Report generation method and system, electronic device, and storage medium

Abstract

Embodiments of the present disclosure provide a report generation method and system, an electronic device, and a storage medium. The report generation method comprises: acquiring requirement text information of a report to be generated in a target application scenario; performing requirement intent recognition on the requirement text information, to acquire a report parameter matching the report to be generated; on the basis of the target application scenario, selecting and arranging a preset intelligent agent, to obtain an intelligent agent call chain; on the basis of the report parameter, performing chain-type calling on the preset intelligent agent in the intelligent agent call chain, to generate a report matching the requirement text information. The present method can automatically and quickly generate a report matching a user requirement, effectively increasing report generation efficiency. Using the present method to generate a report does not require manual data acquisition and analysis; efficiency is higher, and costs are lower.

Description

Report generation method, system, electronic device and storage medium

[0001] This disclosure claims priority to Chinese patent application number 202410224007.5, filed with the Patent Office of China on February 28, 2024, entitled “Report Generation Method, System, Electronic Device and Storage Medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the field of computer technology, and in particular to a report generating method, a report generating system, an electronic device, a storage medium, and a computer program product. Background Art

[0003] In real life and work, it is often necessary to generate various types of insight reports to solve and answer various problems. For example, for national growth project analysis reports, they are used to answer questions such as whether the traffic in certain industries in the implementing country is sufficient, which industry directions or regions are worthy of increased investment, and which industry directions or regions need to reduce investment. For another example, for industry development trend reports, they are used to display the current hot trends in the industry, the national differences in the corresponding trends, and suggestions for future development of the industry. For another example, strategic analysis reports in the field of e-commerce are used to combine the national economic macro-situation and the competitive situation to produce strategic analysis results. In the existing technology, reports in various fields and solving various problems are usually collected by data analysts in the corresponding fields, and data statistics and analysis are manually performed. After that, the corresponding reports are manually generated. In the existing technology, the method of manually generating reports has at least the disadvantages of high cost and long cycle.

[0004] It can be seen that the report generation method in the prior art still needs to be improved. Summary of the Invention

[0005] The embodiments of the present disclosure provide a report generation method that can quickly generate reports according to user needs with low cost and high efficiency.

[0006] Accordingly, the embodiments of the present disclosure also provide a report generation system, an electronic device, a storage medium, and a computer program product to ensure the implementation and application of the above-mentioned report generation method.

[0007] In order to solve the above problems, the present disclosure discloses a report generation method, which includes:

[0008] Obtain the required text information of the report to be generated in the target application scenario;

[0009] Identify the demand intent of the demand text information and obtain report parameters that match the report to be generated;

[0010] Select and arrange preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain;

[0011] Based on the report parameters, the preset agent in the agent call chain is chain-called to generate a report matching the required text information.

[0012] The present disclosure discloses a report generation method, which is applied to a client. The method includes:

[0013] Obtain the target application scenario and requirement text information of the report to be generated;

[0014] The target application scenario and the requirement text information are sent to a preset server, so that the preset server performs the following report generation operations based on the target application scenario and the requirement text information: performing requirement intent recognition on the requirement text information to obtain report parameters that match the report to be generated; selecting and arranging preset agents based on the target application scenario to obtain an agent call chain; and chain-calling the preset agents in the agent call chain based on the report parameters to generate a report that matches the requirement text information;

[0015] Obtaining the report generated by the preset server;

[0016] The report is presented.

[0017] The present disclosure embodiment discloses a report generation system, which includes: a client and a server, wherein:

[0018] The client is configured to obtain target application scenarios and required text information of a report to be generated, and send the target application scenarios and required text information to the server;

[0019] The server is configured to receive the target application scenario and the requirement text information, identify the requirement intent of the requirement text information, and obtain report parameters that match the report to be generated;

[0020] The server is further configured to select and arrange preset agents based on the target application scenario to obtain an agent call chain;

[0021] The server is further configured to perform a chain call on the preset agent in the agent call chain based on the report parameters to generate a report matching the required text information;

[0022] The client is further used to obtain the report and display the report.

[0023] An embodiment of the present disclosure also discloses an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the embodiment of the present disclosure.

[0024] The embodiment of the present disclosure further discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the embodiment of the present disclosure.

[0025] The present disclosure also discloses a computer program product, including a computer program / computer executable instructions, wherein the computer program / computer executable instructions, when executed by a processor in an electronic device, implement the method described in the present disclosure.

[0026] Compared with the prior art, the embodiments of the present disclosure have the following advantages:

[0027] After obtaining the required text information for the report to be generated in the target application scenario, the system first identifies the required intent of the required text information and obtains report parameters that match the report to be generated, thereby accurately understanding the user's needs. Then, based on the target application scenario, it selects and arranges preset agents to obtain an agent call chain. Finally, based on the report parameters, it chain-calls the preset agents in the agent call chain to generate a report that matches the required text information. This method can automatically and quickly generate reports that match user needs, effectively improving report generation efficiency. Generating reports using this method eliminates the need for manual data collection and analysis, resulting in higher efficiency and lower costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] FIG1 is a flowchart of a report generation method disclosed in an embodiment of the present disclosure;

[0029] FIG2 is a flowchart of another step of the report generation method disclosed in an embodiment of the present disclosure;

[0030] FIG3 is a schematic diagram of a client interface in the report generation method disclosed in an embodiment of the present disclosure;

[0031] FIG4 is a schematic diagram of a report displayed by a client in the report generation method disclosed in an embodiment of the present disclosure;

[0032] FIG5 is an interactive diagram of a report generation system disclosed in an embodiment of the present disclosure;

[0033] FIG6 is a schematic diagram of an implementation architecture of a report generation system disclosed in an embodiment of the present disclosure;

[0034] FIG7 is a schematic diagram of a report generation process in an application scenario of the report generation system disclosed in an embodiment of the present disclosure;

[0035] FIG8 is a schematic structural diagram of an exemplary apparatus provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] In order to make the above-mentioned objects, features and advantages of the present disclosure more obvious and easy to understand, the present disclosure is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0037] The report generation method disclosed in the embodiments of the present disclosure can be applied to generate various types of reports in various application scenarios. For example, in the national growth analysis scenario of a cross-border e-commerce website, the website assistant needs to answer questions such as whether the traffic of a certain industry in a specified country is sufficient, which industries are worth increasing investment, and which industries need to reduce investment. For another example, some services need to produce trend reports such as what are the hot trends in a specified industry and what are the national differences in these trends. For another example, in the field of e-commerce, when website sales maintain merchant relationships, they need to provide future development recommendation reports based on the merchant’s operating conditions on the website and the industry trends of the merchant’s main categories. For another example, when conducting a strategic analysis of cross-border e-commerce, it is necessary to generate a strategic analysis report based on the economic macro-situation and market competition conditions of each country.

[0038] In specific implementations, the report generation method disclosed in the embodiments of this disclosure abstracts a common report generation process and automatically configures intelligent agents with corresponding capabilities at each stage of the report generation process to complete various AI (Artificial Intelligence) tasks such as question and answer understanding, data extraction, content generation, and text summarization. Optionally, the implementation of the intelligent agent includes, but is not limited to, any of the following: components, applications, service interfaces, and functional modules.

[0039] In addition, in response to different report content output requirements, by providing the automated orchestration capabilities of intelligent entities, dynamic assembly of report generation processes can be achieved, thereby understanding and responding to various report generation requirements and automatically generating reports that match user needs.

