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

Abstract

The embodiment of the invention provides a report generation method, system and device, electronic equipment and a storage medium, and belongs to the technical field of report processing. The method comprises the following steps: receiving a report generation request of a user, wherein the report generation request comprises first report demand information; performing word slot extraction on the first report demand information to obtain report data information in a source language format; wherein the report data information comprises an intention data type, a data filtering condition and time dimension information; obtaining report data information in a target language format according to the report data information in the source language format; target data is extracted from the data model according to the report data information in the target language format, a target report corresponding to the target data is generated, the data type of the target data is an intention data type, the target data meets the data filtering condition, and the time processing dimension of data in the target report is the target time processing dimension. According to the embodiment of the invention, the report generation efficiency is high.

Description

Technical Field

[0001] The present application relates to the technical field of report processing, and in particular to a report generation method, system, device, electronic device and storage medium. Background Art

[0002] In today's business environment, data-driven decision-making is becoming increasingly important. Enterprises need to be able to quickly extract valuable information from large amounts of data in order to adjust strategies and optimize operations in a timely manner.

[0003] Currently, many companies still rely on traditional reporting systems, which usually require business personnel to put forward specific requirements in advance, and then the development team will develop and go through the release process to finally present the data. This process may take from a few days to a few months, resulting in significant delays in the generation of reports. This delay not only affects the business team's timely analysis and control of operations, but also causes some small or urgent requirements to be ignored because they may not be worth investing a lot of time and resources in development and testing. All of these have led to the problem of low efficiency in existing reporting systems. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a report generation method, system, device, electronic device and storage medium, aiming to improve the efficiency of report generation.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a report generation method, the method comprising:

[0006] Receiving a report generation request from a user, wherein the report generation request includes first report requirement information;

[0007] Performing word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report;

[0008] According to the report data information in the source language format, acquiring the report data information in the target language format, wherein the target language format is a language format recognizable by the data model;

[0009] According to the report data information in the target language format, target data is extracted from the data model, and a target report corresponding to the target data is generated, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

[0010] In some embodiments, the step of performing word slot extraction on the report requirement information to obtain report data information in a source language format includes:

[0011] Performing word slot extraction on the first report requirement information using a word slot extraction rule to obtain a first word slot extraction result; wherein the word slot extraction rule is used for word slot extraction of a target structure sentence;

[0012] When the first word slot extraction result is that the word slot extraction is successful, the report data information in the source language format is determined according to the first word slot extraction result.

[0013] In some embodiments, determining the report data information in the source language format according to the first word slot extraction result includes:

[0014] In the case where the first word slot extraction result includes all information of the report data information, determining the first word slot extraction result as the report data information in the source language format;

[0015] In the case where the first word slot extraction result includes the first part of the report data information, outputting prompt information; the prompt information is used to prompt input of the second part of the report data information except the first part of the information;

[0016] Receiving second report requirement information input by a user;

[0017] Performing word slot extraction on the second report requirement information to obtain the second part of information;

[0018] The first part of information and the second part of information are combined to obtain report data information in a source language format.

[0019] In some embodiments, after extracting word slots from the first report requirement information using word slot extraction rules to obtain a first word slot extraction result, the method further includes:

[0020] When the first word slot extraction result is a word slot extraction failure, performing word slot extraction on the report requirement information using a word slot extraction model to obtain a second word slot extraction result;

[0021] According to the second word slot extraction result, the report data information in the source language format is determined.

[0022] In some embodiments, the step of acquiring the report data information in the target language format according to the report data information in the source language format includes:

[0023] Acquire a knowledge base; the knowledge base stores words in source language format and the target language format of the words;

[0024] According to the report data information in the source language format, the knowledge base is queried to obtain the report data information in the target language format.

[0025] In some embodiments, the step of extracting target data from the data model according to the report data information in the target language format and generating a report corresponding to the target data includes:

[0026] Acquire the target data from the data model according to the intended data type and data filtering condition in the target language format;

[0027] The target data is processed according to the time dimension information in the target language format to obtain the target report.

