Project data analysis method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a project data analysis method and device, electronic equipment and a storage medium. The method comprises the steps that an analysis target is acquired; acquiring initial data set information; circularly determining an analysis strategy for the analysis target according to the current data set information; in response to the fact that the type of the analysis strategy belongs 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 fact that the type of the analysis strategy belongs to a data organization, combining the data sets, and updating the data set information according to the combined data sets; and in response to the fact that the type of the analysis strategy belongs to the data summary, determining a first analysis result according to the current data set information, and ending the cycle. The data analysis effect for the project can be improved, and the project management efficiency is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a project data analysis method, apparatus, electronic device, and storage medium. Background Art

[0002] In today's environment where development is data-driven, the importance of intelligent data reports in the project management process has become increasingly prominent. Currently, in the process of analyzing and generating data reports, the data extraction logic is single, resulting in low extraction accuracy and success rate, and it is unable to meet in-depth analysis. The project data analysis effect is poor, affecting the project management efficiency. Summary of the Invention

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

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

[0005] Obtain an analysis target;

[0006] Obtain initial dataset information;

[0007] Repeatedly determine an analysis strategy for the analysis target according to the current dataset information;

[0008] In response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy, and update the dataset information according to the dataset;

[0009] In response to the type of the analysis strategy belonging to data organization, merge the datasets, and update the dataset information according to the merged datasets;

[0010] In response to the type of the analysis strategy belonging to data summary, determine a first analysis result according to the current dataset information, and end the loop.

[0011] In a second aspect, embodiments of the present disclosure further provide a project data analysis apparatus, including:

[0012] A first acquisition module, configured to obtain an analysis target;

[0013] A second acquisition module, configured to obtain initial dataset information;

[0014] A decision module, configured to repeatedly determine an analysis strategy for the analysis target according to the current dataset information;

[0015] A query module, configured to, in response to the type of the analysis strategy belonging to data query, query a data set according to the analysis strategy, and update the data set information based on the data set;

[0016] An organization module, configured to, in response to the type of the analysis strategy belonging to data organization, merge the data sets, and update the data set information based on the merged data sets;

[0017] An analysis module, configured to, in response to the type of the analysis strategy belonging to data summary, determine a first analysis result according to the current data set information, and end the loop.

[0018] In a third aspect, an embodiment of the present disclosure further provides an electronic device, which includes:

[0019] One or more processors;

[0020] A storage device, configured to store 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 according to any one of the embodiments of the present disclosure.

[0022] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the project data analysis method according to any one of the embodiments of the present disclosure when executed by a computer processor.

[0023] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, characterized in that the computer program product includes a computer program, and the computer program implements the project data analysis method according to any one of the embodiments of the present disclosure when executed by a processor.

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

[0025] By looping to determine the next analysis strategy based on the current dataset information, it is possible to query the dataset when the current dataset is insufficient for analyzing the analysis target; perform the association and merging of datasets when there is an association between datasets that needs to be merged; and analyze the analysis target based on the current dataset when the dataset is sufficient for analyzing the analysis target. Thus, it is possible to achieve multiple and dynamic data fetching and merging, improve the accuracy and success rate of data fetching, enhance the data analysis effect for the project, and improve the project management efficiency. Moreover, when there is a need for in-depth query of the dataset, it is possible to strengthen the depth of data query to support in-depth data analysis, further improving the project data analysis effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. 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 that the original components and elements are not necessarily drawn to scale.

[0027] Figure 1 is a flowchart showing a project data analysis method provided by an embodiment of the present disclosure;

[0028] Figure 2 is a flowchart showing the process of querying a dataset in a project data analysis method provided by an embodiment of the present disclosure;

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

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

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

[0032] Figure 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0034] It should be understood that the various steps described in the method embodiments of the present disclosure may be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0035] As used herein, the term "comprising" and its variations are open-ended, i.e., "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". The relevant definitions of other terms will be given in the following description.

[0036] It should be noted that the concepts such as "first", "second", etc. mentioned in the present disclosure are only used 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 interdependent relationships.

[0037] It should be noted that the modification of "one" and "a plurality" mentioned in the present disclosure is illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

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

[0039] Figure 1 The flowchart shows a method for project data analysis provided by an embodiment of the present disclosure. The embodiments of the present disclosure are applicable to the situation of data analysis for projects, such as the situation of generating intelligent data reports. This method can be executed by a project data analysis device, which can be implemented in the form of software and / or hardware, and can be configured in an electronic device, such as a computer device.

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

[0041] S110. Obtain the analysis target.

[0042] In the embodiments of the present disclosure, the analysis objective may refer to the objective of data analysis for a project and may be represented in text form. Exemplarily, the analysis objective may include contents such as "comparison of total investment in each project", "comparison of per capita output in each project", and "investment trend in each project", etc. Among them, the analysis objective input by the user can be received through a preset interface, or the analysis objective can be automatically generated according to preset information. Among them, automatically generating the analysis objective according to preset information, for example, includes generating the analysis objective according to the theme of the data report, etc.

[0043] S120. Obtain the initial dataset information.

[0044] In the embodiments of the present disclosure, the dataset information may include, but is not limited to, information such as datasets, dataset status, and the association relationship between datasets, etc. Among them, a dataset may refer to a set composed of data and may be represented in the form of a data table, etc. Among them, the dataset status may include normal and abnormal, and can be determined based on the data within the dataset. For example, in the case of data missing or data anomaly in the dataset, the dataset status can be determined to be abnormal; in the case where the internal data of the dataset is complete and normal, the dataset status can be determined to be normal. Among them, the association relationship between datasets may include associated and unassociated. Among them, if the datasets are associated, it can be considered that there is a need for merging between the datasets; if the datasets are unassociated, it can be considered that there is no need for merging between the datasets.