[0040] The report generation method disclosed in the embodiment of the present disclosure is applied to a server, as shown in FIG1 , and includes steps 102 to 108 .

[0041] Step 102: Obtain the required text information of the report to be generated in the target application scenario.

[0042] In some optional embodiments, the report generation method disclosed in the embodiments of the present disclosure can be implemented via a report generation system. The report generation system includes a client and a server. A user can select an application scenario through the client, enter textual information about the report to be generated, and send the application scenario and textual information to the server. The server then executes the report generation method disclosed in the embodiments of the present disclosure, generates a report, and sends it to the client for presentation. The client can be implemented as a webpage, application, or other form.

[0043] The report generation system supports the generation of reports for a variety of application scenarios. For example, the report generation system supports the generation of reports including but not limited to the following application scenarios: user growth scenarios, merchant growth scenarios, and commodity growth scenarios. Among them, the user growth scenario can be, for example: interpreting the market of a certain industry in a certain country and generating a user growth budget control report; the merchant growth scenario can be, for example: interpreting the market segment trends of a certain industry in a certain international country and generating a merchant development opportunity analysis report; the commodity growth scenario is: industry hot spot push, market segment trend words, price value index interpretation, etc. The target application scenario is the application scenario selected by the user through the client. The application scenarios supported by the report generation system are defined according to application requirements.

[0044] The demand text information is used to describe the requirements for the report to be generated. The content of the demand text information is not limited in the embodiments of the present disclosure. For example, the demand text information can be: "X Country Clothing Industry Trend Recommendations", or "Commodity Sales Comparative Analysis", etc. In some optional embodiments, the user can select an application scenario through the client and then further input the question of interest. Accordingly, the client uses the question entered by the user as the demand text information, and sends the demand text information and the application scenario selected by the user to the server to trigger the report generation system to generate the report content of the question under the corresponding application scenario.

[0045] Step 104: identify the demand intent of the demand text information and obtain report parameters that match the report to be generated.

[0046] During implementation, user-entered requirement texts vary widely and lack standardization. To generate reports that meet user needs based on these non-standard requirements, the first challenge is to accurately understand the requirements text and obtain the clear report parameters that correspond to the report generation requirements. Then, the report can be automatically generated based on these clear report parameters.

[0047] In order to realize the automatic generation of reports based on the required text information input by the user, several application scenarios are pre-defined in the embodiment of the present disclosure, and several indicators that need to be paid attention to when generating reports are pre-defined for each application scenario as report parameters. Optionally, the report parameters include one or more of the following dimensions: region, industry, time, data analysis object, and report type. For example, for the user growth application scenario, it is necessary to pay attention to information such as region, industry, and report type; for another example, for the merchant growth application scenario, it is necessary to pay attention to information such as region, industry, and report type; for another example, for the commodity growth application scenario, it is necessary to pay attention to information such as industry, category, region, time, and growth indicator list.

[0048] Among them, the report parameters of the regional dimension include but are not limited to any one of the following: geographical areas such as countries, provinces, and cities. The report parameters of the industry dimension include but are not limited to: clothing, food, tourism, technology, etc. The report parameters of the time dimension are used to describe the generation time of the original data for generating the report. The report parameters of the data analysis object dimension vary depending on the application scenario. For example, for the commodity growth application scenario, the data analysis object can be: monthly sales volume of commodities, quarterly sales volume, etc. For another example, for the user growth application scenario, the data analysis object can be: holidays, user registration volume, etc. The report parameters of the report type dimension are used to describe the type of report generated, including but not limited to any one of the following: macro reports, trend charts, theme summaries, analytical insights, etc.

[0049] In the embodiment of the present disclosure, the report parameters concerned in each application scenario are determined according to the specific application scenario. In the embodiment of the present disclosure, there is no restriction on the report parameters that need to be concerned in each application scenario.

[0050] The report parameters can be expressed using preset keywords for the corresponding dimension, or by words with corresponding attributes. For example, the report parameter for the region dimension can be expressed by "a certain country", and the report parameter for the report type dimension can be expressed by "trend", "popularity", etc.

[0051] When the present disclosure is specifically implemented, the following two methods may be used to identify the demand intent of the demand text information and obtain report parameters that match the report to be generated.

[0052] 1. Content Generation Method

[0053] In some optional embodiments, the requirement intention is identified on the requirement text information to obtain report parameters that match the report to be generated, including: formatting a preset prompt word template corresponding to the target application scenario based on the requirement text information to obtain a first prompt word; calling a preset generative pre-trained model based on the first prompt word, so that the generative pre-trained model analyzes and extracts information according to the requirement text information to obtain report parameters.

[0054] For example, a generative pre-trained model, such as a GPT (Generative Pre-trained Transformer) model, can be used to extract report parameters from the demand text information. In the embodiment of the present disclosure, corresponding prompt words can be pre-trained for each application scenario, thereby generating a prompt word template for generating report parameters for the corresponding application scenario based on the input text. For example, a general prompt word that has been fine-tuned and tested in advance can be used as a solidified prompt word in the prompt word template, and the information that needs to be dynamically obtained can be expressed as a placeholder to generate a prompt word template. The creation process of the prompt word template can be referred to the prior art and will not be repeated here.

[0055] Optionally, the prompt word template includes at least the following: a question description, a system role description, and an answer description. The question description is used to describe the textual information required, the system role description is used to describe the report parameter dimensions that the generative pre-trained model needs to generate based on the input, and the answer description is used to describe the format of the output content of the generative pre-trained model. In some optional embodiments, the preset prompt word template for identifying the demand intent can be expressed as follows:

[0056] "question:$input

[0057] system_role: Extracts the target country, industry, and report type from the input question. Outputs in JSON format.

[0058] answer:{'country'=$country, 'industry'=$industry, 'target'=$report type}".

[0059] In this prompt word template, "$input" represents the placeholder for the required text information, "$country" represents the placeholder for the extracted country information, "$industry" represents the placeholder for the extracted industry information, and "$report type" represents the placeholder for the extracted report type parameter.

[0060] After formatting the preset prompt word template using the acquired demand text information, a report parameter extraction prompt word is generated. Then, based on the generated report parameter extraction prompt word, a generative pre-trained model is called, so that the generative pre-trained model extracts the prompt word based on the report parameter, performs a corresponding report parameter generation operation, and generates report parameters.

[0061] For example, for the user-input demand text information "Recommendations on the trend of the clothing industry in country X in the past six months", the report parameter extraction prompt words obtained after formatting the demand text information may include the following text content:

[0062] 1. Question (i.e., "question"), for example, "Development trend of clothing industry in country X";

[0063] 2. System role (i.e., "system_role"), for example, could be: "Extract target country, industry, and target parameters from the input question and output them in JSON format";

[0064] 3. Response (i.e., "answer"), for example, can be: "The output content includes: region, industry, and report type, output in three lines, where region is the extracted target country, industry is the extracted industry, and report type is the extracted target parameter."

[0065] Based on the formatted report parameter extraction prompt, the generative pre-trained model is invoked to extract the report parameters, resulting in the following output: Region = "Country X", Industry = "Apparel", Report Type = "Trend Analysis". "Country X", "Apparel", and "Trend Analysis" represent report parameters of different dimensions.