[0028] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a report generation system, the report generation system comprising a front end, a word slot extraction end, a server end, an automatic analysis platform and a data model;

[0029] The front end is used to: receive a report generation request from a user, wherein the report generation request includes first report requirement information;

[0030] The word slot extraction end is used to: perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report;

[0031] The server is used to: obtain report data information in a target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by the data model;

[0032] The self-service analysis platform is used to: extract target data from the data model according to the report data information in the target language format, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

[0033] To achieve the above-mentioned purpose, a third aspect of an embodiment of the present application provides a report generation device, the device comprising:

[0034] A receiving module, configured to receive a report generation request from a user, wherein the report generation request includes first report requirement information;

[0035] an extraction module, configured to perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report;

[0036] An acquisition module, configured to acquire report data information in a target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by a data model;

[0037] A generation module is used to extract target data from the data model according to the report data information in the target language format, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

[0038] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0039] The report generation method, system, device, electronic device and storage medium proposed in the present application receive a report generation request from a user, wherein the report generation request includes first report requirement information; perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report; according to the report data information in the source language format, obtain the report data information in the target language format, wherein the target language format is a language format recognizable by a data model; according to the report data information in the target language format, extract the target data from the data model, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension. That is, the first report demand information is subjected to word slot extraction, and the report data information is obtained through the word slot extraction. After the extracted report data information is converted, it is input into the data model to obtain the target data and automatically generate a random report, thereby solving the problem of low efficiency existing in the existing report system and improving the immediacy and efficiency of report generation. Furthermore, the method proposed in the present application allows users to directly input requirements through natural language, and the system can respond and generate reports in seconds, which greatly simplifies the process and improves efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of a report generation method provided in an embodiment of the present application;

[0041] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0042] Figure 3 yes Figure 2 Flow chart of step S202 in FIG.

[0043] Figure 4 yes Figure 2 The flowchart after step S201 in FIG.

[0044] Figure 5 yes Figure 1 Flow chart of step S103 in FIG.

[0045] Figure 6 yes Figure 1 Flow chart of step S104 in FIG.

[0046] Figure 7 is a relationship diagram of a report generation system provided in an embodiment of the present application;

[0047] Figure 8 It is a structural schematic diagram of a report generating device provided in an embodiment of the present application;

[0048] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0052] First, some nouns involved in this application are analyzed:

[0053] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0054] Natural language processing (NLP): NLP uses computers to process, understand and apply human languages ​​(such as Chinese, English, etc.). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is often used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0055] Information Extraction: A text processing technology that extracts specified types of entity, relationship, event and other factual information from natural language text and forms structured data output. Information extraction is a technology that extracts specific information from text data. Text data is composed of some specific units, such as sentences, paragraphs, and chapters. Text information is composed of some small specific units, such as characters, words, phrases, sentences, paragraphs, or a combination of these specific units. Extracting noun phrases, names, place names, etc. from text data are all text information extraction. Of course, the information extracted by text information extraction technology can be various types of information.

[0056] Based on this, the embodiments of the present application provide a report generation method, device, electronic device and storage medium, aiming to improve the efficiency of report generation.

[0057] The report generation method, device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the report generation method in the embodiments of the present application is described.

[0058] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0059] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0060] The report generation method provided in the embodiment of the present application relates to the field of report processing technology. The report generation method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the report generation method, etc., but is not limited to the above forms.

[0061] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0062] Figure 1 is an optional flow chart of the report generation method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0063] Step S101, receiving a report generation request from a user, wherein the report generation request includes first report requirement information;

[0064] Step S102, performing word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report;

[0065] Step S103, acquiring report data information in a target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by a data model;

[0066] Step S104, extracting target data from the data model according to the report data information in the target language format, and generating a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

[0067] In steps S101 to S104 shown in the embodiment of the present application, a report generation request from a user is received, wherein the report generation request includes first report requirement information; word slot extraction is performed on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report; according to the report data information in the source language format, report data information in a target language format is obtained, wherein the target language format is a language format recognizable by a data model; according to the report data information in the target language format, target data is extracted from the data model, and a target report corresponding to the target data is generated, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension. That is, the first report demand information is subjected to word slot extraction, and the report data information is obtained through the word slot extraction. After the extracted report data information is converted, it is input into the data model to obtain the target data and automatically generate a random report, thereby solving the problem of low efficiency existing in the existing report system and improving the immediacy and efficiency of report generation. Furthermore, the method proposed in the present application allows users to directly input requirements through natural language, and the system can respond and generate reports in seconds, which greatly simplifies the process and improves efficiency.

[0068] In step S101 of some embodiments, a report generation request submitted by a user is received, and the request includes specific demand information of the user for the report.

