Financial report data query method and device, equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, can be applied to the field of financial science and technology, and discloses a financial report data query method, device and equipment and a storage medium. Obtaining a financial report text in the current financial report data; determining an expansion word corresponding to the current financial report data based on the financial report text; inputting the financial report text and the expansion word into a preset target language model; determining a current data report based on the target language model, the expansion word and the financial report text; and executing query operation in the current data report to obtain a query result of the current financial report data. The query efficiency of the current financial report data can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology and can be applied to the field of financial technology. In particular, the present invention relates to a financial report data query method, device, equipment and storage medium. Background Art

[0002] Financial report data is the key basis for evaluating corporate value. By querying financial report data, users can understand the status of the company and make more rational investment decisions, thereby effectively avoiding the risks brought about by information asymmetry.

[0003] However, the current query process of financial report data is cumbersome, which is not conducive to improving the query efficiency of current financial report data. The reason is that the existing technology mainly relies on manual query to obtain the query results of current financial report data, and the manual query method is inefficient and prone to errors, so it is not conducive to improving the query efficiency of current financial report data. Summary of the invention

[0004] The present invention provides a financial report data query method, device, computer equipment and storage medium to solve the technical problem that the current financial report data query process is cumbersome and is not conducive to improving the query efficiency of the current financial report data.

[0005] In a first aspect, a financial report data query method is provided, comprising:

[0006] Extract current financial report data from data sources;

[0007] Obtaining the financial report text in the current financial report data;

[0008] Based on the financial report text, determining an expansion word corresponding to the current financial report data;

[0009] Inputting the financial report text and the expanded words into a preset target language model;

[0010] Determining a current data report based on the target language model, the expanded words, and the financial report text;

[0011] A query operation is performed in the current data report to obtain a query result of the current financial report data.

[0012] Further, the obtaining of the financial report text in the current financial report data includes:

[0013] Preprocessing the current financial report data to obtain the preprocessed current financial report data;

[0014] The financial report text in the preprocessed current financial report data is obtained, wherein the preprocessing includes one or a combination of format conversion processing, duplicate data processing, and error data processing.

[0015] Furthermore, the step of determining, based on the financial report text, an expansion word corresponding to the current financial report data includes:

[0016] Obtaining keywords in the financial report text;

[0017] Select synonyms or near-synonyms of the keyword as expansion words corresponding to the keyword.

[0018] Furthermore, the step of inputting the financial report text and the expanded words into a preset target language model includes:

[0019] Obtain a model file, and load a preset target language model from the model file;

[0020] The input function of the target language model is called, and the financial report text and the expanded words are input into the target language model through the input function.

[0021] Further, the determining of the current data report based on the target language model, the expanded word and the financial report text includes:

[0022] Inputting the financial report text and the expanded words into the feature extractor of the target language model, performing feature extraction on the financial report text and the expanded words by the feature extractor, and obtaining a feature vector of the financial report text and a feature vector of the expanded words;

[0023] The feature vector of the financial report text and the feature vector of the expanded word are concatenated to generate a target feature vector of the current financial report data, the target feature vector is input into the generator of the target language model, and the target feature vector is processed by the generator to obtain the current data report.

[0024] Furthermore, the query operation is performed in the current data report to obtain the query result of the current financial report data, including:

[0025] Obtaining preset query conditions and submitting the query conditions to the query interface;

[0026] The query operation corresponding to the query condition is performed on the current data report through the query interface to obtain the query result of the current financial report data.

[0027] Furthermore, after performing a query operation in the current data report and obtaining a query result of the current financial report data, the financial report data query method includes:

[0028] A display area of ​​the screen is acquired, a display window of the display area is created, and the query result is displayed through the display window.

[0029] In a second aspect, a financial report data query device is provided, comprising:

[0030] Extraction module, used to extract current financial report data from the data source;

[0031] An acquisition module, used to acquire the financial report text in the current financial report data;

[0032] A first determination module, configured to determine, based on the financial report text, an expansion word corresponding to the current financial report data;

[0033] An input module, used for inputting the financial report text and the expanded words into a preset target language model;

[0034] A second determination module, configured to determine a current data report based on the target language model, the expanded word and the financial report text;

[0035] The query module is used to perform a query operation in the current data report to obtain the query result of the current financial report data.