[0066] (2) Keyword extraction method

[0067] In some optional embodiments, the demand intent identification of the demand text information and the acquisition of report parameters that match the report to be generated include: identifying preset keywords included in the demand text information through word matching technology; and obtaining report parameters based on the identified preset keywords.

[0068] In other optional embodiments, a number of keywords can be set in advance according to the report parameters of various dimensions to form a keyword library. For example, keywords such as country name, province name, industry name, report type name, time unit, etc. are set to form a keyword library. During the report generation stage, the demand text information input by the user is first segmented to obtain a number of segmented words included in the demand text information; then, each segmented word is matched with the keywords in the keyword library for similarity, and based on the matching results, the preset keywords included in the demand text information are identified; then, based on the identified keywords and the preset report parameters corresponding to the keywords, the report parameters identified in the demand text information are obtained.

[0069] For example, if the keyword library includes "country X," "apparel," "quarter," and "trend analysis," and the word segmentation results for the demand text "trend suggestions for the apparel industry in country X" include the following words: "country X," "apparel," "industry," "trend," and "suggestion," similarity matching can identify that the demand text includes the following keywords: "country X," "apparel," and "trend analysis." Furthermore, the report parameters corresponding to the demand text can be expressed as: "country X," "apparel," and "trend analysis," where "country X" represents the value of the region-dimensional report parameter, "apparel" represents the value of the industry-dimensional report parameter, and "trend analysis" represents the value of the report type-dimensional report parameter.

[0070] Optionally, the step of performing demand intent recognition on the demand text information and obtaining report parameters that match the report to be generated can be executed by a preset intelligent agent for performing intent recognition.

[0071] In other embodiments, other methods may be used to extract preset information from the demand text information to obtain report parameters, which will not be listed one by one in the embodiments of this disclosure.

[0072] Step 106: Select and arrange the preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain.

[0073] In some optional embodiments, the preset agent is created by performing functional decomposition and aggregation processing on the report generation process of the preset application scenario to obtain multiple atomic capabilities after deduplication, and creating a preset agent corresponding to the atomic capabilities, wherein the implementation method of the preset agent includes: implementation based on a generative pre-trained model call or implementation based on a service interface call. In the embodiments of the present disclosure, the atomic capability is a function implemented by an agent, which can be artificially divided according to the specific application scenario.

[0074] In the embodiments of the present disclosure, a general report generation process is abstracted by analyzing the report generation process of several application scenarios. At the same time, adaptive intelligent agents are set up in each link of the report generation process to complete the tasks of each link from basic data acquisition, data analysis and processing, text induction, to report output. In different application scenarios, the links included in the report generation process can be different, and the input and output content of each link can be different. In the embodiments of the present disclosure, several intelligent agents are pre-set by analyzing the report generation process of several application scenarios.

[0075] For example, by referring to the software development functional module design plan, the report generation process supported by the report generation system is functionally decomposed to obtain one or more tasks, each of which implements an atomic capability. Each report generation process is then decomposed into one or more atomic capabilities that are implemented in sequence. Each atomic capability obtained by decomposition corresponds to a specific task and has specified inputs and outputs. In some optional embodiments, functional decomposition can be performed with the goal of decoupling tasks and reducing duplication.

[0076] Furthermore, the atomic capabilities obtained by decomposing each application scenario are aggregated, and the atomic capabilities with the same function are regarded as the capabilities of an agent, and an agent that implements the atomic capabilities is created. In order to make the atomic capabilities applicable to different application scenarios, the inputs and outputs of the atomic capabilities related to the application scenarios can be defined as variables of the agent. For example, the report generation process of application scenario S1 is decomposed into n atomic capabilities S11, S12, ..., S1n, and the report generation process of application scenario S2 is decomposed into S21, S22, ..., S2m, and m atomic capabilities, where m and n are positive integers. If the principle capability S1n obtained by decomposing application scenario S1 is to format input text to generate a report in a first format, and the principle capability S2m obtained by decomposing application scenario S2 is also to format input text to generate a report in a first format, then only one preset agent can be created. This preset agent is used to format input text to generate a report in a first format, and this preset agent can be reused by application scenarios S1 and S2.

[0077] Optionally, the preset intelligent agent includes any one or more of the following: an intelligent agent for generating database query statements, an intelligent agent for formatting data into a report in a target format, an intelligent agent for executing specified database query instructions to obtain data within the system, and an intelligent agent for calling a preset service interface to obtain data outside the system.

[0078] For example, if the report generation system only supports user growth and merchant growth scenarios, the report generation process for the user growth scenario can be broken down into: generating database query statements, executing database query statements to read the database, data retrieval, user metric drill-down analysis, comparative analysis, trend analysis, generating a national summary, and generating an industry summary. The report generation process for the merchant growth scenario can be broken down into: generating database query statements, executing database query statements to read the database, data retrieval, merchant metric drill-down analysis, comparative analysis, trend analysis, generating a national summary, generating an industry summary, and generating a hot search and hot selling summary. The atomic capabilities corresponding to each of these tasks for these two scenarios are aggregated by function to yield the following atomic capabilities: generating database query statements, executing database query statements to read the database, data retrieval, user metric drill-down analysis, merchant metric drill-down analysis, comparative analysis, trend analysis, generating a national summary, generating an industry summary, and generating a hot search and hot selling summary. For each aggregated task, an intelligent agent (such as the component corresponding to each task) is created to realize the atomic capabilities corresponding to the corresponding task, and multiple intelligent agents can be obtained.

[0079] As can be seen from the above agent creation method, each agent has specific capabilities and designated inputs and outputs. These agents can be reused in multiple application scenarios, thereby improving the development efficiency of the report generation system and reducing development costs.

[0080] In some embodiments of the present disclosure, each preset agent can be encapsulated as a component in the report generation system for system program call.

[0081] During the development of the report generation system, the preset intelligent agents that implement each of the atomic capabilities can be implemented based on the call of a generative pre-trained model, or based on the call of a service interface, or based on a completely independently written program code. For example, one or some of the preset intelligent agents can be implemented by reading prompt words through program code, and then calling a generative pre-trained model based on the read prompt words. For another example, one or some of the preset intelligent agents can be implemented by reading input content through program code, and then calling a query service interface of a specified search engine with the input content as an entry parameter. In the embodiments of the present disclosure, there is no limitation on the implementation method of the preset intelligent agent.

[0082] As mentioned above, agents are derived from the decomposition of the report generation process. As the reverse operation of decomposition, during the report generation phase, agents are selected from the pre-set agents and orchestrated according to the requirements of a specific application scenario, enabling dynamic assembly of the report generation process. Subsequently, based on the assembly results, the selected agents are sequentially invoked to perform the corresponding tasks, generating a report for the corresponding application scenario.

[0083] In actual application, the report generation processes corresponding to different application scenarios may be different. Therefore, it is necessary to determine in real time the various links of the report generation process for the target application scenario and the preset agents corresponding to each link based on the target application scenario, so as to determine which preset agents need to be called in sequence when generating the report for the target application scenario. The preset agents that need to be called in sequence when generating the report for the target application scenario constitute an agent call chain. The process of determining which preset agents need to be called in sequence when generating the report for the target application scenario is the process of selecting and arranging the preset agents.

[0084] The method of selecting and arranging preset agents based on the target application scenario to obtain an agent call chain includes but is not limited to any of the following methods.