[0069] It should be noted that the report generation request may be a request submitted by a user, including information required for creating a specific report. The first report requirement information may be information required for creating a specific report.

[0070] In step S102 of some embodiments, the demand information submitted by the user is analyzed to extract key report data information, i.e., report data information in the source language format. This information is presented in the source language format (the language format originally requested by the user), including the intended data type, data filtering conditions, and time dimension information.

[0071] It should be noted that word slot extraction can be an information extraction process used to identify and extract key data from user requests. The source language format can be the language format of the user's original request, which can be a natural language or a query language in a specific format. Report data information can be key data extracted from user needs for generating reports, including intended data types, data filtering conditions, and time dimension information. Intended data types can be the types of data that users want to be included in the report (such as sales, number of users, etc.). Data filtering conditions can be conditions used to limit the source of report data, such as a specific organization or time period. Time dimension information can be how users want to process report data based on time, such as summarizing by day, month, or year.

[0072] See also Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S202:

[0073] Step S201, performing word slot extraction on the first report requirement information using a word slot extraction rule to obtain a first word slot extraction result; wherein the word slot extraction rule is used for word slot extraction of a target structure sentence;

[0074] Step S202: when the first word slot extraction result is that the word slot extraction is successful, determine the report data information in the source language format according to the first word slot extraction result.

[0075] In step S201 of some embodiments, the user's first report demand information is analyzed using predefined word slot extraction rules. These rules are designed based on the target structure sentence pattern and are used to identify key components in the demand information. By applying the word slot extraction rules, a first word slot extraction result is obtained, which is potential key data extracted from the user's demand information.

[0076] In step S202 of some embodiments, if the first word slot extraction result indicates that the extraction is successful, it means that the sentence pattern of the first report demand information is the target structure sentence pattern, then the source language format report data information in the user demand can be determined based on the first word slot extraction result, and this information includes the intended data type, data filtering conditions and time dimension information.

[0077] It should be noted that the word slot extraction rules can be a set of predefined rules or patterns used to guide the word slot extraction process and help the system identify and extract specific information. The target structure sentence can be a specific type of sentence or query format designed to be processed, which is usually related to a specific application scenario or task.

[0078] In the steps S201 to S202 shown in the embodiment of the present application, the first report requirement information is subjected to a word slot extraction by using a word slot extraction rule to obtain a first word slot extraction result; wherein the word slot extraction rule is used for word slot extraction of a target structure sentence; when the first word slot extraction result is a successful word slot extraction, the report data information in the source language format is determined according to the first word slot extraction result. That is, only when the sentence pattern of the first report requirement information is a target structure sentence pattern, the report data information in the source language format will be extracted successfully. By using the word slot extraction rule, the key information in the user requirements can be more accurately identified and extracted, misunderstandings or errors can be reduced, and accuracy can be improved. The automated word slot extraction process reduces the need for manual intervention, speeds up the entire process of report generation, and improves efficiency. Users can propose report requirements in a natural language without having to learn a complex query language, which improves the convenience of use and enhances the user experience. At the same time, it supports complex queries, can handle complex report requirements containing multiple conditions and dimensions, and provides more flexible data analysis capabilities.

[0079] See also Figure 3 In some embodiments, step S202 may include but is not limited to steps S301 to S305:

[0080] Step S301, when the first word slot extraction result includes all information of the report data information, determining the first word slot extraction result as the report data information in the source language format;

[0081] Step S302: if the first word slot extraction result includes the first part of the report data information, output prompt information; the prompt information is used to prompt the user to input the second part of the report data information except the first part of the information;

[0082] Step S303, receiving second report requirement information input by the user;

[0083] Step S304, performing word slot extraction on the second report requirement information to obtain the second part of information;

[0084] Step S305: Combine the first part of information and the second part of information to obtain report data information in a source language format.

[0085] In step S301 of some embodiments, word slot extraction is first performed on the user's first report requirement information to obtain report data information. If the extraction result contains all necessary report data information (all information), the information is determined as report data information in the source language format.

[0086] In step S302 of some embodiments, if the extraction result only includes part of the report data information (the first part of information), a prompt message will be output to require the user to provide the remaining information (the second part of information).

[0087] In step S303 of some embodiments, the user enters additional report requirement information (second report requirement information) according to the prompt.