[0045] Among them, the initial dataset information may be empty. Among them, the initial dataset information can be obtained through existing initialization statements. The dataset information can be updated according to subsequent operations.

[0046] S130. Continuously determine the analysis strategy for the analysis objective according to the current dataset information.

[0047] In the embodiments of the present disclosure, for the analysis objective, the next action (i.e., the analysis strategy) can be continuously determined according to the current dataset information. Among them, the types of analysis strategies may include data query, data organization, and data summary, etc. Among them, the analysis strategy determined according to the current dataset information usually includes one type.

[0048] Among them, the analysis strategy can be represented in text form and may include contents such as the type of analysis strategy, specific analysis actions, and the reasons for determining the analysis strategy, etc. Exemplarily, the analysis strategy may, for example, include contents such as "conduct data query according to the project dimension, including but not limited to: ×× data; the current dataset is empty and there is no previous analysis step, and it is necessary to preferentially obtain the basic data to support the analysis objective", etc. From the example, it can be seen that in the first round of loop, the current dataset information is the initial dataset information, for example, empty, and at this time, the usually determined analysis strategy is data query to obtain the basic data to support the analysis objective.

[0049] Among them, the next analysis strategy can be determined according to the current dataset information through preset rules and templates, or through a completed neural network model. Among them, by dynamically determining the analysis strategy, dataset query can be performed when the current dataset is insufficient to analyze the analysis target to supplement the dataset; dataset merging can be performed when datasets are associated to facilitate project data analysis; when the dataset is sufficient to analyze the analysis target, the analysis target can be analyzed according to the current dataset to obtain the first analysis result. In addition, dataset query can also be performed for anomalies in the current dataset to explore the reasons for the anomalies; or, dataset query can be performed for important concerns in the existing datasets to query the necessary detailed data. By strengthening the depth of data query when there are in-depth query requirements such as dataset anomalies or concerns, to support in-depth data analysis, the project data analysis effect can be further improved.

[0050] In some optional implementation manners, after determining the analysis strategy for the analysis target, it may further include: determining the verification result of the analysis strategy according to the current dataset information and the analysis strategy; in response to the verification result being verified as passed, performing subsequent steps according to the type of the analysis strategy.

[0051] Among them, the feasibility, rationality, etc. of the analysis strategy can be verified through a completed neural network model (such as a language model). For example, prompt words for the language model can be constructed according to the current dataset information and the analysis strategy, so that the language model outputs whether the analysis strategy is feasible and necessary. When the analysis strategy is feasible and reasonable, the verification result of the analysis strategy can be considered as verified passed. At this time, subsequent steps can be performed according to the strategy type of the analysis strategy. When the analysis strategy is not feasible and / or not reasonable, the verification result of the analysis strategy can be considered as verified not passed. At this time, the analysis strategy can be regenerated and verified until it is verified passed, so as to perform subsequent steps according to the strategy type of the analysis strategy.

[0052] In these optional implementation manners, by verifying the analysis strategy, the feasibility and rationality of the analysis strategy can be guaranteed, which helps to improve the project data analysis effect.

[0053] S141. In response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy, and update the dataset information according to the dataset.

[0054] When the type of the analysis strategy belongs to data query, the dataset query can be performed according to the specific analysis actions in the analysis strategy. For example, the dataset query can be performed according to the query parameters carried in the analysis actions. Moreover, based on the dataset obtained by the query, the dataset information can be updated. For example, the dataset obtained by the query can be supplemented to the dataset in the dataset information. For another example, based on the dataset obtained by the query, the dataset status and / or the association relationship between datasets in the dataset information can be updated.

[0055] In response to the update of the dataset information, the next round of loop can be entered, and again according to the current dataset information (i.e., the updated dataset information), the analysis strategy for the analysis target can be determined. Among them, the upper limit of the data query round can be preset to restrict the total time consumption of the project data analysis process.

[0056] S142. In response to the type of the analysis strategy belonging to data organization, the datasets are merged, and the dataset information is updated according to the merged datasets.

[0057] When the type of the analysis strategy belongs to data organization, the dataset merge can be performed according to the specific analysis actions in the analysis strategy. Among them, performing the dataset merge can include: writing code statements that can be executed by the in-memory database engine according to the given datasets and specific merge operations in the analysis actions, such as writing Structured Query Language (SQL) code; running the code statements through the in-memory database engine to achieve the associative merge between datasets.

[0058] Among them, in response to the dataset merge, the dataset information can be updated according to the merged datasets. For example, the existing datasets in the dataset information can be updated according to the merged datasets. For another example, the dataset status and / or the association relationship between datasets in the dataset information can be updated according to the merged datasets. Similarly, in response to the update of the dataset information, the next round of loop can be entered, and again according to the current dataset information (i.e., the updated dataset information), the analysis strategy for the analysis target can be determined.

[0059] In the embodiments of the present disclosure, step S141 and step S142 can be interspersed and executed. For example, after executing step S141, if the dataset after the query is associated with the existing datasets, the determined next analysis strategy can be of the data organization type, and then step S142 can be executed; after executing step S142, if the datasets are still insufficient for analyzing the analysis target, the determined next analysis strategy can be of the data query type, and then step S141 can be executed. Generally, during the execution of multiple rounds of step S141, step S142 can be interspersed and executed.