[0085] (1) Agent selection and arrangement based on configuration information

[0086] In some optional embodiments, the preset agents are selected and arranged based on the target application scenario to obtain an agent call chain, including: obtaining an agent call chain based on the agent configuration information of the target application scenario, wherein the agent configuration information is used to describe the preset agents that need to be called in sequence when generating a report for the target application scenario.

[0087] In some embodiments of the present disclosure, descriptive information may be further set for a specified application scenario, and the descriptive information is used to describe the preset agents that need to be called in sequence when generating a report for the corresponding application scenario. In the embodiments of the present disclosure, the descriptive information pre-set for each application scenario is recorded as "agent configuration information." The preset agents that need to be called in sequence when generating a report for the corresponding application scenario are set based on the requirements of the application scenario, the input and output content of each application scenario, and the capabilities of each preset agent.

[0088] Taking the merchant growth application scenario of an e-commerce website as an example, the following three agents can be set up to work together: a data collection agent, a data understanding agent, and an interpretation result generation agent. Among them, the data collection agent is used to connect to the designated on-site database, generate database query statements based on user questions, and interact with the database based on the generated database query statements to obtain the basic data required for generating reports; the data understanding agent is used to understand and process the acquired basic data to obtain indicator values ​​corresponding to user needs; the interpretation result generation agent is used to generate the final report content based on the indicator values ​​obtained from the data processing. Among them, the data collection agent, the data understanding agent, and the interpretation result generation agent can be fully or partially implemented by pre-writing generation prompt words to call a generative pre-training model.

[0089] In other application scenarios, two types of data collection agents can also be created, one for reading the basic data on a specified website, and the other for calling an off-site search engine interface to obtain off-site basic data in real time; accordingly, the data understanding agent can be used to understand and process the acquired on-site basic data and off-site basic data to obtain indicator values ​​corresponding to user needs.

[0090] For example, according to the capabilities of the preset agents, each link in the report generation process of the target application scenario S3 can be broken down into three tasks. These three task blocks can be respectively implemented by preset agents A, B, and C with corresponding capabilities. Then, the agent configuration information of the target application scenario S3 can be expressed as: S3 = {A, B, C}, where A, B, and C respectively represent the three agents that need to be called in sequence when generating the report of the target application scenario S3. Correspondingly, based on the agent configuration information of the target application scenario S3, the call chain of the agent of the target application scenario S3 can be determined as: S3 = A→B→C.

[0091] For example, in an application scenario where valuable growth insight reports are provided to smart assistant applications for merchants and industries, the report generation process for the growth insight report includes the following steps in sequence: obtaining on-site industry data from an e-commerce website, obtaining off-site industry data from a search engine, and generating a growth insight report based on the on-site and off-site data. The agent configuration information in this application scenario can be described as a sequence of an on-site data collection agent, an off-site data collection agent, and a report generation agent. In the sequence, the on-site data collection agent is used to obtain on-site industry data from an e-commerce website; the off-site data collection agent is used to obtain off-site industry data from a specified search engine; and the report generation agent is used to generate a growth insight report based on the input industry data. During the report generation stage, the above sequence can be used to determine the various intelligent agents that need to be called in sequence when generating the growth insight report. The intelligent agents called in sequence constitute an intelligent agent call chain corresponding to the corresponding application scenario, for example, expressed as: (A1, A2)→B1, where A1 and A2 represent the on-site data collection intelligent agent and the off-site data collection intelligent agent respectively, and B1 represents the report generation intelligent agent.

[0092] (2) Using generative pre-trained models for agent selection and orchestration

[0093] In some optional embodiments, the preset agents are selected and arranged based on the target application scenario to obtain an agent call chain, including: based on the target application scenario and the capability description text of the preset agents, calling a generative pre-trained model to generate an agent call chain corresponding to the target application scenario.

[0094] The generative pre-trained model has a powerful content generation capability. In some optional embodiments, by pre-training prompt words, the generative pre-trained model can generate an agent call chain corresponding to the target application scenario based on the agent capability description text given in the prompt words and the target application scenario information. The capability description text includes but is not limited to: the identifier of each preset agent and the capability description text of each preset agent. Taking the LangChain framework (a programming framework that helps use large language models in applications) as an example to implement agent selection and arrangement, the preset agent can be used as a component, and the preset agent can be pre-configured in the LangChain framework, as well as the agent arrangement prompt word template, so that the framework has the ability to automatically generate a call chain composed of preset agents, so that after each agent in the call chain is called according to the dependency relationship, a report on the target application scenario can be generated.

[0095] For the specific implementation of configuring the preset intelligent agent in the LangChain framework, please refer to the method of using the LangChain framework in the prior art, which will not be repeated in the embodiments of this disclosure.

[0096] Step 108: Based on the report parameters, chain call the preset agent in the agent call chain to generate a report that matches the required text information.

[0097] After obtaining the calling chain of the intelligent agent matching the current demand text information in the above steps, each intelligent agent in the calling chain is called in sequence to generate a report matching the current demand text information.

[0098] Taking the preceding steps for intent recognition and report generation, the agent call chain can be represented as: E→F→G, where E represents the data query statement generation agent, F represents the data collection agent, and G represents the report generation agent. In this step, the data query statement generation agent E is first called to generate a data query statement. Next, the data collection agent F is called to execute the query statement, perform a data query, and obtain the query data. Finally, the report generation agent G is called to format the query data output by the data collection agent F to obtain the specified report.

[0099] Due to different application scenarios, the number and type of pre-set agents included in the agent call chain are usually different. On the other hand, the capabilities and creation methods of different pre-set agents vary, resulting in different calling methods for pre-set agents.

[0100] In some optional embodiments, based on the report parameters, the preset agent in the agent call chain is chain-called to generate a report matching the required text information, including: in order from the beginning to the end, the agents in the call chain are sequentially used as the current agent, and the following calling operations are performed on the current agent: calling the current agent to obtain the output content of the current step call; calling the current agent based on the report parameters to obtain the output content of the current step call; calling the current agent based on the output content generated by one or more previous step call operations to obtain the output content of the current step call; calling the current agent based on the output content generated by one or more previous step call operations and one or more parameters in the report parameters to obtain the output content of the current step call.

[0101] In some embodiments of the present disclosure, the calling process of each preset agent in the call chain can be executed by a preset agent scheduling task. The preset agent may have input content or may not have input content. The input content and output content of the preset agent are predetermined according to the capabilities of the preset agent and are declared in the report generation system. When calling the current agent, the agent scheduling task first determines whether the current agent depends on the input content. If it depends on the input content, the value of the dependent input content is first obtained, and then the value of the obtained input content is used as the calling parameter of the current agent to call the current agent; if it does not depend on the input content, the current agent is directly called.

[0102] For example, for a preset intelligent agent used to read external data required to generate a report, its input content comes from user input, for example, its input content is one or more report parameters extracted from the required text information input by the user, and its output content is a document obtained by searching from a specified search engine.

[0103] For example, for a preset agent used to generate database query statements, this type of agent can set prompt words for each combination of database and application scenario. Therefore, when this type of preset agent is called, the generative pre-trained model is called based on the preset prompt words to generate a database query statement.

[0104] For another example, a pre-configured agent for data analysis may analyze and process data read by other agents to generate the indicator values ​​required for a report. The input content of this pre-configured agent may be the output content of one or more pre-configured agents. In some optional embodiments, the input content of this pre-configured agent may include both the output content of the pre-configured agents and the report parameters.