[0036] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned financial report data query method when executing the computer program.

[0037] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned financial report data query method are implemented.

[0038] The present application provides a financial report data query method, device, computer equipment and storage medium, which extract current financial report data from a data source; obtain financial report text in the current financial report data; determine the expansion words corresponding to the current financial report data based on the financial report text; input the financial report text and the expansion words into a preset target language model; determine the current data report based on the target language model, the expansion words and the financial report text; perform a query operation in the current data report to obtain the query result of the current financial report data, and the beneficial effects are in two aspects. On the one hand, a query operation is performed in the current data report to obtain the query result of the current financial report data. Since no manual query is required, the query time of the current financial report data is reduced, which is conducive to improving the query efficiency of the current financial report data; on the other hand, since the automatic query is not prone to errors, it is conducive to improving the reliability of the query result. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0040] Figure 1 This is a schematic diagram of an application environment of a financial report data query method in one embodiment of the present invention;

[0041] Figure 2 A flowchart of a financial report data query method provided by an embodiment of the present invention;

[0042] Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S23;

[0043] Figure 4 yes Figure 1 A schematic flow chart of a specific implementation of step S25;

[0044] Figure 5 yes Figure 1 A schematic flow chart of a specific implementation of step S26;

[0045] Figure 6 It is a structural schematic diagram of a financial report data query device in one embodiment of the present invention;

[0046] Figure 7 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0047] Figure 8 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1 , Figure 1 Schematic diagram of an application environment of a financial report data query method in an embodiment of the present invention. The financial report data query method provided by the embodiment of the present invention can be applied in the following situations: Figure 1 In an application environment, a client communicates with a server through a network.

[0050] The server extracts the current financial report data from the data source through the client;

[0051] Obtaining the financial report text in the current financial report data;

[0052] Based on the financial report text, determining an expansion word corresponding to the current financial report data;

[0053] Inputting the financial report text and the expanded words into a preset target language model;

[0054] Determining a current data report based on the target language model, the expanded words, and the financial report text;

[0055] A query operation is performed in the current data report to obtain a query result of the current financial report data.

[0056] In the scheme implemented by the above-mentioned financial report data query method, device, equipment and medium, the beneficial effects are in two aspects. On the one hand, a query operation is performed in the current data report to obtain the query result of the current financial report data. Since no manual query is required, the query time of the current financial report data is reduced, which is conducive to improving the query efficiency of the current financial report data. On the other hand, since the automatic query is not prone to errors, it is conducive to improving the reliability of the query results.

[0057] The device running the client is referred to as a client device.

[0058] The device running the server is referred to as the server device.

[0059] The client devices may include but are not limited to various personal computers, laptops, smart phones, tablet computers, and portable wearable devices.

[0060] The server device can be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0061] See also Figure 2 , Figure 2 A flowchart of a financial report data query method provided by an embodiment of the present invention includes the following steps:

[0062] S21, extracting current financial report data from the data source;

[0063] Exemplarily, extracting current financial report data from a data source includes:

[0064] Connect to a target platform and extract current financial report data from a data source of the target platform, wherein the target platform includes one or a combination of a financial platform, a technology platform, and an insurance platform.

[0065] Among them, the current financial report data refers to the current financial report data.

[0066] Among them, financial report data is the numbers and text descriptions in written reports that are regularly compiled and released by enterprises, aiming to comprehensively, systematically and accurately reflect their financial status, operating results, cash flow and other key economic information to stakeholders such as investors, creditors, regulators and the public. These data are professionally processed and audited, follow specific accounting principles and reporting standards, and are highly objective and comparable.

[0067] Among them, the financial platform is an online service system based on advanced information technology architecture. The financial platform integrates multiple computer technologies such as data processing, network communication, user interface design, and security encryption. The financial platform can help investors evaluate corporate value and formulate investment strategies by collecting, organizing and displaying the financial report data of listed companies.

[0068] Among them, the science and technology platform is a comprehensive system that integrates a variety of advanced scientific and technological resources and services. The science and technology platform closely connects various scientific and technological innovation achievements, R&D resources, professional services and market demands.

