tools to query data, the understanding requirements of the query execution agent during the project data analysis process can be reduced, which helps to improve the success rate and accuracy of data retrieval.

[0134] For example, the output of a data query agent may include the following:

[0135] Determining data query targets based on analysis strategy...

[0136] Data query objective: To obtain ×× data for each project.

[0137] For example, the output of the query planning agent may include the following:

[0138] Determine the query plan based on the data query objectives...

[0139] Query plan: 1. Call tool × to obtain ×× data; 2. Call tool × to obtain ×× data. The current toolset is complete and can complete the data query.

[0140] For example, the output of the query execution agent may include the following:

[0141] Executing a data query...

[0142] Data query results: Retrieved ×× data and ×× data.

[0143] By extending the traditional single data retrieval logic into a second intelligent agent module, each step of the data retrieval process is handled by a dedicated intelligent agent, which minimizes the overall responsibility and thus ensures the success rate and accuracy of data retrieval.

[0144] The response to the analysis strategy belongs to data organization. The dataset can be merged through the third intelligent agent module, and the dataset information can be updated based on the merged dataset.

[0145] Figure 4 In this framework, the third agent module can include a data organizer and an organizer summarizer. The organizer, through a coder, writes code statements (such as SQL code) that can be executed in an in-memory database engine based on the given dataset and specific merging operations in the analysis action. This code statement can then be executed through the in-memory database engine to achieve the merging of datasets. The organizer summarizer analyzes the merged dataset to obtain a third analysis result; and updates the dataset information based on the merged dataset and the third analysis result.

[0146] If the type of analysis strategy is data summarization, the fourth agent module can determine the first analysis result based on the current dataset information and end the loop.

[0147] Figure 4 In this framework, the fourth intelligent agent module may include a data summarizer. This data summarizer can determine the first analysis result based on the current dataset information and then end the loop. For example, the data summarizer can analyze and summarize the analysis based on the analysis objective and its approach, the current dataset, the second analysis result, and the third analysis result to obtain the first analysis result.

[0148] In some implementations, the analysis objectives may include at least two; alternatively, a fourth intelligent agent module can be used to analyze each of the first analysis results to obtain a fourth analysis result. Specifically, a data summarizing intelligent agent can be used to analyze each of the first analysis results to obtain the fourth analysis result.

[0149] In this embodiment, an "observation-decision-execution" architecture can be used to achieve in-depth analysis for each analysis objective. The query-summarizing agent and the organization-summarizing agent belong to the observation part, updating the current dataset information; the decision-maker agent belongs to the decision-making part, determining the analysis strategy for the next round based on the current round's dataset information; and the second, third, and fourth agent modules belong to the execution part, performing operations such as data querying, data organization, and data summarization.

[0150] The technical solution of this disclosure can realize project data analysis based on a multi-agent module. By having multiple agent modules execute corresponding steps respectively, the understanding of business data by traditional models can be decoupled, reducing the requirements for model coding capabilities. This allows for the construction of agents based on a general model, reducing model training costs and thus lowering project data analysis costs. Furthermore, by having each step in the data method executed by a dedicated agent, the responsibilities of the agents are minimized, which helps improve the success rate and accuracy of data retrieval, as well as the depth of project data analysis, thereby improving the effectiveness of project data analysis.

[0151] The project data analysis method provided in this embodiment belongs to the same concept as the project data analysis method provided in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and the same technical features have the same beneficial effects in this embodiment and the above embodiments.

[0152] Figure 5 This is a schematic diagram of a project data analysis device provided in an embodiment of this disclosure. The project data analysis device provided in this embodiment is applicable to project data analysis, such as the generation of intelligent data reports.

[0153] like Figure 5 As shown, the project data analysis apparatus provided in this embodiment may include:

[0154] The first acquisition module 510 is used to acquire the analysis target;

[0155] The second acquisition module 520 is used to acquire initial dataset information;

[0156] Decision module 530 is used to cyclically determine the analysis strategy for the analysis target based on the current dataset information;

[0157] The query module 540 is used to respond to the analysis strategy being a data query, query the dataset according to the analysis strategy, and update the dataset information based on the dataset.

[0158] The organization module 550 is used to merge datasets and update dataset information based on the merged datasets in response to the analysis strategy being of the data organization type.

[0159] Analysis module 560 is used to respond to the analysis strategy type being data summary, determine the first analysis result based on the current dataset information, and end the loop.

[0160] In some alternative implementations, the query module can be used for:

[0161] Determine the data query target based on the analysis strategy;

[0162] Determine the query plan based on the data query objectives;

[0163] The data query operations are executed sequentially according to the query steps in the query plan to obtain the dataset.

[0164] In some optional implementations, the query plan includes query tools corresponding to the query steps; the query module can be used for:

[0165] Extract query parameters from the data query target;

[0166] The query tool performs data query operations based on the query parameters.