[0105] After being called, each agent executes according to the preset program flow to complete the corresponding task. In the specific implementation process, the program flow of each preset agent is set according to the specific capability requirements. In the embodiments of the present disclosure, there is no restriction on the program flow of each preset agent.

[0106] As mentioned above, the preset agent can be implemented based on the call of a generative pre-trained model, the call of a service interface, or the implementation of self-written program code. The execution logic of the agent implemented in different ways will be different after being called.

[0107] For example, for a preset intelligent agent implemented based on a service interface call, the input content can be read first to obtain the call parameter value of the preset service interface; then, the preset service interface (such as a search engine interface) is called based on the call parameter value to obtain the search results; then, the output content is generated according to the search results and the output is completed.

[0108] For another example, an intelligent agent implemented based on a generative pre-trained model call can directly read the corresponding preset prompt words, and then call the preset generative pre-trained model based on the read preset prompt words to generate output content.

[0109] For another example, for an intelligent agent implemented based on a generative pre-trained model call, the corresponding prompt word template and input content can be obtained first; then, the obtained prompt word template is formatted based on the read input content to generate a prompt word; then, the preset generative pre-trained model is called based on the generated prompt word to generate output content.

[0110] In some embodiments of the present disclosure, when an agent call chain is generated using the LangChain framework, the LangChain framework can also be used to execute chain calls on each preset agent in the agent call chain. The specific manner in which the LangChain framework executes chain calls on each preset agent in the agent call chain is described in the prior art and will not be further described here.

[0111] In summary, the report generation method disclosed in the embodiment of the present disclosure, after obtaining the demand text information of the report to be generated in the target application scenario, first identifies the demand intent of the demand text information, obtains the report parameters that match the report to be generated, and realizes accurate understanding of user needs; then, based on the target application scenario, the preset intelligent agents are selected and arranged to obtain an intelligent agent call chain; finally, based on the report parameters, the preset intelligent agents in the intelligent agent call chain are chain-called to generate a report that matches the demand text information. This method can automatically and quickly generate a report that matches the user's needs, effectively improving the efficiency of report generation. Generating reports using this method does not require manual data collection and analysis, which is more efficient and less costly.

[0112] On the other hand, by disassembling and aggregating the report generation process in advance, we can build preset intelligent agents corresponding to atomic capabilities, and orchestrate the intelligent agents in real time during the report generation stage to realize the dynamic assembly of the report generation process, and obtain the intelligent agent call chain, which effectively realizes the reuse of preset intelligent agents, improves the energy-saving performance of the report generation system, and realizes the flexible expansion of the report generation process, thereby improving the functional expansion capability of the report generation system.

[0113] Based on the above embodiment, the present disclosure also discloses a report generation method, which is applied to a client of a report generation system. As shown in FIG2 , the report generation method includes steps 202 to 208 .

[0114] Step 202: Obtain target application scenario and required text information of the report to be generated.

[0115] In some optional embodiments, a selection list of application scenarios and a requirements editing area can be provided on the client, and the application scenarios supported by the report generation system can be displayed in the selection list, as shown in Figure 3. By clicking on the selection list 310, the user can select the application scenario for which a report is to be generated and enter the requirements text for the report to be generated in the requirements editing area 320. The client detects the selected status of the application scenario in the selection list to obtain the target application scenario for the report to be generated. At the same time, the input text in the requirements editing area is read as the requirements text information for the report to be generated.

[0116] In other optional embodiments, the client can also obtain the target application scenario and required text information of the report to be generated through other human-computer interaction methods. In the embodiments of the present disclosure, the specific implementation method of obtaining the target application scenario and required text information of the report to be generated is not limited.

[0117] Step 204: Send the target application scenario and the requirement text information to the preset server, so that the preset server performs the following report generation operations based on the target application scenario and the requirement text information: identify the requirement intent of the requirement text information, and obtain report parameters that match the report to be generated; select and arrange the preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain; based on the report parameters, chain call the preset intelligent agents in the intelligent agent call chain to generate a report that matches the requirement text information.

[0118] The preset server is the server of the report generation system.

[0119] In some optional embodiments, a button for submitting a report generation request may be set on the client. When the button is triggered, the client encapsulates the target application scenario and the required text information into a report generation request and sends it to the preset server.

[0120] In other optional embodiments, the client may also use other methods to send the target application scenario and the required text information to the preset server. In the embodiments of the present disclosure, there is no limitation on the specific implementation method of the client sending the target application scenario and the required text information to the preset server.

[0121] In some optional embodiments, after the preset server receives the report generation request sent by the client, it obtains the target application scenario and the required text information of the report to be generated by parsing the report generation request. Furthermore, the preset server adopts the method described in steps 104 to 108 of the report generation method in the aforementioned embodiment to identify the demand intent of the required text information, obtain the report parameters that match the report to be generated, and select and arrange the preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain. Finally, based on the report parameters, the preset intelligent agents in the intelligent agent call chain are chain-called to generate a report that matches the required text information.

[0122] Step 206: Obtain the report generated by the preset server.

[0123] In some optional embodiments, after generating the report, the preset server may send a report generation message to the client to notify the client to actively pull the report from the preset server. In other optional embodiments, after generating the report, the preset server may send the report to the client.

[0124] In the embodiments of the present disclosure, there is no limitation on the specific implementation method of the client obtaining the report generated by the preset server.

[0125] Step 208: Display the report.

[0126] The client can display the report according to a preset page layout. As shown in Figure 4, the report displayed by the client includes any one or more of the following report content formats: text, images, and tables. In some optional embodiments, the client can also display a summary or outline of the report in a reduced format, and expand the report content after the user triggers the display of the report details.

[0127] In the embodiments of the present disclosure, there is no limitation on the display layout of the report content.

[0128] In summary, the report generation method disclosed in the embodiment of the present disclosure, after obtaining the target application scenario and the requirement text information of the report to be generated, sends the target application scenario and the requirement text information to the preset server, so that the preset server performs the following report generation operations based on the target application scenario and the requirement text information: identifies the requirement intent of the requirement text information and obtains the report parameters that match the report to be generated; selects and arranges the preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain; based on the report parameters, performs chain calls on the preset intelligent agents in the intelligent agent call chain to generate a report that matches the requirement text information; thereafter, obtains the report generated by the preset server and displays it, quickly generates a report that matches the user's needs, and effectively improves the efficiency of report generation. At the same time, using this method to generate reports does not require manual data collection and analysis, which is more efficient and less costly.

[0129] Based on the above embodiments, the present disclosure also discloses a report generation system for implementing the above report generation method.

[0130] As shown in Figure 5, the report generation system includes a client 502 and a server 504. The implementation scheme of the report generation system will be described below with reference to Figure 5.

[0131] The client 502 is configured to obtain target application scenarios and required text information of a report to be generated, and send the target application scenarios and required text information to the server 504;

[0132] The server 504 is configured to receive the target application scenario and the requirement text information, identify the requirement intent of the requirement text information, and obtain report parameters that match the report to be generated;

[0133] The server 504 is further configured to select and arrange preset agents based on the target application scenario to obtain an agent call chain;

[0134] The server 504 is further configured to perform a chain call on the preset agent in the agent call chain based on the report parameters to generate a report matching the required text information;

[0135] The client 502 is further configured to obtain the report and display the report.