[0060] S143. In response to the type of the analysis strategy belonging to data summarization, determine a first analysis result according to the current dataset information and end the loop.

[0061] When the dataset is sufficient for analyzing the analysis target or reaches the upper limit of the data query rounds, the determined analysis strategy can be of the data summarization type. At this time, the dataset in the current dataset information can be analyzed and summarized according to the specific analysis actions in the analysis strategy to obtain a first analysis result. For example, the dataset can be analyzed and summarized according to the analysis target carried in the analysis actions. Among them, the loop can be ended in response to obtaining the first analysis result of the analysis target.

[0062] In some alternative implementation manners, updating the dataset information according to the dataset may include: analyzing the dataset to obtain a second analysis result; and updating the dataset information according to the dataset and the second analysis result.

[0063] Among them, the dataset can be analyzed in a first preset dimension to obtain a second analysis result. The first preset dimension may include, for example, a query result dimension and an analysis target dimension. Analyzing the dataset in the query result dimension may include: analyzing the integrity of the currently queried dataset, determining the part where the query fails, and analyzing the failure reason, etc. Analyzing the dataset in the analysis target dimension may include: a brief analysis of the analysis target based on the currently queried dataset.

[0064] Among them, updating the dataset information according to the second analysis result may include: updating the dataset status in the dataset information according to the second analysis result in the query result dimension; and storing the second analysis result in the analysis target dimension in the dataset information. Correspondingly, determining the first analysis result according to the current dataset information may include: analyzing and summarizing the dataset and the second analysis result in the current dataset information according to the analysis target to obtain a first analysis result.

[0065] In these alternative implementation manners, by analyzing the dataset and updating the dataset information based on the obtained second analysis result, it can provide a reference for determining the analysis strategy in the next round, which is beneficial to improving the rationality of the analysis strategy so as to improve the project data analysis effect.

[0066] In some alternative implementation manners, updating the dataset information according to the merged dataset may include: analyzing the merged dataset to obtain a third analysis result; and updating the dataset information according to the merged dataset and the third analysis result.

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

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

[0069] In these alternative implementation manners, by analyzing the merged dataset and updating the dataset information based on the obtained third analysis result, it is possible to provide a reference for determining the next round of analysis strategy, which is conducive to improving the rationality of the analysis strategy and thus enhancing the data analysis effect of the project.

[0070] In the technical solution of the embodiments of the present disclosure, an analysis target can be obtained; initial dataset information can be obtained; the analysis strategy for the analysis target is determined cyclically according to the current dataset information; in response to the type of the analysis strategy belonging to 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 type of the analysis strategy belonging to data organization, the datasets are merged, and the dataset information is updated according to the merged dataset; in response to the type of the analysis strategy belonging to data summary, the first analysis result is determined according to the current dataset information, and the loop ends.

[0071] By cyclically determining the next analysis strategy according to the current dataset information, it is possible to query the dataset when the current dataset is insufficient for analyzing the analysis target; perform the association and merge of the datasets when there is an association between the datasets that needs to be merged; and analyze the analysis target according to the current dataset when the dataset is sufficient for analyzing the analysis target. Thus, it is possible to achieve multiple and dynamic data fetching and merging, improve the accuracy and success rate of data fetching, enhance the data analysis effect for the project, and improve the project management efficiency. Moreover, when there is a need for in-depth query of the dataset, the depth of data query can be strengthened to support in-depth data analysis, further improving the data analysis effect of the project.

[0072] The optional solutions in the project data analysis method provided in the embodiments of the present disclosure can be combined with those in the above embodiments. The project data analysis method provided in this embodiment describes the dataset query process in detail.

[0073] Figure 2 It is a schematic flowchart of querying a dataset in a project data analysis method provided in an embodiment of the present disclosure. As Figure 2 shown, in the project data analysis method provided in this embodiment, querying a dataset according to an analysis strategy may include:

[0074] S210. Determine a data query target according to the analysis strategy.

[0075] In this embodiment, the query target may be represented in text form. Among them, through existing text processing algorithms, the interference of irrelevant semantics in the analysis strategy can be excluded, and the information related to data query in the analysis strategy can be extracted to obtain a refined data query target.

[0076] Exemplarily, assuming that the content of the analysis strategy includes "perform data query according to the project dimension, including but not limited to: ×× data; the current dataset is empty and there is no previous analysis step, and it is necessary to preferentially obtain the basic data to support the analysis target", then the data query target translated according to the analysis strategy may include "obtain the ×× data of each project". Among them, the query data item "×× data" included in the query target may be the same as or different from the query data item "×× data" included in the analysis strategy. For example, based on the query data item included in the analysis strategy, relevant project field conversion, expansion, etc. operations can be performed to obtain the query data item in the query target.

[0077] S220. Determine a query plan according to the data query target.

[0078] In this embodiment, the query target may be represented in text form. Among them, according to the dependency relationship of the query data items in the data query target, etc., a query plan including at least one query step may be generated.

[0079] S230. Perform data query operations in sequence according to the query steps in the query plan to obtain a dataset.

[0080] In this embodiment, the query of query data items can be performed in sequence according to the query steps, and the results obtained according to each query step can be summarized and processed, etc., to obtain the dataset of this round of query.

[0081] In some implementations, a query plan may include query tools corresponding to query steps. Among them, the query tools may include tools built by users themselves or accessed externally for data query, and the query logic for data query can be developed by the business side. Among them, the query tools may include, but are not limited to: data overview query tools, data distribution query tools, data details query tools, etc. Among them, the data overview query tool may have the ability to statistically analyze the source data in a third preset dimension; the data distribution query tool may have the ability to determine the data distribution in a fourth preset dimension; the data details query tool may have the ability to query details with a fifth preset dimension as a parameter condition.