[0167] In some alternative implementations, the project data analysis apparatus may also include:

[0168] The tool deployment module is used to deploy the query tool in response to the query tool not being included in the preset tool library before performing a data query operation based on the query parameters.

[0169] In some alternative implementations, the query module can be used for:

[0170] The dataset was analyzed to obtain the second analysis result;

[0171] The dataset information is updated based on the dataset and the results of the second analysis.

[0172] In some alternative implementations, the organization module can be used for:

[0173] The merged dataset was analyzed to obtain the third analysis result;

[0174] The dataset information is updated based on the merged dataset and the results of the third analysis.

[0175] In some alternative implementations, the analysis objectives include at least two; the analysis module can also be used for:

[0176] The results of the first analysis were analyzed to obtain the fourth analysis result.

[0177] In some alternative implementations, the first acquisition module can be used for:

[0178] The analysis target is determined based on the first content in the dialogue; where the first content refers to the user input in the dialogue.

[0179] In some alternative implementations, the first acquisition module can also be used for:

[0180] Determine the strategy guidance information based on the first content;

[0181] Correspondingly, the decision-making module can be used for:

[0182] The loop determines the analysis strategy for the analysis target based on the current dataset information and strategy guidance information.

[0183] In some alternative implementations, the decision module can also be used for:

[0184] After determining the analysis strategy for the analysis target, the validation results of the analysis strategy are determined based on the current dataset information and the analysis strategy.

[0185] If the verification result is successful, proceed with the next steps based on the type of analysis strategy.

[0186] In some alternative implementations, the analysis strategy is determined by the first agent module; the dataset is queried based on the second agent module; the dataset is merged based on the third agent module; and the first analysis result is determined based on the fourth agent module.

[0187] The project data analysis apparatus provided in this disclosure can execute the project data analysis method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the method execution.

[0188] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0189] The following is for reference. Figure 6 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 6The diagram below shows the structure of the terminal device (or server) 600. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0190] like Figure 6 As shown, electronic device 600 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of electronic device 600. The processing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0191] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays, speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0192] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined in the project data analysis method of embodiments of this disclosure.

[0193] The electronic device provided in this embodiment and the project data analysis method provided in the above embodiments belong to the same disclosed concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0194] This disclosure provides a storage medium for computer-executable instructions, which, when executed by a computer processor, can be used to perform the project data analysis method provided in the above embodiments.

[0195] It should be noted that the storage medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but 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 (FLASH), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores executable instructions that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable executable instructions. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit executable instructions for use by or in connection with an instruction execution system, apparatus, or device. Executable instructions contained on the storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, radio frequency (RF), etc., or any suitable combination thereof.

[0196] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0197] The aforementioned storage medium may be included in the aforementioned electronic device; or it may exist independently and not be assembled into the electronic device.

[0198] The aforementioned storage medium carries one or more executable instructions, which, when executed by the electronic device, cause the electronic device to:

[0199] The process involves: obtaining the analysis objective; obtaining initial dataset information; determining the analysis strategy for the analysis objective based on the current dataset information; responding to the analysis strategy type being data query, querying the dataset according to the analysis strategy, and updating the dataset information accordingly; responding to the analysis strategy type being data organization, merging the datasets, and updating the dataset information according to the merged dataset; responding to the analysis strategy type being data summarization, determining the first analysis result based on the current dataset information, and ending the loop.

[0200] Executable instructions for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The executable instructions 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).

[0201] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, can implement the project data analysis method provided in any embodiment of this disclosure.

[0202] The computer program product includes a computer program hosted on a non-transitory computer-readable medium, which contains program code for executing project data analysis methods. The program code can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as 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).

[0203] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. 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 a 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, can 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.

[0204] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units and modules do not, in certain circumstances, constitute a limitation on the unit or module itself.

[0205] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0206] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, or any suitable combination of the foregoing.

[0207] According to one or more embodiments of this disclosure, a project data analysis method is provided, the method comprising:

[0208] Obtain the analysis target;

[0209] Obtain initial dataset information;

[0210] The loop determines the analysis strategy for the analysis objective based on the current dataset information.

[0211] In response to the analysis strategy being a data query, the dataset is queried according to the analysis strategy, and the dataset information is updated based on the dataset.

[0212] In response to the analysis strategy being of the type of data organization, the datasets are merged, and the dataset information is updated based on the merged datasets;

[0213] In response to the analysis strategy being of the type of data summary, a first analysis result is determined based on the current dataset information, and the loop ends.

[0214] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0215] In some optional implementations, querying the dataset according to the analysis strategy includes:

[0216] The data query target is determined based on the analysis strategy described above;

[0217] Determine a query plan based on the data query objectives;

[0218] The data query operations are executed sequentially according to the query steps in the query plan to obtain the dataset.