[0136] In some optional embodiments, the preset agent is created by the following method: functional decomposition and aggregation processing of the report generation process of the preset application scenario is performed to obtain multiple atomic capabilities after deduplication, and a preset agent corresponding to the atomic capabilities is created, wherein the implementation method of the preset agent includes: based on the generative pre-trained model call implementation or based on the service interface call implementation

[0137] The specific implementation methods of the client and the server can be found in the relevant descriptions in the above embodiments and will not be repeated here.

[0138] In some optional embodiments, the report generation system may be implemented using the system architecture shown in Figure 6. The implementation schemes of various parts of the system architecture are described below.

[0139] The platform support layer 602 includes a large language model management center, a data center, and a system platform. The large language model management center is used to access various LLMs (Large Language Models) and maximize the capabilities of generative pre-trained models based on application scenarios. The data center is used to consolidate data assets and knowledge bases and provide data content. The system platform is responsible for accessing second- and third-party service capabilities and expanding the capabilities of the report generation system. The large-scale language models and data content in the platform support layer 602 will be accessed or called by the intelligent agents called by the report generation system's server during the report generation phase.

[0140] The agent layer 604 includes several agents with various capabilities. For example, agents for intent understanding, agents for data collection, and agents for content generation, etc. In some optional embodiments, each agent may have one or more subdivided capabilities. For example, the agent for intent understanding has one or more of the following subdivided capabilities: application scenario identification, problem understanding, demand splitting, capability matching, etc.; the agent for data collection has one or more of the following subdivided capabilities: text understanding, web page parsing, data interpretation, knowledge retrieval, etc.; the agent for content generation has one or more of the following subdivided capabilities: text summarization, code generation, service orchestration, web page generation, etc. In the report generation stage, for a certain application scenario, the server of the report generation system can select some agents from the preset agents in the agent layer 604, arrange the calling sequence, and thus obtain the agent call chain of the application scenario.

[0141] The service center 606 is used to provide a variety of service capabilities. For example, through experience summary and accumulation, it provides a set of general report production framework processes, report customization capabilities, question and answer service capabilities, scheduled push notifications and other personalized service capabilities.

[0142] The application layer 608 interacts with the service center 606 and utilizes the underlying system capabilities to achieve report generation capabilities for various application scenarios.

[0143] In order to make the report generation method and report generation system disclosed in the embodiments of the present disclosure more clear, the execution process of the report generation method in the report generation system is further explained below with reference to the report generation process schematic diagram shown in FIG7 .

[0144] First, a variety of large-scale language models are integrated into the report generation system as generative pre-trained models called during the execution of the report generation method. On the other hand, a number of intelligent agents with various capabilities are preset in the report generation system, which are used to be selected and arranged according to the needs of the target application scenario during the report generation stage to obtain an intelligent agent call chain, and the intelligent agent call chain is executed to execute the report generation process of the target application scenario. Among them, the creation method of the preset intelligent agent is described above. For the intelligent agent implemented based on the generative pre-trained model (i.e., the large-scale language model), when the present disclosure is specifically implemented, the prompt word or prompt word template of each intelligent agent is created in advance through testing.

[0145] Then, each step of the above report generation method is executed by the above report generation system.

[0146] In an application scenario where an industry insight report is generated for an e-commerce website, a user enters a question through the client, such as "Analyze the clothing industry in Country X." After the client determines the application scenario selected by the user, it sends the target application scenario (i.e., the user-selected application scenario) and the required text information (i.e., the user-entered question) to the server.

[0147] The server recognizes the demand intent of the demand text information and obtains report parameters that match the report to be generated, such as "country X" and "clothing".

[0148] Next, based on the target application scenario and the capabilities of the pre-set agents in the report generation system, the server selects one or more pre-set agents and orchestrates them to create an agent call chain. For example, the resulting agent call chain includes pre-set agents 701 and 702 for data collection, agents 703, 704, and 705 for data analysis, and agents 706, 707, and 708 for report output.

[0149] Then, based on the report parameters, the server performs a chain call to the preset agents 701 to 708 in the agent call chain to generate a report corresponding to the report generation requirement.

[0150] Among them, the preset intelligent agent 701 can retrieve import and export data, hot search terms and hot-selling products related to the clothing industry in Country X by calling a preset third-party service interface, and collect off-site content of the e-commerce website; the preset intelligent agent 702 can generate database query statements for a specified database by calling a generative pre-trained model, and execute the generated database query statements to search for data and transaction data on the site, etc., to collect on-site content of the e-commerce website.

[0151] The preset intelligent agent 703 performs comparative analysis on the off-site content output by the preset intelligent agent 701 and the on-site content output by the preset intelligent agent 702 to obtain comparative analysis results; the preset intelligent agent 704 performs drill-down analysis on the off-site content output by the preset intelligent agent 701 and the on-site content output by the preset intelligent agent 702 to obtain drill-down analysis results; the preset intelligent agent 705 performs trend analysis on the drill-down analysis results output by the preset intelligent agent 704 to obtain trend analysis results. Afterwards, the server uses one or more of the comparative analysis results output by the preset intelligent agent 703, the drill-down analysis results output by the preset intelligent agent 704, and the trend analysis results output by the preset intelligent agent 705 as data analysis results.

[0152] The preset intelligent agents 706, 707 and 708 are respectively called according to the data dependency relationship, and are used to perform corresponding formatting processing on the analysis results output by the preset intelligent agents 703, 704 and 705 that have been called, such as generating a national summary, an industry summary, a hot search and hot-selling product summary, etc., and finally generating a report in a specified format and containing specified content.

[0153] The report generation method and system disclosed in the present embodiments are based on breaking down and aggregating the report generation process for each application scenario supported by the report generation system to create several agents with corresponding atomic capabilities. Leveraging the powerful generative capabilities of generative pre-trained models to implement agents can further improve report generation efficiency.

[0154] For example, in the aforementioned preset agent 702, a preset prompt word template for calling the generative pre-trained model to generate a database query statement can be created in advance through testing and training, such as "

[0155] system_role = 'As a data analyst, output SQL code to extract data content according to data model and analysis requirements.'

[0156] data_schema=open('data / traffic_schema.txt').read().strip()

[0157] question = 'Data schema {data_schema},\nAnalysis requirements: Region $country Industry $industry.'"

[0158] In the above preset prompt word template, the symbol "$country" represents a placeholder for a report parameter in the region dimension, and "$industry" represents a placeholder for a report parameter in the industry dimension. When the preset agent 702 is called, it formats the preset prompt word template based on the input content to generate prompt words. Then, based on the generated prompt words, it calls the generative pre-trained model to generate SQL code.

[0159] In addition, the agents 706, 707 and 708 that output reports can also be implemented based on generative pre-trained model calls.

[0160] Those skilled in the art will appreciate that the report generation process illustrated in FIG7 is merely an example of a possible agent orchestration result for a particular application scenario and should not be construed as limiting the report generation method and system disclosed in the embodiments of the present disclosure. Pre-set agents in the report generation system may be added, modified, or removed based on application requirements. Accordingly, for a given application scenario, the agent call chain for implementing a report in that application scenario may vary.

[0161] It should be noted that for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present disclosure are not limited by the order of the actions described, because according to the embodiments of the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present disclosure.