[0069] Among them, the insurance platform is an online service platform that integrates insurance product sales, information consultation, customer service and risk management. The insurance platform uses modern information technologies such as the Internet, big data, and cloud computing to closely connect insurance companies, insurance agents, consumers, and third-party service providers, forming an efficient, convenient, and transparent insurance service ecosystem.

[0070] Among them, on the insurance platform, users can access the current financial report data of the insurance company. The current financial report data can help users evaluate the profitability indicators, risk status and growth potential of the insurance company, and provide a basis for investment decisions. At the same time, it is also convenient for regulatory agencies to supervise and evaluate the financial status of insurance companies to ensure the stability and healthy development of the insurance market.

[0071] Exemplarily, before extracting the current financial report data from the data source, the financial report data query method includes:

[0072] Obtaining preset financial report data and preset data reports corresponding to the preset financial report data;

[0073] Select a BERT model or a GPT model as the initial model, input the preset financial report data into the initial model, and obtain a forecast data report output by the initial model;

[0074] According to the loss value between the predicted data report and the preset data report, the initial model is trained, and the trained initial model is selected as the target language model.

[0075] Among them, the preset financial report data is the preset financial report data.

[0076] The preset data report is a preset data report. The forecast data report is a forecast data report.

[0077] The Chinese name of the BERT model is: Bidirectional Transformer Model, and the English name of the BERT model is: Bidirectional Encoder Representations from Transformers. The BERT model is a bidirectional model that can be trained with contextual information, which has better language understanding and generation capabilities compared to traditional unidirectional models (such as

[0078] Among them, the BERT model not only focuses on the previous context information of the current word, but also considers the subsequent context information, so that it can more accurately capture the overall structure and semantic relationship of the language.

[0079] Among them, the Chinese name of the GPT model is: Generative Pre-trained Transformer model, and the English name of the GPT model is: Generative Pre-trained Transformer.

[0080] Among them, the GPT model has generative capabilities, that is, it can generate new text content that conforms to grammatical rules and semantic logic based on the input text or instructions. This generative ability makes the GPT model have broad application prospects in the field of natural language processing, such as text generation, language translation, dialogue systems, etc.

[0081] S22, obtaining the financial report text in the current financial report data;

[0082] Wherein, the obtaining of the financial report text in the current financial report data includes:

[0083] Preprocessing the current financial report data to obtain the preprocessed current financial report data;

[0084] The financial report text in the preprocessed current financial report data is obtained, wherein the preprocessing includes one or a combination of format conversion processing, duplicate data processing, and error data processing.

[0085] S23, based on the financial report text, determining an expansion word corresponding to the current financial report data;

[0086] Among them, the expanded words corresponding to the current financial report data can cover more concepts and terms related to finance, thereby providing more comprehensive financial information. This helps users to have a deeper understanding of the company's financial status, operating results, cash flow and other information.

[0087] S24, inputting the financial report text and the expanded words into a preset target language model;

[0088] The step of inputting the financial report text and the expanded words into a preset target language model includes:

[0089] Obtain a model file, and load a preset target language model from the model file;

[0090] The input function of the target language model is called, and the financial report text and the expanded words are input into the target language model through the input function.

[0091] Among them, loading the preset target language model does not require repeated training, which greatly saves time and computing resources. Because training models often require a large amount of data and computing power, loading the preset target language model can directly use existing results. It is easy to deploy and expand quickly, and can significantly improve the efficiency of data processing.

[0092] S25, determining a current data report based on the target language model, the expanded words and the financial report text;

[0093] Among them, the current data report is the current data report.

[0094] Among them, the current data report organizes, summarizes and presents the key information in the current financial report data.

[0095] S26, performing a query operation in the current data report to obtain a query result of the current financial report data.

[0096] Exemplarily, performing a query operation in the current data report to obtain the query result of the current financial report data includes:

[0097] Obtain the industry type of the current financial report data;

[0098] When the industry type is the financial industry, a query operation corresponding to the financial industry is performed in the current data report to obtain profitability indicators, asset-liability indicators, and risk management indicators in the current data report, and the profitability indicators, asset-liability indicators, and risk management indicators are combined to obtain a query result of the current financial report data;

[0099] When the industry type is the name of the manufacturing industry, a query operation corresponding to the manufacturing industry is performed in the current data report to obtain the capacity utilization, production cost, and technological innovation information in the current data report, and the profitability indicators, asset-liability indicators, and risk management indicators are combined to obtain the query results of the current financial report data.