[0088] In step S304 of some embodiments, word slot extraction is performed on the second report requirement information input by the user to obtain the second part of report data information.

[0089] In step S305 of some embodiments, the first part of information and the second part of information are combined to form complete report data information in the source language format.

[0090] It should be noted that the first part of information may be a part of the report data information obtained in the initial word slot extraction. The second part of information may be the remaining part of the report data information that needs to be additionally provided by the user. The prompt information may be output information used to guide the user to provide the missing report data information.

[0091] In addition, the second report requirement information input by the user is subjected to word slot extraction to obtain the second part of information. The word slot extraction implementation logic for the second report requirement information is the same as that for the first report requirement information. The second report requirement information may or may not contain all the information of the second part of information. In the case where the second report requirement information does not contain all the information of the second part of information, it is necessary to output prompt information again to require the user to provide the remaining information, which may involve more rounds of dialogue.

[0092] In the steps S301 to S305 shown in the embodiment of the present application, when the first word slot extraction result includes all the information of the report data information, the first word slot extraction result is determined as the report data information in the source language format; when the first word slot extraction result includes the first part of the information of the report data information, prompt information is output; the prompt information is used to prompt the input of the second part of the information of the report data information except the first part of the information; receive the second report requirement information input by the user; perform word slot extraction on the second report requirement information to obtain the second part of the information; combine the first part of the information and the second part of the information to obtain the report data information in the source language format. That is, judging whether all the information is included according to the first word slot result, if not all the information is included, it is necessary to prompt the user to input the second report requirement information, and after obtaining all the information, determine the report data information in the source language format. By interactively acquiring and combining information, it is possible to ensure that all necessary report data information is collected, and improve the completeness and accuracy of the report. The user can provide information in steps, which makes the report generation process more flexible and user-friendly, and enhances the user experience. By clearly prompting the user which information is necessary, errors or omissions caused by incomplete information are reduced. At the same time, it can also handle report requests of different complexities, improving the adaptability of the system.

[0093] See also Figure 4 In some embodiments, after step S201, the report generation method may include but is not limited to steps S401 to S402:

[0094] Step S401, when the first word slot extraction result is a word slot extraction failure, using a word slot extraction model to perform word slot extraction on the report requirement information to obtain a second word slot extraction result;

[0095] Step S402: determining report data information in a source language format according to the second word slot extraction result.

[0096] In step S401 of some embodiments, the user's first report demand information is processed using predefined word slot extraction rules to try to extract key information. Check whether the initial extraction result is successful. If the initial extraction fails, that is, all the required information is not obtained, indicating that the sentence pattern of the first report demand information is not the target structure sentence pattern, then the word slot extraction model is used to perform a second extraction to obtain a second word slot extraction result.

[0097] In step S402 of some embodiments, report data information in the source language format is determined according to the result of the second word slot extraction, and this information will be used in the subsequent report generation process.

[0098] It should be noted that the word slot extraction model can be a machine learning-based model that can identify and extract specific information from text even when rules cannot be applied. The report data information in the source language format can be the report-related data in the user's original request, which exists in the form of natural language and has not yet been converted into a structured format that can be operated by a machine.

[0099] In addition, according to the second word slot extraction result, the implementation method of the report data information in the source language format is determined. Figure 3 The implementation methods of the method steps shown are the same and will not be repeated here.

[0100] The method provided in the embodiment of the present application is to use the word slot extraction model to perform word slot extraction on the report demand information to obtain a second word slot extraction result when the first word slot extraction result is a word slot extraction failure. That is, the word slot extraction rules are first used to perform word slot extraction on the first report demand information to obtain a first word slot extraction result, and then the word slot extraction model is used to perform word slot extraction on the report demand information.

[0101] In another feasible implementation, the model report requirement information may be directly used to extract word slots.

[0102] In steps S401 to S402 shown in the embodiment of the present application, when the first word slot extraction result is a word slot extraction failure, the word slot extraction model is used to perform word slot extraction on the report demand information to obtain a second word slot extraction result; based on the second word slot extraction result, the report data information in the source language format is determined. That is, when the sentence pattern of the first report demand information is not the target structure sentence pattern, the word slot extraction model is used to extract, and the second word slot extraction result is obtained, and then the report data information in the source language format is determined. By using the word slot extraction model, a backup plan can be provided when the initial rule extraction fails, thereby improving the accuracy of key information extraction. Even in the face of complex or irregular report demand information, the required information can be extracted through the model, thereby enhancing the robustness of the system. Users do not need to worry about extraction failures caused by non-standard expressions, and can respond flexibly to improve the user experience.