[0162] Based on the above embodiment, this embodiment further provides a report generating device, the device comprising:

[0163] The demand information acquisition module is used to obtain the demand text information of the report to be generated in the target application scenario;

[0164] A report parameter acquisition module is used to identify the demand intent of the demand text information and obtain report parameters that match the report to be generated;

[0165] An agent orchestration module, configured to select and orchestrate preset agents based on the target application scenario to obtain an agent call chain;

[0166] A report generation module is used to perform a chain call on the preset agent in the agent call chain based on the report parameters to generate a report matching the required text information.

[0167] In some optional embodiments, the report parameter acquisition module is further configured to:

[0168] Formatting a preset prompt word template corresponding to the target application scenario based on the demand text information to obtain a first prompt word;

[0169] A preset generative pre-training model is called based on the first prompt word, so that the generative pre-training model analyzes and extracts information according to the demand text information to obtain report parameters.

[0170] In some optional embodiments, the report parameter acquisition module is further configured to:

[0171] Identifying preset keywords included in the demand text information through word matching technology;

[0172] Report parameters are obtained based on the identified preset keywords.

[0173] In some optional embodiments, the report parameters include one or more of the following dimensions: region, industry, time, data analysis object, and report type.

[0174] In some optional embodiments, the agent orchestration module is further configured to:

[0175] Obtaining an agent call chain based on agent configuration information of the target application scenario, wherein the agent configuration information is used to describe preset agents that need to be called in sequence when generating a report for the target application scenario; or

[0176] Based on the target application scenario and the capability description text of the preset intelligent agent, the generative pre-training model is called to generate the intelligent agent call chain corresponding to the target application scenario.

[0177] In some optional embodiments, the preset agent is created by the following method:

[0178] The report generation process of the preset application scenario is functionally decomposed and aggregated to obtain multiple deduplicated atomic capabilities, and a preset intelligent agent corresponding to the atomic capabilities is created, wherein the implementation method of the preset intelligent agent includes: implementation based on generative pre-trained model calls or implementation based on service interface calls.

[0179] In some optional embodiments, the preset agent includes any one or more of the following: an agent for generating database query statements, an agent for formatting data into a report in a target format, an agent for executing specified database query instructions to obtain data within the system, and an agent for calling a preset service interface to obtain data outside the system.

[0180] In some optional embodiments, the report generation module is further configured to:

[0181] In order from the beginning to the end, the agents in the call chain are taken as the current agent, and any of the following call operations are performed on the current agent:

[0182] Call the current agent to obtain the output content of the current step call;

[0183] Call the current agent based on the report parameters to obtain the output content of the current step call;

[0184] Call the current agent based on the output content generated by one or more previous step call operations to obtain the output content of the current step call;

[0185] The current agent is called based on the output content generated by one or more previous step call operations and one or more parameters in the report parameters to obtain the output content of the current step call.

[0186] In summary, the report generation device disclosed in the embodiment of the present disclosure, after obtaining the demand text information of the report to be generated in the target application scenario, first identifies the demand intent of the demand text information, obtains the report parameters that match the report to be generated, and realizes accurate understanding of user needs; then, based on the target application scenario, the preset intelligent agents are selected and arranged to obtain an intelligent agent call chain; finally, based on the report parameters, the preset intelligent agents in the intelligent agent call chain are chain-called to generate a report that matches the demand text information. This method can automatically and quickly generate a report that matches the user needs, effectively improving the efficiency of report generation. When using this method to generate reports, there is no need for manual data collection and analysis, which is more efficient and less costly.

[0187] On the other hand, by disassembling and aggregating the report generation process in advance, we can build preset intelligent agents corresponding to atomic capabilities, and choreograph intelligent agents in real time during the report generation phase to achieve dynamic assembly of the report generation process, thus obtaining an intelligent agent call chain. This effectively realizes the reuse of preset intelligent agents, improves the energy-saving performance of the report generation system, and realizes the flexible expansion of the report generation process, thereby improving the functional expansion capability of the report generation system.

[0188] The embodiment of the present disclosure also discloses a report generating device, which is applied to a client and includes a demand information acquisition module for acquiring target application scenarios and demand text information of a report to be generated;

[0189] A demand information sending module is used to send the target application scenario and the demand text information to a preset server, so that the preset server performs the following report generation operations based on the target application scenario and the demand text information: performing demand intent recognition on the demand text information to obtain report parameters that match the report to be generated; selecting and arranging preset agents based on the target application scenario to obtain an agent call chain; and chain-calling the preset agents in the agent call chain based on the report parameters to generate a report that matches the demand text information;

[0190] A report acquisition module, configured to acquire the report generated by the preset server;

[0191] The report display module is used to display the report.

[0192] In summary, the report generation device disclosed in the embodiment of the present disclosure, after obtaining the target application scenario and the requirement text information of the report to be generated, sends the target application scenario and the requirement text information to the preset server, so that the preset server performs the following report generation operations based on the target application scenario and the requirement text information: identifies the requirement intent of the requirement text information and obtains the report parameters that match the report to be generated; selects and arranges the preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain; based on the report parameters, performs chain calls on the preset intelligent agents in the intelligent agent call chain to generate a report that matches the requirement text information; then, obtains the report generated by the preset server and displays it, quickly generates a report that matches the user's needs, and effectively improves the report generation efficiency. At the same time, using this method to generate reports does not require manual data collection and analysis, which is more efficient and less costly.

[0193] The embodiments of the present disclosure further provide a non-volatile readable storage medium, which stores one or more modules (programs). When the one or more modules are applied to a device, the device can execute instructions (instructions) of each method step in the embodiments of the present disclosure.

[0194] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the embodiment of the present disclosure.

[0195] The present disclosure also provides an electronic device, comprising: a processor and a memory communicatively connected to the processor; the memory storing computer-executable instructions; and the processor executing the computer-executable instructions stored in the memory to implement the method described in the present disclosure. In the present disclosure, the electronic device includes a server, a terminal device, and other devices.

[0196] The present disclosure also discloses a computer program product, including a computer program / computer executable instructions, wherein the computer program / computer executable instructions, when executed by a processor in an electronic device, implement the method described in the present disclosure.

[0197] The embodiments of the present disclosure may be implemented as a device configured as desired using any appropriate hardware, firmware, software, or any combination thereof, and the device may include electronic devices such as a server (cluster), a terminal, etc. FIG8 schematically illustrates an exemplary device 800 that may be used to implement various embodiments described in the present disclosure.

[0198] For one embodiment, Figure 8 shows an exemplary apparatus 800 having one or more processors 802, a control module (chip set) 804 coupled to at least one of the processor(s) 802, a memory 806 coupled to the control module 804, a non-volatile memory (NVM) / storage device 808 coupled to the control module 804, one or more input / output devices 810 coupled to the control module 804, and a network interface 812 coupled to the control module 804.

[0199] The processor 802 may include one or more single-core or multi-core processors, and the processor 802 may include any combination of general-purpose processors or dedicated processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 800 can serve as a server, terminal, or other device described in the embodiments of the present disclosure.

[0200] In some embodiments, the apparatus 800 may include one or more computer-readable media (e.g., memory 806 or NVM / storage 808) having instructions 814 and one or more processors 802 configured in conjunction with the one or more computer-readable media to execute the instructions 814 to implement a module to perform the actions described in the present disclosure.

[0201] For one embodiment, the control module 804 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 802 and / or any suitable device or component in communication with the control module 804 .