[0219] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0220] In some optional implementations, the query plan includes a query tool corresponding to the query step; the execution of the data query operation includes:

[0221] Extract the query parameters from the data query target;

[0222] The query tool performs a data query operation based on the query parameters.

[0223] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0224] In some optional implementations, before performing the data query operation based on the query parameters using the query tool, the method further includes:

[0225] In response to the fact that the query tool is not included in the preset tool library, the query tool is deployed.

[0226] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0227] In some optional implementations, updating the dataset information based on the dataset includes:

[0228] The dataset was analyzed to obtain a second analysis result;

[0229] The dataset information is updated based on the dataset and the second analysis result.

[0230] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0231] In some optional implementations, updating the dataset information based on the merged dataset includes:

[0232] The merged dataset was analyzed to obtain the third analysis result;

[0233] The dataset information is updated based on the merged dataset and the third analysis results.

[0234] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0235] In some alternative implementations, the analysis objectives include at least two; the method further includes:

[0236] The first analysis results are analyzed to obtain the fourth analysis result.

[0237] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0238] In some alternative implementations, obtaining the analysis target includes:

[0239] The analysis target is determined based on the first content in the dialogue content; wherein the first content belongs to the content input by the user in the dialogue content.

[0240] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0241] In some optional implementations, the strategy guidance information is determined based on the first content;

[0242] The loop determines an analysis strategy for the analysis objective based on the current dataset information, including:

[0243] The loop determines the analysis strategy for the analysis target based on the current dataset information and the strategy guidance information.

[0244] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0245] In some alternative implementations, after determining the analysis strategy for the analysis objective, the method further includes:

[0246] Based on the current dataset information and the analysis strategy, determine the verification result of the analysis strategy;

[0247] If the verification result is successful, subsequent steps are executed according to the type of the analysis strategy.

[0248] According to one or more embodiments of this disclosure, a project data analysis method is provided, further comprising:

[0249] In some alternative implementations, the analysis strategy is determined by a first agent module; the dataset is queried based on a second agent module; the dataset is merged based on a third agent module; and the first analysis result is determined based on a fourth agent module.

[0250] According to one or more embodiments of this disclosure, a project data analysis apparatus is provided, the apparatus comprising:

[0251] The first acquisition module is used to acquire the analysis target;

[0252] The second acquisition module is used to acquire initial dataset information;

[0253] The decision module is used to cyclically determine the analysis strategy for the analysis target based on the current dataset information;

[0254] The query module is used to respond to the fact that the analysis strategy is a data query, query the dataset according to the analysis strategy, and update the dataset information according to the dataset.

[0255] An organization module is used to merge the datasets in response to the analysis strategy being of the type of data organization, and to update the dataset information based on the merged datasets;

[0256] The analysis module is used to determine a first analysis result based on the current dataset information in response to the analysis strategy being of the type of data summary, and then end the loop.

[0257] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure 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-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0258] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0259] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A project data analysis method, characterized in that, include: Obtain the analysis target; Obtain initial dataset information; The loop determines the analysis strategy for the analysis objective based on the current dataset information. When the current dataset is insufficient to analyze the target, in response to the analysis strategy being of the type of data query, the dataset is queried according to the analysis strategy, and the dataset information is updated according to the dataset. If the dataset queried based on the data query type is related to an existing dataset, in response to the analysis strategy being of the type of data organization, the dataset is merged, and the dataset information is updated based on the merged dataset; If, after data organization, the dataset is still insufficient to analyze the analysis target, the next analysis strategy is determined to be a data query type, and the process returns to execute the data query. When the dataset is sufficient to analyze the target, or when the upper limit of the data query rounds is reached, in response to the analysis strategy being of the type of data summary, a first analysis result is determined based on the current dataset information, and the loop ends; After determining the analysis strategy for the analysis objective, the method further includes: Based on the current dataset information and the analysis strategy, determine the verification result of the analysis strategy; If the verification result is successful, subsequent steps are executed according to the type of the analysis strategy. The step of determining whether the verification result passes includes: verifying the feasibility and rationality of the analysis strategy using the constructed neural network model; when the analysis strategy is feasible and reasonable, the verification result of the analysis strategy is that it passes; when the analysis strategy is not feasible and / or not reasonable, the verification result of the analysis strategy is that it fails. The analysis strategy is determined by the first intelligent agent module; the dataset is queried based on the second intelligent agent module; the dataset is merged based on the third intelligent agent module; the first analysis result is determined based on the fourth intelligent agent module. The process of merging datasets includes: writing code statements that are executed in the in-memory database engine based on the datasets and specific merging operations given in the specific analysis actions of the analysis strategy; and running the code statements through the in-memory database engine to achieve the association and merging of datasets. The step of updating the dataset information based on the merged dataset includes: The merged dataset is analyzed according to a second preset dimension to obtain a third analysis result; wherein, the second preset dimension includes the merged result dimension and the analysis target dimension; The dataset information is updated based on the merged dataset and the third analysis results; The process of updating the dataset information based on the results of the third analysis includes: Based on the third analysis result of the merged result dimension, update the dataset status in the dataset information; The third analysis results of the target dimension are stored in the dataset information; Accordingly, determining the first analysis result based on the current dataset information includes: analyzing and summarizing the dataset and the third analysis result in the current dataset information according to the analysis objective to obtain the first analysis result.

