A report data analysis method, device and medium

By using the preset attribute keyword database to determine the pending analysis keywords and matching analysis types, and generating data analysis results, the problem of inflexible report data analysis is solved, efficient data analysis is achieved, and labor and time costs are reduced.

CN118013949BActive Publication Date: 2024-12-06INSPUR GENERSOFT CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202410102699.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-24
Publication Date
2024-12-06
Estimated Expiration
2044-01-24

AI Technical Summary

Technical Problem

In the prior art, the report data analysis is not flexible enough, resulting in high labor and time costs and low data analysis efficiency.

Method used

By obtaining the data attribute text in the pending report, using the preset attribute keyword library to determine the pending analysis keywords, matching the corresponding analysis type, and generating data analysis results based on the selected analysis function, and providing them to the user terminal.

Benefits of technology

It realizes flexible data analysis, reduces users' need to understand the data analysis list, saves labor and time costs, and improves data analysis efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118013949B_ABST
    Figure CN118013949B_ABST
Patent Text Reader

Abstract

The present application provides a report data analysis method, device and medium, which belongs to the field of computer technology. It is used to solve the problems that report data analysis is not flexible enough, consumes labor costs and time costs, and has low data analysis efficiency. The method obtains a report to be processed; the report to be processed includes the data to be processed and its corresponding data attribute text; based on a preset attribute keyword library, the pending analysis keywords in the report to be processed are determined; according to the pending analysis keywords, the corresponding analysis type is matched. For each analysis type, one or more analysis functions are determined and displayed on the user terminal; after receiving each selected analysis function selected from the user terminal, the data analysis result corresponding to the analysis type is determined according to the report to be processed and the selected analysis function, and the data analysis result is stored in the report analysis data set.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a report data analysis method, device and medium. Background Art

[0002] With the continuous development of computer technology, the types and quantity of data reports are increasing, and high-quality data analysis is becoming more and more important.

[0003] When performing data analysis, there are often several data analysis reports, and there are also some data analysis requirements for the data analysis reports. The data analysis requirements for each analysis may be different. Data report analysts need to manually set the data analysis rules solidified in the code according to each data analysis requirement, and use manual methods to perform data analysis, data sorting, classification, etc. If data analysis is to be performed more flexibly, it is necessary to manually understand the overall picture of the data analysis list or manually adjust and analyze the data, which is time-consuming and has low data analysis efficiency. Summary of the invention

[0004] The embodiments of the present application provide a report data analysis method, device and medium, which are used to solve the problems that report data analysis is not flexible enough, consumes labor costs and time costs, and has low data analysis efficiency.

[0005] On the one hand, an embodiment of the present application provides a report data analysis method, the method comprising:

[0006] Obtaining a report to be processed; the report to be processed includes the data to be processed and its corresponding data attribute text;

[0007] Based on a preset attribute keyword library, determining the pending analysis keywords in the report to be processed;

[0008] According to the pending analysis keyword, matching the corresponding analysis type;

[0009] For each of the analysis types, one or more analysis functions are determined and displayed on a user terminal;

[0010] After receiving each selected analysis function selected from the user terminal, a data analysis result corresponding to the analysis type is determined according to the report to be processed and the selected analysis function, and the data analysis result is stored in a report analysis data set.

[0011] In one implementation of the present application, based on a preset attribute keyword library, determining the pending analysis keywords in the report to be processed specifically includes:

[0012] Input the data attribute text into a pre-trained short text recognition model to determine one or more corresponding first attribute keywords; wherein the first attribute keywords represent the attributes of the corresponding data to be processed;

[0013] Comparing each of the first attribute keywords with each of the second attribute keywords in the attribute keyword library, and comparing a combined attribute keyword corresponding to a plurality of the first attribute keywords with each of the second attribute keywords in the attribute keyword library;

[0014] According to the comparison result and the attribute keyword library, a keyword network corresponding to each of the second attribute keywords whose comparison similarity is greater than a first preset threshold is determined; wherein the keyword network at least includes the correlation degree between each of the second attribute keywords; the correlation degree is obtained based on the TF-IDF value of the attribute keyword in the report corresponding to the several historical analysis types;

[0015] Eliminate the node links in the keyword network whose correlation degree is less than a second preset threshold; wherein the node links represent that the plurality of second attribute keywords connected have a common analysis type;

[0016] The pending analysis keyword is generated according to the second attribute keyword corresponding to each node in the keyword network and the remaining node connections.