[0082] Correspondingly, performing a data query operation may include: extracting query parameters in the data query target; and performing a data query operation according to the query parameters through the query tool. Among them, the query parameter items in the data query target may include query parameters, such as parameters like data fields. Among them, the query tool can be called according to the query parameters to perform a data query operation through the query tool.

[0083] Among them, the amount of data queried can be controlled through the query tool. For example, for a data details query with an uncontrollable amount of data, the amount of data can be limited through the query tool. Thereby, the situation of an overly long data set can be avoided, the occurrence of analysis illusions can be largely avoided, which is beneficial to improving the data analysis effect of the project.

[0084] In these implementations, by calling tools for data query, the requirement for understanding the business data model in the project data analysis process can be reduced, which helps to improve the success rate and accuracy of data extraction.

[0085] In some implementations, before performing a data query operation according to the query parameters through the query tool, it may further include: in response to the query tool not being included in the preset tool library, deploying the query tool.

[0086] In these implementations, in response to the query tool required by the query plan not being included in the preset tool library, a prompt message including the missing tool set may also be generated. Among them, the prompt message can be sent to the preset terminal to prompt relevant users to supplement tools with relevant capabilities, and deploy the query tool according to the user's operation, so as to achieve continuous iterative ability supplementation. In addition, the query tool can be a plug-in tool, and the plug-in tool can be added or deleted according to the specific application scenario.

[0087] The technical solution of the embodiment of the present disclosure describes the dataset query process in detail. By translating the analysis strategy into a query target, irrelevant semantic interference can be excluded; by formulating and executing a step-by-step query plan according to the query target, dataset query can be achieved. By calling tools for data query, the requirement for understanding the business data model in the project data analysis process can be reduced, which helps to improve the success rate and accuracy of data extraction. The project data analysis method provided by the embodiment of the present disclosure and the project data analysis method provided by the above embodiment belong to the same general concept. Technical details not described in detail in this embodiment can be referred to the above embodiment, and the same technical features have the same beneficial effects in this embodiment and the above embodiment.

[0088] The various alternative solutions in the project data analysis methods provided by the embodiment of the present disclosure and the above embodiment can be combined. The project data analysis method provided in this embodiment supplements the project data analysis process.

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

[0090] First, an analysis target can be determined according to the first content in the conversation content; wherein, the first content belongs to the content input by the user in the conversation content.

[0091] In this embodiment, an interactive dialogue method can be adopted to clarify and inquire about the user's project data analysis requirements. The conversation content may include the first content input by the user, or may include the second content automatically generated according to the first content for clarifying the project data analysis requirements. Among them, the analysis target of the project data analysis can be determined according to the first content through existing natural language processing algorithms.

[0092] Among them, the analysis target may include at least two ( Figure 3 including analysis targets 1-n). By splitting the user's project data analysis requirements into at least two analysis targets, the length of the dataset for each analysis target can be effectively controlled, the occurrence of analysis hallucinations can be largely avoided, and it is beneficial to improve the project data analysis effect.

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

[0094] Obtain the initial dataset information; loop to determine the analysis strategy for the analysis target based on the current dataset information; in response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy and update the dataset information based on the dataset; in response to the type of the analysis strategy belonging to data organization, merge the datasets and update the dataset information based on the merged dataset; in response to the type of the analysis strategy belonging to data summary, determine the first analysis result based on the current dataset information and end the loop.

[0095] Finally, each of the first analysis results ( Figure 3 which includes the first analysis results 1 - n) can be analyzed to obtain the fourth analysis result. Among them, the first analysis result can include datasets and visualization icons, etc.; among them, each of the first analysis results can be summarized and analyzed to obtain the fourth analysis result. Among them, the fourth analysis result can be represented in the form of a data report.

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

[0097] As Figure 3 shown, the project data analysis method may further include: determining the strategy guidance information according to the first content. Among them, the strategy guidance information can be represented in text form and can be used to characterize the user - specific project data analysis requirements. Exemplarily, the strategy guidance information includes, for example, contents such as "pay attention to exploring the reasons for abnormal data" and "pay attention to exploring data details", etc. Among them, the strategy guidance information can be determined according to the first content through existing natural language processing algorithms.

[0098] Correspondingly, loop to determine the analysis strategy for the analysis target based on the current dataset information may include: loop to determine the analysis strategy for the analysis target based on the current dataset information and the strategy guidance information. By injecting the strategy guidance information, it is possible to support determining the analysis strategy according to the user - specific project data analysis requirements and improve the user experience.

[0099] The technical solution of the embodiment of the present disclosure supplements the project data analysis process. Through multiple rounds of conversations with users, one or at least two analysis objectives can be formulated. When there are two or more analysis objectives, each analysis objective can be analyzed in parallel to obtain the first analysis result. On this basis, the fourth analysis result can be obtained by analyzing according to each first analysis result. By disassembling the analysis objectives and analyzing them one by one, the length of the analysis data can be effectively controlled, and the situation of analysis hallucination can be largely avoided. In addition, the strategy guidance information can be determined through conversations with users, and the analysis strategy can be generated in combination with the strategy guidance information, which is beneficial to meeting the specific project data analysis needs of users and improving the user experience.

[0100] The project data analysis method provided by the embodiment of the present disclosure and the project data analysis method provided by the above embodiment belong to the same general concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and the same technical features have the same beneficial effects in this embodiment and the above embodiment.