[0100] Among them, the financial industry includes one or a combination of banking, insurance, and securities.

[0101] Banks: Industrial and Commercial Bank of China, China Construction Bank, etc., providing financial services such as deposits, loans, payment and settlement.

[0102] Insurance: life insurance companies, property insurance companies.

[0103] Securities: securities companies, securities investment fund management companies.

[0104] Among them, in the financial industry, users pay attention to the profitability indicators, asset-liability indicators and risk management indicators of the enterprise, and combine the profitability indicators, asset-liability indicators and risk management indicators to obtain the query results of the current financial report data.

[0105] Among them, the manufacturing industry includes one or a combination of food, beverage, tobacco processing, clothing, textiles, leather, wood processing, furniture, and printing.

[0106] Among them, in the manufacturing industry, users focus on the profitability indicators, asset-liability indicators and risk management indicators of the enterprise, and combine the capacity utilization, production cost and technological innovation information to obtain the query results of the current financial report data.

[0107] Wherein, after performing a query operation in the current data report and obtaining a query result of the current financial report data, the financial report data query method includes:

[0108] A display area of ​​the screen is acquired, a display window of the display area is created, and the query result is displayed through the display window.

[0109] In the embodiment of the present invention, the beneficial effects lie in two aspects. On the one hand, a query operation is performed in the current data report to obtain the query results of the current financial report data. Since no manual query is required, the query time of the current financial report data is reduced, which is beneficial to improving the query efficiency of the current financial report data. On the other hand, since the automatic query is not prone to errors, it is beneficial to improve the reliability of the query results.

[0110] See also Figure 3 , Figure 3 yes Figure 1 A specific implementation flow diagram of step S23 is described in detail as follows:

[0111] S31, obtaining keywords in the financial report text;

[0112] The financial report text is processed by using a semantic role labeling method and a dependency syntax analysis method to obtain the processed financial report text and acquire keywords in the processed financial report text.

[0113] Among them, Semantic Role Labeling (SRL) is a natural language processing technology that assigns a specific semantic role to each component in a sentence by analyzing the predicate in the sentence. Semantic role labeling can not only capture the grammatical structure of the sentence, but more importantly, it can reveal the deep semantic information of the sentence. Therefore, through semantic role labeling, the meaning of the sentence can be understood more accurately.

[0114] Among them, dependency syntactic analysis determines the syntactic structure of a sentence by analyzing the dependency relationship between words in the sentence. This analysis technique reveals the dominant and dominated relationships between sentence components, such as subject-predicate relationships, verb-object relationships, etc., and expresses these relationships in the form of a tree structure.

[0115] S32: Select synonyms or near synonyms of the keyword as expansion words corresponding to the keyword.

[0116] In the embodiment of the present invention, the synonyms or near-synonyms of the keyword are selected as the expansion words corresponding to the keyword, which improves the richness and depth of the text content of the financial report and is conducive to mining more valuable information.

[0117] See also Figure 4 , Figure 4 yes Figure 1 A specific implementation flow diagram of step S25 is described in detail as follows:

[0118] S41, inputting the financial report text and the expanded word into the feature extractor of the target language model, performing feature extraction on the financial report text and the expanded word by the feature extractor, and obtaining a feature vector of the financial report text and a feature vector of the expanded word;

[0119] S42, concatenating the feature vector of the financial report text and the feature vector of the expanded word to generate a target feature vector of the current financial report data, inputting the target feature vector into the generator of the target language model, processing the target feature vector through the generator, and obtaining the current data report.

[0120] In an embodiment of the present invention, the target feature vector is input into the generator of the target language model, and the target feature vector is processed by the generator to obtain the current data report. The data report displays the financial report text in a structured manner, making the financial report text clearer and facilitating users to quickly find required information.

[0121] See also Figure 5 , Figure 5 yes Figure 1 A specific implementation flow diagram of step S26 is described in detail as follows:

[0122] S51, obtaining a preset query condition, and submitting the query condition to a query interface;

[0123] S52, executing a query operation corresponding to the query condition on the current data report through the query interface to obtain a query result of the current financial report data.