[0103] In step S103 of some embodiments, the report data information in the source language format is converted into a target language format recognizable by the data model.

[0104] It should be noted that the target language format can be a language format that the data model can understand and process, usually a structured query language. The data model can be a model for storing and processing data, which can respond to queries and provide required data. The data model contains a doris database, and the doris database stores the corresponding data. For example, based on performance data, a data model is created in cube.js, and the performance data is imported into the doris database.

[0105] In a feasible implementation, the report data information in the source language format is converted into the target language format recognizable by the data model, and the knowledge base is queried according to the report data information in the source language format to obtain the report data information in the target language format.

[0106] In another feasible implementation, the report data information in the source language format is converted into the target language format recognizable by the data model, which may be to directly translate the report data information in the source language format to obtain the report data information in the target language format.

[0107] See also Figure 5 In some embodiments, step S103 may include but is not limited to steps S501 to S502:

[0108] Step S501, obtaining a knowledge base; the knowledge base stores words in a source language format and the words in a target language format;

[0109] Step S502: query the knowledge base according to the report data information in the source language format to obtain the report data information in the target language format.

[0110] In step S501 of some embodiments, a pre-built knowledge base is accessed, and the knowledge base contains mapping relationships between words in source language format and their corresponding target language format.

[0111] In step S502 of some embodiments, according to the report data information in the source language format in the user report requirement, the corresponding entry in the knowledge base is queried, and the corresponding report data information in the target language format is obtained through the query.

[0112] It should be noted that the target language format can be a language format that can be recognized and processed by the data model, usually a structured query language such as SQL. The knowledge base can be a database or data set that stores source language format words and their corresponding target language formats for language format conversion.

[0113] Steps S501 to S502 shown in the embodiment of the present application are obtained by acquiring a knowledge base; the knowledge base stores words in source language format and the target language format of the words; according to the report data information in the source language format, the knowledge base is queried to obtain the report data information in the target language format. That is, the knowledge base is queried to obtain the report data information in the target language format. By using the knowledge base, the data information in the source language format can be more accurately converted to the target language format, reducing misunderstandings and errors and improving the accuracy of conversion. The automated conversion process reduces the need for manual intervention and improves the efficiency of report generation. In addition, as long as there is a corresponding mapping relationship in the knowledge base, various source language formats can be processed, enhancing the flexibility of the system.

[0114] In step S104 of some embodiments, corresponding target data is extracted from the data model according to the report data information in the target language format, and a final report is generated using the extracted target data, which meets all the needs of the user, including data types, filtering conditions and time dimensions.

[0115] It should be noted that the target data may be data that meets specific conditions extracted from the data model according to the user's request. The target report may be the final generated report, which contains all the information requested by the user and is presented in a suitable format.

[0116] For example, suppose a market analyst wants to generate a report on the monthly sales of the Shenzhen branch.

[0117] The analyst submits a requirement, requesting a report showing the monthly sales data of the Shenzhen branch in 2024. The system identifies "sales" as the intended data type, "January 1, 2024 to date" and "Shenzhen branch" as data filtering conditions, and the time dimension information is to convert the date into a month. The system converts this information into report data information in the target language format, and then executes the query to extract the monthly sales data of the Shenzhen branch in 2024 from the data model. The system uses this data to generate a report with rich charts, showing the trend and analysis of the monthly sales of the Shenzhen branch.

[0118] Through this process, analysts can quickly obtain the required reports to conduct market analysis and make decisions.

[0119] See also Figure 6 In some embodiments, step S104 may include but is not limited to steps S601 to S602:

[0120] Step S601, acquiring the target data from the data model according to the intended data type and data filtering condition in the target language format;

[0121] Step S602: Process the target data according to the time dimension information in the target language format to obtain the target report.

[0122] In step S601 of some embodiments, the corresponding target data is retrieved from the data model according to the intended data type and data filtering conditions in the target language format. This involves executing a query, such as an SQL query, to extract matching data from the database.

[0123] In step S602 of some embodiments, the target data is processed according to the time dimension information in the target language format. This may include data aggregation, grouping, sorting or other time series analysis to meet the time dimension requirements of the report. The processed target data is used to generate the final report.