[0017] In one implementation of the present application, generating the pending analysis keyword according to the second attribute keyword corresponding to each node in the keyword network and the remaining node connections specifically includes:

[0018] Traversing the remaining node links, combining the second attribute keywords connected by the remaining node links in sequence to obtain a pending attribute keyword group; wherein the pending attribute keyword group includes at least two of the second attribute keywords;

[0019] According to the preset analysis type list, determining whether the pending attribute keyword group has a corresponding common analysis type;

[0020] If so, taking the pending attribute keyword group as an attribute keyword group, and concatenating each of the second attribute keywords in the attribute keyword group as a first pending analysis keyword;

[0021] The second attribute keyword corresponding to each node is used as the second pending analysis keyword, and the first pending analysis keyword and the second pending analysis keyword are used as the pending analysis keywords.

[0022] In one implementation of the present application, matching the corresponding analysis type according to the pending analysis keyword specifically includes:

[0023] The pending analysis keyword is input into a preset analysis type list to match the pending analysis keyword with the attribute keyword column in the analysis type list, so as to determine the analysis type in the same row as the matching attribute keyword according to the matched matching attribute keyword.

[0024] In one implementation of the present application, for each analysis type, one or more analysis functions are determined, specifically including:

[0025] Matching each of the analysis types with a preset basic analysis function set respectively;

[0026] In the case where it is determined that a basic analysis function corresponding to the analysis type exists in the preset basic analysis function set, determining that the corresponding analysis type is a primary analysis type, and adding the corresponding basic analysis function to the primary analysis type set;

[0027] In the case where it is determined that the analysis type corresponds to a combined analysis function obtained by combining a plurality of the basic analysis functions in the preset basic analysis function set, determining that the corresponding analysis type is a secondary analysis type, and adding the corresponding combined analysis function to the secondary analysis type set;

[0028] In the case where it is determined that the analysis type corresponds to an updated analysis function after modifying the custom item parameters of the basic analysis function or the combined analysis function, determining that the corresponding analysis type is a third-level analysis type, and sending parameter update information to the user terminal to add the corresponding combined analysis function to the third-level analysis type set according to the modification operation from the user terminal;

[0029] One or more of the analysis functions are determined according to the analysis functions in the primary analysis type set, the secondary analysis type set, and the tertiary analysis type set.

[0030] In one implementation of the present application, the basic analysis function and the combined analysis function have custom item parameters, and the custom item parameters are at least used to select the range of the data to be processed for analysis.

[0031] In one implementation of the present application, the method further includes:

[0032] Displaying the analysis functions in the primary analysis type set, the secondary analysis type set, and the tertiary analysis type set on the user terminal respectively;

[0033] Based on the basic analysis function update operation from the user terminal, the preset basic analysis function set is updated.

[0034] In one implementation of the present application, after receiving each selected analysis function selected from the user terminal, the method further includes:

[0035] Each of the analysis functions is added to a hidden control, so that each of the analysis functions can be displayed in combination through a function list in the hidden control.

[0036] On the other hand, an embodiment of the present application further provides a report data analysis device, the device comprising:

[0037] at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0038] Obtaining a report to be processed; the report to be processed includes the data to be processed and its corresponding data attribute text;

[0039] Based on a preset attribute keyword library, determining the pending analysis keywords in the report to be processed;

[0040] According to the pending analysis keyword, matching the corresponding analysis type;

[0041] For each of the analysis types, one or more analysis functions are determined and displayed on a user terminal;

[0042] After receiving each selected analysis function selected from the user terminal, a data analysis result corresponding to the analysis type is determined according to the report to be processed and the selected analysis function, and the data analysis result is stored in a report analysis data set.

[0043] On the other hand, the embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0044] Obtaining a report to be processed; the report to be processed includes the data to be processed and its corresponding data attribute text;

[0045] Based on a preset attribute keyword library, determining the pending analysis keywords in the report to be processed;

[0046] According to the pending analysis keyword, matching the corresponding analysis type;

[0047] For each of the analysis types, one or more analysis functions are determined and displayed on a user terminal;

[0048] After receiving each selected analysis function selected from the user terminal, a data analysis result corresponding to the analysis type is determined according to the report to be processed and the selected analysis function, and the data analysis result is stored in a report analysis data set.