[0124] Exemplarily, performing a query operation corresponding to the query condition on the current data report through the query interface to obtain a query result of the current financial report data includes:

[0125] Obtain the industry type of the current financial report data;

[0126] When the industry type is the financial industry, the query operation corresponding to the financial industry is performed in the current data report through the query interface to obtain the profitability index, asset-liability index, and risk management index in the current data report, and the profitability index, asset-liability index, and risk management index are combined to obtain the query result of the current financial report data;

[0127] When the industry type is the name of the manufacturing industry, the query operation corresponding to the manufacturing industry is performed in the current data report through the query interface to obtain the capacity utilization, production cost, and technological innovation information in the current data report, and the profitability indicators, asset-liability indicators, and risk management indicators are combined to obtain the query results of the current financial report data.

[0128] In an embodiment of the present invention, a query operation corresponding to the query condition is performed on the current data report through the query interface to obtain a query result of the current financial report data. Since no manual query is required, the query time of the current financial report data is reduced, which is conducive to improving the query efficiency of the current financial report data.

[0129] See also Figure 6 , Figure 6 : is a schematic diagram of a structure of a financial report data query device in one embodiment of the present invention. Figure 6As shown, the financial report data query device includes an extraction module 101, an acquisition module 102, a first determination module 103, an input module 104, a second determination module 105, and a query module 106. The functional modules are described in detail as follows:

[0130] Extraction module 101, used to extract current financial report data from a data source;

[0131] An acquisition module 102 is used to acquire the financial report text in the current financial report data;

[0132] A first determination module 103, configured to determine, based on the financial report text, an expansion word corresponding to the current financial report data;

[0133] An input module 104, used to input the financial report text and the expanded words into a preset target language model;

[0134] A second determination module 105 is used to determine a current data report based on the target language model, the expanded words and the financial report text;

[0135] The query module 106 is used to perform a query operation in the current data report to obtain the query result of the current financial report data.

[0136] In one embodiment, the acquisition module 102 includes:

[0137] A processing subunit, configured to preprocess the current financial report data to obtain the preprocessed current financial report data;

[0138] The first acquisition subunit is used to acquire the financial report text in the current financial report data after preprocessing, and the preprocessing includes one or a combination of format conversion processing, duplicate data processing, and error data processing.

[0139] In one embodiment, the first determining module 103 includes:

[0140] A second acquisition subunit is used to acquire keywords in the financial report text;

[0141] The selection subunit is used to select synonyms or near synonyms of the keyword as the expansion word corresponding to the keyword.

[0142] In one embodiment, the input module 104 includes:

[0143] A loading subunit is used to obtain a model file and load a preset target language model from the model file;

[0144] The first input subunit is used to call the input function of the target language model, and input the financial report text and the expanded words into the target language model through the input function.

[0145] In one embodiment, the second determining module 105 includes:

[0146] An extraction subunit, used for inputting the financial report text and the expanded word into a feature extractor of the target language model, performing feature extraction on the financial report text and the expanded word through the feature extractor, and obtaining a feature vector of the financial report text and a feature vector of the expanded word;

[0147] The second input sub-unit is used to concatenate the feature vector of the financial report text and the feature vector of the expanded word to generate a target feature vector of the current financial report data, input the target feature vector into the generator of the target language model, and process the target feature vector through the generator to obtain the current data report.

[0148] In one embodiment, the query module 106 includes:

[0149] A third acquisition subunit is used to acquire a preset query condition and submit the query condition to the query interface;

[0150] The query subunit is used to perform a query operation corresponding to the query condition on the current data report through the query interface to obtain a query result of the current financial report data.

[0151] In one embodiment, the financial report data query device further includes:

[0152] The display module is used to obtain a display area of ​​the screen, create a display window of the display area, and display the query result through the display window.

[0153] In the embodiment of the present invention, the beneficial effects lie in two aspects. On the one hand, a query operation is performed in the current data report to obtain the query results of the current financial report data. Since no manual query is required, the query time of the current financial report data is reduced, which is beneficial to improving the query efficiency of the current financial report data. On the other hand, since the automatic query is not prone to errors, it is beneficial to improve the reliability of the query results.