[0124] It should be noted that the target language format can be a language format that can be recognized and processed by the data model, usually a structured query language. The data model can be a model for storing and processing data, which can respond to queries and provide required data. The target data can be data that meets specific conditions extracted from the data model according to user requests. The target report can be the final generated report, which contains all the information requested by the user for report generation and is presented in a suitable format.

[0125] Steps S601 to S602 shown in the embodiment of the present application are to obtain the target data from the data model according to the intended data type and data filtering conditions in the target language format; and to process the target data according to the time dimension information in the target language format to obtain the target report. That is, according to the report data information, the target data is extracted from the data model and the corresponding report is generated. The embodiment of the present application can ensure that the extracted data accurately reflects the user's request, including the correct data type and filtering conditions, thereby improving data accuracy. By processing the time dimension information, a data view that matches the user's time requirements can be provided, ensuring time sensitivity. Customized reports can be generated according to the different needs of users, thereby improving the flexibility of the report and user satisfaction. At the same time, the automated data processing and report generation process reduces the need for manual operations and improves overall work efficiency.

[0126] The embodiment of the present application also provides a report generation system, which includes a front end, a word slot extraction end, a server end, an autonomous analysis platform and a data model.

[0127] The front end is used to: receive a report generation request from a user, wherein the report generation request includes first report requirement information;

[0128] The word slot extraction end is used to: perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report;

[0129] The server is used to: obtain report data information in a target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by the data model;

[0130] The self-service analysis platform is used to: extract target data from the data model according to the report data information in the target language format, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

[0131] For example, see Figure 7 , Figure 7 Generate a diagram of the system for reporting:

[0132] 1. The user inputs demand information through the front end, such as the monthly sales in Shenzhen in 2024;

[0133] 2. The front end passes the demand information to the word slot extraction end, and parses the semantics, mainly parsing into the following modules: intent data type, data filtering conditions and time dimension information. 1) The intent data type is the target indicator. For example, the demand in the example is sales. 2) The data filtering condition is the time from January 1, 2024 to the present, and the secondary institution is Shenzhen. 3) The time dimension information is to convert the date into a month for aggregation. If the business demand is not clear enough, it may involve intent clarification. For example, if the user inputs the demand: Shenzhen sales, the user needs to be asked to enter the time. Therefore, multiple rounds of dialogue may be involved. Considering the diversity of user questions, such as the last month, January 2024, 202401, etc., it needs to be converted into a standardized structure and unified as "2024-01-01". If the rule can directly parse out the user's information, the rule is directly output. If not, the word slot extraction model service interface is called to parse the user information through the word slot extraction model. The word slot extraction model currently uses the chatg lm3-6b model. The report data information in the source language format is extracted in the above way.

[0134] 3. The word slot extraction end returns the report data information in the source language format to the front end, and the front end inputs the report data information in the source language format to the server end. The server end parses the report data information in the source language format and converts the report data information in the source language format into information that can be recognized by the data model, that is, the report data information in the target language format by querying the knowledge base.

[0135] 4. The information converted by the server is finally transmitted to the self-service analysis platform, which calls the data model interface to obtain the target data and displays it in charts (generates reports) based on the target data.

[0136] 5. Feedback the generated report to the user, who can download the report.

[0137] See also Figure 8 The embodiment of the present application also provides a report generation device, which can implement the above report generation method, and the device includes:

[0138] A receiving module 801 is used to receive a report generation request from a user, where the report generation request includes first report requirement information;

[0139] The extraction module 802 is used to perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report;

[0140] The acquisition module 803 is used to acquire the report data information in the target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by the data model;

[0141] The generation module 804 is used to extract target data from the data model according to the report data information in the target language format, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

[0142] The specific implementation of the report generation device is substantially the same as the specific implementation of the report generation method described above, and will not be described in detail herein.

[0143] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above report generation method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0144] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0145] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0146] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the report generation method of the embodiment of this application;

[0147] Input / output interface 903, used to implement information input and output;

[0148] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0149] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0150] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0151] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned report generation method is implemented.