[0101] In the embodiment of the present disclosure and the project data analysis method provided in the above embodiment, each optional solution can be combined. The project data analysis method provided in this embodiment can realize project data analysis based on multiple agents.

[0102] In the embodiment of the present disclosure, the analysis strategy is determined by the first agent module; the data set is queried based on the second agent module; the data set is merged based on the third agent module; the first analysis result is determined based on the fourth agent module.

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

[0104] In this embodiment, the first agent module can be used to repeatedly determine the analysis strategy for the analysis objective according to the current data set information. In response to the type of the analysis strategy belonging to data query, the second agent module can query the data set according to the analysis strategy. In response to the type of the analysis strategy belonging to data organization, the third agent module can merge the data set. In response to the type of the analysis strategy belonging to data summary, the fourth agent module can determine the first analysis result according to the current data set information.

[0105] In the embodiment of the present disclosure, by separately executing corresponding steps through multiple agent modules, the understanding of business data by traditional models can be decoupled, the requirements for the model coding ability can be reduced, so that the construction of agents can rely on general language models, the model training cost can be reduced, and the project data analysis cost can be reduced.

[0106] Exemplarily, Figure 4 is a schematic data flow diagram of a project data analysis method provided by an embodiment of the present disclosure. As Figure 4 shown, the project data analysis method provided in this embodiment may include:

[0107] First, a framework design agent can be used to determine an analysis target and strategy guidance information according to the first content in the conversation content; wherein, the first content belongs to the content input by the user in the conversation content.

[0108] Among them, the framework design agent (Planner) can have an interactive conversation with the user and can automatically generate a second content for clarifying the project data analysis requirements according to the first content input by the user. Among them, the framework design agent can determine the strategy guidance information and at least one analysis target according to the first content. In addition, the framework design agent can also generate other information according to the first content, such as the report theme, specific problems, and analysis ideas of the project data analysis report.

[0109] Exemplarily, the output of the framework design agent may include the following content:

[0110] Report theme: Comparative analysis report on the human input of each project;

[0111] Specific problems: Identify the differences in human input for each project, locate the key areas of resource allocation, and evaluate the rationality of input;

[0112] Analysis objectives and ideas:

[0113] Analysis objective 1: Comparison of total project input; Ideas: 1. Aggregate the estimated total working hours of all work items by project; 2. Count the number of participating roles and the total number of tasks for each project; 3. Generate a project input ranking list, and the 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; Ideas: 1. Calculate the per capita working hours of the project, and the query data items can include total working hours and number of participants, etc.; 2. Analyze the relationship between the demand completion rate and per capita input; 3. Compare the node transfer efficiency of high-input projects;

[0115] Analysis objective 3: Input trend analysis; Ideas: 1. Statistically analyze the working hour distribution of each project on a weekly basis; 2. Identify the time characteristics of continuously high-input projects; 3. Analyze the correlation between abnormal input fluctuations and project phases.

[0116] Among them, when continuously determining the analysis strategy, the analysis strategy can also be determined in combination with the ideas corresponding to the analysis objectives, which can further improve the rationality of the analysis strategy.

[0117] In the embodiments of the present disclosure, the framework design agent and the subsequent agents involved can generate relevant content based on the prompt technology. Among them, the content items included in the prompts corresponding to different agents can be different, and the content items can include, but are not limited to, roles, goals, skills, work processes, task descriptions, strategies, constraints, output formats, etc., and will not be enumerated here.

[0118] Then, through the first agent module, for each analysis target, the following steps can be executed in parallel: obtain the initial dataset information; and loop to determine the analysis strategy for the analysis target according to the current dataset information and the policy guidance information.

[0119] Figure 4 Among them, the first agent module can include a decision-making agent (Reasoner). Among them, for each analysis target and its train of thought, the decision-making agent loops to determine and verify the analysis strategy for the analysis target according to the current dataset information and the policy guidance information. Among them, the types of analysis strategies can include data query, data organization, data summary, etc.

[0120] Exemplarily, the output of the decision-making agent can include, for example, the following content:

[0121] Start analysis: Analysis target 1: Comparison of total project investment; Train of thought: 1. Aggregate the estimated total man-hours of all work items by project; 2. Count the number of participating roles and the total number of tasks for each project; 3. Generate a project investment ranking, and the data items to be queried can include total man-hours, number of tasks, and number of participants, etc.;

[0122] Current dataset: Empty;

[0123] Policy round: 1;

[0124] Determining the analysis strategy according to the current dataset information...

[0125] Analysis strategy:

[0126] Perform data query by project dimension, including but not limited to: ×× data; The current dataset is empty and there is no previous analysis step, so it is necessary to obtain the basic data to support the analysis target first;

[0127] Verifying the analysis strategy...

[0128] Verification result:

[0129] The current dataset is empty and there is no previous analysis step, and the analysis target requires data query by project dimension, so it is reasonable and necessary to obtain the basic data to support the analysis target first.

[0130] In response to the type of the analysis policy belonging to data query, the second agent module can query the data set according to the analysis policy and update the data set information based on the data set.

[0131] Figure 4 Among them, the second agent module may include a Data Queryer, a Query Planner, a Query Executor, and a Query Summarizer.

[0132] Among them, the data query target can be determined by the Data Queryer according to the analysis policy; the query plan can be determined by the Query Planner according to the data query target; the data query operation can be sequentially executed by the Query Executor according to the query steps in the query plan to obtain the data set. Among them, the data set can be analyzed by the Query Summarizer to obtain the second analysis result; the data set information is updated based on the data set and the second analysis result.