2. The method according to claim 1, characterized in that, The step of querying the dataset according to the analysis strategy includes: The data query target is determined based on the analysis strategy described above; Determine a query plan based on the data query objectives; The data query operations are executed sequentially according to the query steps in the query plan to obtain the dataset.

3. The method according to claim 2, characterized in that, The query plan includes query tools corresponding to the query steps; The data query operation includes: Extract the query parameters from the data query target; The query tool performs a data query operation based on the query parameters.

4. The method according to claim 3, characterized in that, Before performing the data query operation based on the query parameters using the query tool, the method further includes: In response to the fact that the query tool is not included in the preset tool library, the query tool is deployed.

5. The method according to claim 1, characterized in that, The step of updating the dataset information based on the dataset includes: The dataset was analyzed to obtain a second analysis result; The dataset information is updated based on the dataset and the second analysis result.

6. The method according to claim 1, characterized in that, The analytical objectives include at least two; the method further includes: The first analysis results are analyzed to obtain the fourth analysis result.

7. The method according to claim 1, characterized in that, The acquisition and analysis target includes: The analysis target is determined based on the first content in the dialogue content; wherein the first content belongs to the content input by the user in the dialogue content.

8. The method according to claim 7, characterized in that, Also includes: Determine the strategy guidance information based on the first content; The loop determines an analysis strategy for the analysis objective based on the current dataset information, including: The loop determines the analysis strategy for the analysis target based on the current dataset information and the strategy guidance information.

9. A project data analysis device, characterized in that, include: The first acquisition module is used to acquire the analysis target; The second acquisition module is used to acquire initial dataset information; The decision module is used to cyclically determine the analysis strategy for the analysis target based on the current dataset information; The query module is used to query the dataset according to the analysis strategy when the current dataset is insufficient to analyze the analysis target, and to update the dataset information according to the dataset, in response to the analysis strategy being of the type of data query. The organization module is used to merge the datasets if the dataset queried based on the data query type is related to an existing dataset, in response to the analysis strategy being of the type of data organization, and to update the dataset information based on the merged dataset. The analysis module is used to determine a first analysis result based on the current dataset information and end the loop when the dataset is sufficient to analyze the analysis target or when the upper limit of the data query rounds is reached, in response to the analysis strategy being of the type of data summary. The decision-making module is also used for: After determining the analysis strategy for the analysis target, the verification result of the analysis strategy is determined based on the current dataset information and the analysis strategy. If the verification result is successful, subsequent steps are executed according to the type of the analysis strategy. The step of determining whether the verification result passes includes: verifying the feasibility and rationality of the analysis strategy using the constructed neural network model; when the analysis strategy is feasible and reasonable, the verification result of the analysis strategy is that it passes; when the analysis strategy is not feasible and / or not reasonable, the verification result of the analysis strategy is that it fails. The analysis strategy is determined by the first intelligent agent module; the dataset is queried based on the second intelligent agent module; the dataset is merged based on the third intelligent agent module; the first analysis result is determined based on the fourth intelligent agent module. The organization module is specifically used to write code statements that are executed in the in-memory database engine based on the dataset and specific merging operation given in the specific analysis action of the analysis strategy, and to run the code statements through the in-memory database engine to realize the association and merging between datasets; The organization module is specifically used to: perform analysis on the merged dataset in a second preset dimension to obtain a third analysis result; wherein, the second preset dimension includes the merged result dimension and the analysis target dimension; The dataset information is updated based on the merged dataset and the third analysis results; The process of updating the dataset information based on the results of the third analysis includes: Based on the third analysis results of the merged result dimension, update the dataset status in the dataset information; store the third analysis results of the analysis target dimension in the dataset information; Accordingly, determining the first analysis result based on the current dataset information includes: analyzing and summarizing the dataset and the third analysis result in the current dataset information according to the analysis objective to obtain the first analysis result; The device is further configured to: after performing data organization, if the dataset is still insufficient to analyze the analysis target, determine the next analysis strategy as a data query type and return to execute the data query.

10. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the project data analysis method as described in any one of claims 1-8.

11. A storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the project data analysis method as described in any one of claims 1-8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the project data analysis method as described in any one of claims 1-8.

Images