[0152] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0153] The report generation method, system, device, electronic device and storage medium provided in the embodiments of the present application receive a report generation request from a user, wherein the report generation request includes first report requirement information; word slot extraction is performed on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report; according to the report data information in the source language format, the report data information in the target language format is obtained, wherein the target language format is a language format recognizable by a data model; according to the report data information in the target language format, the target data is extracted from the data model, and a target report corresponding to the target data is generated, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension. That is, the first report demand information is subjected to word slot extraction, and the report data information is obtained through the word slot extraction. After the extracted report data information is converted, it is input into the data model to obtain the target data and automatically generate a random report, thereby solving the problem of low efficiency existing in the existing report system and improving the immediacy and efficiency of report generation. Furthermore, the method proposed in the present application allows users to directly input requirements through natural language, and the system can respond and generate reports in seconds, which greatly simplifies the process and improves efficiency.

[0154] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0155] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0156] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0158] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0159] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0160] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0161] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0163] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0164] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A report generation method, characterized in that: The method comprises: Receiving a report generation request from a user, wherein the report generation request includes first report requirement information; Performing word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report; According to the report data information in the source language format, acquiring the report data information in the target language format, wherein the target language format is a language format recognizable by the data model; According to the report data information in the target language format, target data is extracted from the data model, and a target report corresponding to the target data is generated, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

2. The method according to claim 1, characterized in that The step of extracting word slots from the report requirement information to obtain report data information in a source language format includes: Performing word slot extraction on the first report requirement information using a word slot extraction rule to obtain a first word slot extraction result; wherein the word slot extraction rule is used for word slot extraction of a target structure sentence; When the first word slot extraction result is that the word slot extraction is successful, the report data information in the source language format is determined according to the first word slot extraction result.

3. The method according to claim 2, characterized in that The step of determining the report data information in the source language format according to the first word slot extraction result includes: In the case where the first word slot extraction result includes all information of the report data information, determining the first word slot extraction result as the report data information in the source language format; In the case where the first word slot extraction result includes the first part of the report data information, outputting prompt information; the prompt information is used to prompt input of the second part of the report data information except the first part of the information; Receiving second report requirement information input by a user; Performing word slot extraction on the second report requirement information to obtain the second part of information; The first part of information and the second part of information are combined to obtain report data information in a source language format.

4. The method according to claim 2, characterized in that: After extracting word slots from the first report requirement information using the word slot extraction rule to obtain a first word slot extraction result, the method further includes: When the first word slot extraction result is a word slot extraction failure, performing word slot extraction on the report requirement information using a word slot extraction model to obtain a second word slot extraction result; According to the second word slot extraction result, the report data information in the source language format is determined.

5. The method according to claim 1, characterized in that The step of acquiring the report data information in the target language format according to the report data information in the source language format comprises: Acquire a knowledge base; the knowledge base stores words in source language format and the target language format of the words; According to the report data information in the source language format, the knowledge base is queried to obtain the report data information in the target language format.

6. The method according to claim 1, characterized in that The step of extracting target data from the data model according to the report data information in the target language format and generating a report corresponding to the target data comprises: Acquire the target data from the data model according to the intended data type and data filtering condition in the target language format; The target data is processed according to the time dimension information in the target language format to obtain the target report.

7. A report generation system, characterized in that: The report generation system includes a front end, a word slot extraction end, a server end, an automatic analysis platform and a data model; The front end is used to: receive a report generation request from a user, wherein the report generation request includes first report requirement information; The word slot extraction end is used to: perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report; The server is used to: obtain report data information in a target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by the data model; The self-service analysis platform is used to: extract target data from the data model according to the report data information in the target language format, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

8. A report generation device, characterized in that: The device comprises: A receiving module, configured to receive a report generation request from a user, wherein the report generation request includes first report requirement information; an extraction module, configured to perform word slot extraction on the first report requirement information to obtain report data information in a source language format; wherein the report data information includes an intended data type, a data filtering condition, and time dimension information; the intended data type is used to indicate the data type of the data included in the report, the data filtering condition is used to indicate the source organization and collection time period of the data included in the report, and the time dimension information is used to indicate the target time processing dimension of the data in the report; An acquisition module, configured to acquire report data information in a target language format according to the report data information in the source language format, wherein the target language format is a language format recognizable by a data model; A generation module is used to extract target data from the data model according to the report data information in the target language format, and generate a target report corresponding to the target data, wherein the data type of the target data is the intended data type, the target data satisfies the data filtering condition, and the time processing dimension of the data in the target report is the target time processing dimension.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the report generation method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the report generation method according to any one of claims 1 to 6 when executed by a processor.

Images