[0133] Among them, the Query Executor can pass through a query tool ( Figure 4 which may include Tools 1 - n), and execute the data query operation according to the query parameters. Among them, the tools may include user - built tools (such as Figure 4 Tool n in Figure 4 ), or may also include externally accessed tools (such as

[0134] Tools 1 - 2 in

[0135] ). By invoking the tool for data query, the understanding requirement of the Query Executor in the project data analysis process can be reduced, which helps to improve the success rate and accuracy of data extraction.

[0136] Data query target: Obtain the ×× data of each project.

[0137] Exemplarily, the output of the Query Planner may include the following content:

[0138] Determining the query plan according to the data query target...

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

[0140] Exemplarily, the output of the Query Executor may include the following content:

[0141] Executing data query...

[0142] Data query result: Obtain XX data and XX data.

[0143] By expanding the traditional single data extraction logic into a second agent module, with each step of the data extraction process being responsible by a dedicated agent, the overall responsibility can be minimized, thus ensuring the success rate and accuracy of data extraction.

[0144] In response to the type of analysis strategy belonging to data organization, the dataset can be merged through a third agent module, and the dataset information can be updated based on the merged dataset.

[0145] Figure 4 Among them, the third agent module can include a Data Organizer and an Organizer Summarizer. Among them, the Organizer can, through a Coder, write code statements that can be executed in the in-memory database engine according to the given dataset and specific merge operations in the analysis action, such as SQL code. Among them, the code statements can be run through the in-memory database engine to achieve the associative merge between datasets. Among them, the merged dataset can be analyzed through the Organizer Summarizer to obtain a third analysis result; the dataset information can be updated based on the merged dataset and the third analysis result.

[0146] In response to the type of analysis strategy belonging to data summarization, the first analysis result can be determined based on the current dataset information through a fourth agent module, and the loop can be ended.

[0147] Figure 4 Among them, the fourth agent module can include a Summarizer. Among them, the first analysis result can be determined based on the current dataset information through the Summarizer, and the loop can be ended. For example, the first analysis result can be obtained through the Summarizer by analyzing and summarizing according to the analysis objective and its ideas, the current dataset, the second analysis result, and the third analysis result.

[0148] In some implementation manners, the analysis objective can include at least two; the fourth analysis result can also be obtained by analyzing each first analysis result through the fourth agent module. Among them, the fourth analysis result can be obtained by analyzing each first analysis result through the Summarizer.

[0149] In the embodiments of the present disclosure, in-depth analysis for each analysis target can be achieved through an "observe-decide-execute" architecture. Among them, the query summary agent and the organization summary agent can belong to the observation part to update the current dataset information; the decision maker agent can belong to the decision part to determine the analysis strategy for the next round based on the dataset information of the current round; among them, the second agent module, the third agent module, and the fourth agent module can belong to the execution part to perform operations such as data query, data organization, and data summary.

[0150] The technical solution of the embodiments of the present disclosure can implement project data analysis based on multiple agent modules. By having multiple agent modules perform corresponding steps respectively, the understanding of business data by traditional models can be decoupled, the requirement for the model coding ability can be reduced, so that general models can be relied on for agent construction, the model training cost can be reduced, and thus the project data analysis cost can be reduced. In addition, by having each step in the data method be executed by a dedicated agent, the responsibilities of the agents can be minimized, which is beneficial to improving the success rate and accuracy of data extraction, and is beneficial to improving the depth of project data analysis, and thus the effect of project data analysis can be improved.

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

[0152] Figure 5 It is a schematic structural diagram of a project data analysis device provided in the embodiments of the present disclosure. The project data analysis device provided in this embodiment is applicable to the situation of project data analysis, for example, applicable to the situation of intelligent data report generation.

[0153] As Figure 5 shown, the project data analysis device provided in the embodiments of the present disclosure may include:

[0154] A first acquisition module 510, configured to acquire an analysis target;

[0155] A second acquisition module 520, configured to acquire initial dataset information;

[0156] A decision module 530, configured to repeatedly determine an analysis strategy for the analysis target according to the current dataset information;

[0157] A query module 540, configured to, in response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy and update the dataset information according to the dataset;

[0158] An organization module 550, configured to merge data sets in response to the type of analysis policy belonging to data organization, and update data set information based on the merged data sets;

[0159] An analysis module 560, configured to determine a first analysis result based on the current data set information and end the loop in response to the type of analysis policy belonging to data summary.

[0160] In some alternative implementation manners, a query module may be configured to:

[0161] Determine a data query target according to an analysis policy;

[0162] Determine a query plan according to the data query target;

[0163] Execute data query operations sequentially according to the query steps in the query plan to obtain a data set.

[0164] In some alternative implementation manners, the query plan includes query tools corresponding to the query steps; the query module may be configured to:

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

[0166] Execute data query operations according to the query parameters through the query tools.

[0167] In some alternative implementation manners, the project data analysis device may further include:

[0168] A tool deployment module, configured to deploy a query tool in response to the query tool not being included in a preset tool library before executing data query operations according to the query parameters through the query tool.

[0169] In some alternative implementation manners, the query module may be configured to:

[0170] Analyze the data set to obtain a second analysis result;

[0171] Update data set information according to the data set and the second analysis result.

[0172] In some alternative implementation manners, the organization module may be configured to:

[0173] Analyze the merged data sets to obtain a third analysis result;

[0174] Update data set information according to the merged data sets and the third analysis result.