[0154] The specific limitations on the financial report data query device can be found in the above limitations on the financial report data query method, which will not be repeated here.

[0155] Each module in the above financial report data query device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0156] See also Figure 7 , Figure 7 is a schematic diagram of a computer device in one embodiment of the present invention. In one embodiment, a computer device is provided. The computer device may be a server device, and its internal structure diagram may be as shown in FIG. Figure 7 The computer device includes a processor, a memory, a network interface and a database connected through a system bus.

[0157] The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the functions or steps of a financial report data query method can be implemented on the server-side device.

[0158] See also Figure 8 , Figure 8 is another structural diagram of a computer device in one embodiment of the present invention. In one embodiment, a computer device is provided. The computer device may be a client device, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the functions or steps of a financial report data query method can be implemented on the client device.

[0159] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor.

[0160] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description in the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0161] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0162] The above description and accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent possible changes only. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. Parts and subsamples of some embodiments may be included in or replace parts and subsamples of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of a stated sub-sample, whole, step, operation, element, and / or component, but do not exclude the presence or addition of one or more other sub-samples, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0163] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0164] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units can be 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 sub-samples can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other 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. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0165] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A financial report data query method, characterized in that: include: Extract current financial report data from data sources; Obtaining the financial report text in the current financial report data; Based on the financial report text, determining an expansion word corresponding to the current financial report data; Inputting the financial report text and the expanded words into a preset target language model; Determining a current data report based on the target language model, the expanded words, and the financial report text; A query operation is performed in the current data report to obtain a query result of the current financial report data.

2. The financial report data query method according to claim 1, characterized in that: The obtaining of the financial report text in the current financial report data includes: Preprocessing the current financial report data to obtain the preprocessed current financial report data; The financial report text in the current financial report data after preprocessing is obtained, wherein the preprocessing includes one or a combination of format conversion processing, duplicate data processing, and error data processing.

3. The financial report data query method according to claim 1, characterized in that: The step of determining, based on the financial report text, an expansion word corresponding to the current financial report data includes: Obtaining keywords in the financial report text; Select synonyms or near-synonyms of the keyword as expansion words corresponding to the keyword.

4. The financial report data query method according to claim 1, characterized in that: The step of inputting the financial report text and the expanded words into a preset target language model includes: Obtain a model file, and load a preset target language model from the model file; The input function of the target language model is called, and the financial report text and the expanded words are input into the target language model through the input function.

5. The financial report data query method according to claim 1, characterized in that: The determining of the current data report based on the target language model, the expanded word and the financial report text includes: Inputting the financial report text and the expanded words into the feature extractor of the target language model, performing feature extraction on the financial report text and the expanded words by the feature extractor, and obtaining a feature vector of the financial report text and a feature vector of the expanded words; The feature vector of the financial report text and the feature vector of the expanded word are concatenated to generate a target feature vector of the current financial report data, the target feature vector is input into the generator of the target language model, the target feature vector is processed by the generator to obtain the current data report.

6. The financial report data query method according to claim 1, characterized in that: The query operation is performed in the current data report to obtain the query result of the current financial report data, including: Obtaining preset query conditions and submitting the query conditions to the query interface; The query operation corresponding to the query condition is performed on the current data report through the query interface to obtain the query result of the current financial report data.

7. The financial report data query method according to any one of claims 1 to 6, characterized in that: After performing a query operation in the current data report and obtaining a query result of the current financial report data, the financial report data query method includes: A display area of ​​the screen is acquired, a display window of the display area is created, and the query result is displayed through the display window.

8. A financial report data query device, characterized in that: include: Extraction module, used to extract current financial report data from the data source; An acquisition module, used to acquire the financial report text in the current financial report data; A first determination module, configured to determine, based on the financial report text, an expansion word corresponding to the current financial report data; An input module, used for inputting the financial report text and the expanded words into a preset target language model; A second determination module is used to determine a current data report based on the target language model, the expanded word and the financial report text; The query module is used to perform a query operation in the current data report to obtain the query result of the current financial report data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the financial report data query method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the financial report data query method according to any one of claims 1 to 7 are implemented.

Images