[0202] The control module 804 may include a memory controller module to provide an interface to the memory 806. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0203] The memory 806 can be used, for example, to load and store data and / or instructions 814 for the device 800. For one embodiment, the memory 806 can include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the memory 806 can include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0204] For one embodiment, the control module 804 may include one or more input / output controllers to provide interfaces to the NVM / storage device 808 and the input / output device(s) 810 .

[0205] For example, NVM / storage 808 may be used to store data and / or instructions 814. NVM / storage 808 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0206] NVM / storage device 808 may include storage resources that are part of the device on which apparatus 800 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 808 may be accessed via input / output device(s) 810 over a network.

[0207] (One or more) input / output devices 810 may provide an interface for the apparatus 800 to communicate with any other appropriate device. The input / output device 810 may include a communication component, an audio component, a sensor component, etc. The network interface 812 may provide an interface for the apparatus 800 to communicate via one or more networks. The apparatus 800 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, for example, accessing a wireless network based on a communication standard such as Bluetooth, WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof for wireless communication.

[0208] For one embodiment, at least one of the processor(s) 802 may be packaged together with the logic of one or more controllers of the control module 804 (e.g., a memory controller module). For one embodiment, at least one of the processor(s) 802 may be packaged together with the logic of one or more controllers of the control module 804 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 802 may be integrated on the same die with the logic of one or more controllers of the control module 804. For one embodiment, at least one of the processor(s) 802 may be integrated on the same die with the logic of one or more controllers of the control module 804 to form a system-on-chip (SoC).

[0209] In various embodiments, the apparatus 800 may be, but is not limited to, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the apparatus 800 may have more or fewer components and / or a different architecture. For example, in some embodiments, the apparatus 800 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0210] Among them, the main control chip can be used as a processor or control module in the detection device, sensor data, location information, etc. are stored in the memory or NVM / storage device, the sensor group can be used as an input / output device, and the communication interface may include a network interface.

[0211] The present disclosure also provides an electronic device comprising: a processor; and a memory storing executable code, wherein when the executable code is executed, the processor executes one or more methods described in the present disclosure. The memory in the present disclosure can store various data, such as target files, file-application association data, and user behavior data, thereby providing a data foundation for various processing operations.

[0212] The embodiments of the present disclosure further provide one or more machine-readable media having executable codes stored thereon. When the executable codes are executed, the processor executes one or more methods described in the embodiments of the present disclosure.

[0213] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0214] The various embodiments in the present disclosure are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other.

[0215] The embodiments of the present disclosure are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0216] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0217] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce computer-implemented processing, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0218] Although the preferred embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present disclosure.

[0219] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0220] The report generation method, report generation system, electronic device, storage medium and computer program product provided by the present disclosure are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method of the present disclosure and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present disclosure, there may be changes in the specific implementation methods and application scopes. In summary, the content of the present disclosure should not be understood as a limitation of the present disclosure.

Claims

1. A report generation method, applied to a server, comprising: Obtain the required text information of the report to be generated in the target application scenario; Identify the demand intent of the demand text information and obtain report parameters that match the report to be generated; Select and arrange preset intelligent agents based on the target application scenario to obtain an intelligent agent call chain; Based on the report parameters, the preset agent in the agent call chain is chain-called to generate a report matching the required text information.

2. The method according to claim 1, wherein The step of identifying the demand intent of the demand text information and obtaining matching report parameters for the report to be generated includes: Formatting a preset prompt word template corresponding to the target application scenario based on the demand text information to obtain a first prompt word; A preset generative pre-training model is called based on the first prompt word, so that the generative pre-training model analyzes and extracts information according to the demand text information to obtain report parameters.

3. The method according to claim 1, wherein The step of identifying the demand intent of the demand text information and obtaining matching report parameters for the report to be generated includes: Identifying preset keywords included in the demand text information through word matching technology; Report parameters are obtained based on the identified preset keywords.

4. The method according to any one of claims 1 to 3, wherein: The report parameters include one or more of the following dimensions: region, industry, time, data analysis object, and report type.

5. The method according to any one of claims 1 to 4, wherein: The step of selecting and arranging preset agents based on the target application scenario to obtain an agent call chain includes: Obtaining an agent call chain based on agent configuration information of the target application scenario, wherein the agent configuration information is used to describe preset agents that need to be called in sequence when generating a report for the target application scenario; or Based on the target application scenario and the capability description text of the preset intelligent agent, the generative pre-training model is called to generate the intelligent agent call chain corresponding to the target application scenario.

6. The method according to any one of claims 1 to 5, wherein: The preset agent is created by the following method: The report generation process of the preset application scenario is functionally decomposed and aggregated to obtain multiple deduplicated atomic capabilities, and a preset intelligent agent corresponding to the atomic capabilities is created, wherein the implementation method of the preset intelligent agent includes: implementation based on generative pre-trained model calls or implementation based on service interface calls.

7. The method according to any one of claims 1 to 6, wherein: The preset intelligent agent includes any one or more of the following: an intelligent agent for generating database query statements, an intelligent agent for formatting data into a report in a target format, an intelligent agent for executing specified database query instructions to obtain data within the system, and an intelligent agent for calling a preset service interface to obtain data outside the system.

8. The method according to any one of claims 1 to 7, wherein: The method of chain-calling the preset agent in the agent call chain based on the report parameters to generate a report matching the required text information includes: In order from the beginning to the end, the agents in the call chain are taken as the current agent, and any of the following call operations are performed on the current agent: Call the current agent to obtain the output content of the current step call; Call the current agent based on the report parameters to obtain the output content of the current step call; Call the current agent based on the output content generated by one or more previous step call operations to obtain the output content of the current step call; The current agent is called based on the output content generated by one or more previous step call operations and one or more parameters in the report parameters to obtain the output content of the current step call.

9. A report generation method, applied to a client, comprising: Obtain the target application scenario and requirement text information of the report to be generated; Sending the target application scenario and the requirement text information to a preset server, so that the preset server performs the following report generation operations based on the target application scenario and the requirement text information: identifying the requirement intent of the requirement text information to obtain report parameters that match the report to be generated; selecting and arranging preset agents based on the target application scenario to obtain an agent call chain; Based on the report parameters, chain calling the preset agent in the agent calling chain to generate a report matching the required text information; Obtaining the report generated by the preset server; The report is presented.

10. A report generation system comprising: Client and server, where The client is configured to obtain target application scenarios and required text information of a report to be generated, and send the target application scenarios and required text information to the server; The server is configured to receive the target application scenario and the requirement text information, identify the requirement intent of the requirement text information, and obtain report parameters that match the report to be generated; The server is further configured to select and arrange preset agents based on the target application scenario to obtain an agent call chain; The server is further configured to perform a chain call on the preset agent in the agent call chain based on the report parameters to generate a report matching the required text information; The client is further used to obtain the report and display the report.

11. The system according to claim 10, wherein the preset agent is created by: The report generation process of the preset application scenario is functionally decomposed and aggregated to obtain multiple atomic capabilities after deduplication, and a preset intelligent agent corresponding to the atomic capabilities is created, wherein: The implementation method of the preset intelligent agent includes: implementation based on generative pre-trained model call or implementation based on service interface call.

12. An electronic device comprising: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

13. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, wherein the computer-executable instructions are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

14. A computer program product, comprising a computer program / computer executable instructions, wherein the computer program / computer executable instructions are capable of implementing the method according to any one of claims 1 to 9 when executed by a processor in an electronic device.

Images