[0175] In some alternative implementation manners, the analysis target includes at least two; the analysis module may further be configured to:

[0176] Analyze each first analysis result to obtain a fourth analysis result.

[0177] In some alternative implementation manners, the first acquisition module may be used to:

[0178] Determine an analysis target according to a first content in the conversation content; wherein, the first content belongs to the content input by the user in the conversation content.

[0179] In some alternative implementation manners, the first acquisition module may also be used to:

[0180] Determine policy guidance information according to the first content;

[0181] Correspondingly, the decision-making module may be used to:

[0182] Repeatedly determine an analysis policy for the analysis target according to the current data set information and the policy guidance information.

[0183] In some alternative implementation manners, the decision-making module may also be used to:

[0184] After determining the analysis policy for the analysis target, determine a verification result of the analysis policy according to the current data set information and the analysis policy;

[0185] In response to the verification result being verification passed, execute subsequent steps according to the type of the analysis policy.

[0186] In some alternative implementation manners, the analysis policy is determined by a first intelligent agent module; the data set is queried based on a second intelligent agent module; the data set is merged based on a third intelligent agent module; and the first analysis result is determined based on a fourth intelligent agent module.

[0187] The project data analysis device provided by the embodiments of the present disclosure can execute the project data analysis method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the execution of the method.

[0188] It should be noted that the various units and modules included in the above 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 the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the embodiments of the present disclosure.

[0189] Next, refer to Figure 6 , which shows an electronic device suitable for implementing the embodiments of the present disclosure (such as Figure 6Schematic structural diagram of the terminal device or server) 600 therein. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present disclosure.

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

[0191] Generally, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display, a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 6 the electronic device 600 with various devices is shown, it should be understood that it is not required to implement or include all the shown devices. Instead, more or fewer devices may be implemented or included.

[0192] Specifically, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above functions defined in the project data analysis method of the embodiments of the present disclosure are executed.

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

[0194] The embodiments of the present disclosure provide a storage medium storing computer-executable instructions, and when the computer-executable instructions are executed by a computer processor, they can be used to execute the project data analysis method provided by the above embodiments.

[0195] It should be noted that the above storage medium of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a flash memory (FLASH), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores executable instructions, and the executable instructions may be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable executable instructions are carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit executable instructions for use by or in combination with an instruction execution system, apparatus, or device. The executable instructions included on the storage medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination of the above.

[0196] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0197] The above storage medium can be included in the above electronic device; or it can exist separately without being assembled into the electronic device.

[0198] The above storage medium carries one or more executable instructions. When the above one or more executable instructions are executed by the electronic device, the electronic device is caused to:

[0199] Obtain an analysis target; obtain initial dataset information; repeatedly determine an analysis strategy for the analysis target based on the current dataset information; in response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy and update the dataset information based on the dataset; in response to the type of the analysis strategy belonging to data organization, merge the datasets and update the dataset information based on the merged datasets; in response to the type of the analysis strategy belonging to data summary, determine a first analysis result based on the current dataset information and end the loop.

[0200] The executable instructions for performing the operations of the present disclosure can be written in one or more programming languages or combinations thereof. The above programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include 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, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through 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., by connecting through an Internet service provider via the Internet).

[0201] The embodiments of the present disclosure also provide a computer program product, including a computer program which, when executed by a processor, can implement the item data analysis method provided in any embodiment of the present disclosure.

[0202] Among them, the computer program product includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for executing the project data analysis method. Among them, the program codes can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program codes can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0203] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can also occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for executing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0204] The units involved in the embodiments described in the present disclosure can be implemented in software or in hardware. Among them, the names of the units and modules do not constitute a limitation on the units and modules themselves in some cases.

[0205] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used 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 the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection 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 include, 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 a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM or Flash Memory), an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

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

[0208] Obtain an analysis target;

[0209] Obtain initial dataset information;

[0210] Repeatedly determine an analysis strategy for the analysis target according to the current dataset information;

[0211] In response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy, and update the dataset information according to the dataset;

[0212] In response to the type of the analysis strategy belonging to data organization, merge the dataset, and update the dataset information according to the merged dataset;

[0213] In response to the type of the analysis strategy belonging to data summarization, determine a first analysis result according to the current dataset information, and end the loop.

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

[0215] In some alternative implementation manners, the querying the dataset according to the analysis strategy includes:

[0216] Determine a data query target according to the analysis strategy;

[0217] Determine a query plan according to the data query target;

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

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

[0220] In some alternative implementation manners, the query plan includes a query tool corresponding to the query step; the executing the data query operation includes:

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

[0222] Execute a data query operation according to the query parameters through the query tool.

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

[0224] In some alternative implementation manners, before the executing the data query operation according to the query parameters through the query tool, further including:

[0225] In response to the query tool not being included in a preset tool library, deploy the query tool.

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

[0227] In some alternative implementation manners, the updating the dataset information according to the dataset includes:

[0228] Analyze the dataset to obtain a second analysis result;

[0229] Update the dataset information according to the dataset and the second analysis result.

[0230] According to one or more embodiments of the present disclosure, a method for project data analysis is provided, further including:

[0231] In some alternative implementation manners, updating the dataset information according to the merged dataset includes:

[0232] Analyzing the merged dataset to obtain a third analysis result;

[0233] Updating the dataset information according to the merged dataset and the third analysis result.

[0234] According to one or more embodiments of the present disclosure, a method for project data analysis is provided, further including:

[0235] In some alternative implementation manners, the analysis target includes at least two; the method further includes:

[0236] Analyzing each of the first analysis results to obtain a fourth analysis result.

[0237] According to one or more embodiments of the present disclosure, a method for project data analysis is provided, further including:

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

[0239] Determining the analysis target according to the first content in the conversation content; wherein, the first content belongs to the content input by the user in the conversation content.

[0240] According to one or more embodiments of the present disclosure, a method for project data analysis is provided, further including:

[0241] In some alternative implementation manners, determining the policy guidance information according to the first content;

[0242] The loop of determining the analysis strategy for the analysis target according to the current dataset information includes:

[0243] Looping to determine the analysis strategy for the analysis target according to the current dataset information and the policy guidance information.

[0244] According to one or more embodiments of the present disclosure, a method for project data analysis is provided, further including:

[0245] In some alternative implementation manners, after determining the analysis strategy for the analysis target, it further includes:

[0246] Determining the verification result of the analysis strategy according to the current dataset information and the analysis strategy;

[0247] In response to the verification result being a pass, subsequent steps are executed according to the type of the analysis strategy.

[0248] According to one or more embodiments of the present disclosure, a method for project data analysis is provided, further including:

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

[0250] According to one or more embodiments of the present disclosure, a device for project data analysis is provided, and the device includes:

[0251] A first acquisition module, configured to acquire an analysis target;

[0252] A second acquisition module, configured to acquire initial data set information;

[0253] A decision module, configured to repeatedly determine an analysis strategy for the analysis target according to the current data set information;

[0254] A query module, configured to, in response to the type of the analysis strategy belonging to data query, query a data set according to the analysis strategy and update the data set information according to the data set;

[0255] An organization module, configured to, in response to the type of the analysis strategy belonging to data organization, merge the data set and update the data set information according to the merged data set;

[0256] An analysis module, configured to, in response to the type of the analysis strategy belonging to data summary, determine a first analysis result according to the current data set information and end the loop.

[0257] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principle. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solution formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, a technical solution formed by mutually replacing the above features with technical features having similar functions disclosed in the present disclosure (but not limited to).

[0258] Moreover, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the foregoing discussion, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented separately or in any suitable subcombination in multiple embodiments.

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

Claims

1. A method for project data analysis, characterized in that, Including: Obtain an analysis target; Obtain initial dataset information; Loop to determine an analysis strategy for the analysis target according to the current dataset information; In response to the type of the analysis strategy belonging to data query, query the dataset according to the analysis strategy, and update the dataset information according to the dataset; In response to the type of the analysis strategy belonging to data organization, merge the dataset, and update the dataset information according to the merged dataset; In response to the type of the analysis strategy belonging to data summary, determine a first analysis result according to the current dataset information, and end the loop.

2. The method according to claim 1, wherein The querying the dataset according to the analysis strategy includes: Determine a data query target according to the analysis strategy; Determine a query plan according to the data query target; Execute data query operations in sequence 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 executing the data query operation includes: Extract query parameters in the data query target; Execute data query operations through the query tool according to the query parameters.

4. The method according to claim 3, characterized in that, Before the executing the data query operation through the query tool according to the query parameters, it further includes: In response to the query tool not being included in the preset tool library, deploy the query tool.

5. The method according to claim 1, characterized in that The updating the dataset information according to the dataset includes: Analyze the dataset to obtain a second analysis result; Update the dataset information according to the dataset and the second analysis result.

6. The method according to claim 1, characterized in that, The updating the dataset information according to the merged dataset includes: Analyze the merged dataset to obtain a third analysis result; Update the dataset information according to the merged dataset and the third analysis result.

7. The method according to claim 1, wherein The analysis target includes at least two; the method further includes: Analyze each of the first analysis results to obtain a fourth analysis result.

8. The method according to claim 1, characterized in that, The obtaining the analysis target includes: Determine the analysis target according to the first content in the conversation content; wherein, the first content belongs to the content input by the user in the conversation content.

9. The method according to claim 8, wherein It further includes: Determine strategy guidance information according to the first content; The loop to determine an analysis strategy for the analysis target according to the current dataset information includes: Loop to determine an analysis strategy for the analysis target according to the current dataset information and the strategy guidance information.

10. The method according to claim 1, characterized in that, After the determining the analysis strategy for the analysis target, it further includes: Determine a verification result of the analysis strategy according to the current dataset information and the analysis strategy; In response to the verification result being verification passed, execute subsequent steps according to the type of the analysis strategy.

11. The method according to claim 1, wherein The analysis strategy is determined by a first intelligent agent module; the dataset is queried based on a second intelligent agent module; the dataset is merged based on a third intelligent agent module; the first analysis result is determined based on a fourth intelligent agent module.

12. A project data analysis device, characterized in that, Including: A first obtaining module, configured to obtain an analysis target; A second acquisition module, configured to acquire initial dataset information; A decision-making module, configured to repeatedly determine an analysis strategy for the analysis target according to the current dataset information; A query module, configured to, in response to the type of the analysis strategy belonging to data query, query a dataset according to the analysis strategy and update the dataset information according to the dataset; An organization module, configured to, in response to the type of the analysis strategy belonging to data organization, merge the dataset and update the dataset information according to the merged dataset; An analysis module, configured to, in response to the type of the analysis strategy belonging to data summarization, determine a first analysis result according to the current dataset information and end the loop.

13. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device, configured to store one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the project data analysis method according to any one of claims 1-11.

14. A storage medium containing computer-executable instructions, which are used to execute the project data analysis method according to any one of claims 1-11 when executed by a computer processor.

15. 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 according to any one of claims 1-11.

Images