[0049] Through the above scheme, the data attribute text in the pending report is used to obtain the pending analysis keywords used to determine the report analysis type, so as to obtain the analysis function for users to select according to actual needs, and then flexibly perform data analysis on the pending report. Flexible data analysis is achieved, and users do not need to understand the full picture of the information in the pending report, and receive adjustment and analysis data, which saves labor costs and can efficiently assist users in completing data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0051] Figure 1 A flow chart of a report data analysis method in an embodiment of the present application;

[0052] Figure 2 This is a structural diagram of a report data analysis device in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0054] The embodiments of the present application provide a report data analysis method, device and medium to solve the problems that report data analysis is not flexible enough, consumes labor costs and time costs, and has low data analysis efficiency.

[0055] The following describes in detail various embodiments of the present application in conjunction with the accompanying drawings.

[0056] The present application embodiment provides a report data analysis method, which can be applied to budget reports or profit reports. Figure 1 As shown, the method may include steps S101-S105:

[0057] S101, the server obtains a report to be processed.

[0058] The report to be processed includes the data to be processed and its corresponding data attribute text.

[0059] It should be noted that the server, as the executor of the report data analysis method, is only for exemplary purposes, and the executor is not limited to the server, and this application does not make any specific limitations on this.

[0060] For example, the report to be processed is a budget report, which contains budget numbers, execution numbers, and differences waiting to be processed. At the same time, the data to be processed has data attribute text that represents the data attributes. For example, if the data to be processed of a budget number is a number, data attribute text is required to indicate that the number is a budget number.

[0061] The pending reports may come from the user terminal. Before the user performs report data analysis, the user may send several pending reports to the server through the user terminal. The pending reports may also be pre-stored in the database. When the user indicates that report data analysis is required, the server calls the corresponding pending reports to perform report data analysis. This application does not specifically limit the source of the pending reports.

[0062] S102: The server determines pending analysis keywords in the report to be processed based on a preset attribute keyword library.

[0063] The attribute keyword library is used to determine the pending analysis keywords in the pending report. Although there are data attribute texts in the pending report, they cannot fully represent the pending analysis keywords used for data analysis. Some data attribute texts cannot reflect what kind of data analysis needs to be performed for the report data analysis. If the data attribute texts are processed by some text combination, text screening, etc., it can be flexibly, intelligently and accurately known what kind of data analysis needs to be performed through the input pending report. Therefore, it is necessary to determine the pending analysis keywords first. For example, there are data attribute texts such as budget number and execution number in the report. The pending analysis keywords for report data analysis can be such as budget completion rate, monthly cumulative budget number, monthly cumulative execution number, etc.

[0064] In the embodiment of the present application, based on the preset attribute keyword library, determining the pending analysis keywords in the report to be processed specifically includes:

[0065] First, the data attribute text is input into the pre-trained short text recognition model to determine the corresponding one or more first attribute keywords. The first attribute keyword represents the attribute of the corresponding data to be processed. Subsequently, each first attribute keyword is compared with each second attribute keyword in the attribute keyword library, and the combined attribute keyword corresponding to multiple first attribute keywords is compared with each second attribute keyword in the attribute keyword library. Then, based on the comparison results and the attribute keyword library, the keyword network corresponding to each second attribute keyword whose comparison similarity is greater than the first preset threshold is determined. The keyword network at least includes the degree of association between each second attribute keyword. The degree of association is obtained based on the TF-IDF value of the attribute keyword in the report corresponding to several historical analysis types. Then, the node links in the keyword network with a degree of association less than the second preset threshold are eliminated. The node links represent that the multiple second attribute keywords connected have a common analysis type. Finally, the undetermined analysis keywords are generated based on the second attribute keywords corresponding to each node in the keyword network and the remaining node links.

[0066] In other words, in the process of generating the pending analysis keywords, the server will process the data attribute text through the short text recognition model to obtain one or more first attribute keywords related to the data attribute text. The short text recognition model can be a neural network model or a machine learning model for text processing, and can be obtained by training a number of data attribute text samples marked with the first attribute keywords. The combined attribute keyword can correspond to multiple first attribute keywords. For example, the above-mentioned budget completion rate is a combined attribute keyword, which corresponds to the two first attribute keywords of the budget number and the execution number. Several second attribute keywords are stored in the attribute keyword library, and the second attribute keyword corresponds to the analysis type. The analysis type is associated with the analysis function used for report data analysis. After obtaining each first attribute keyword and combined attribute keyword, the server will respectively calculate the similarity between each first attribute keyword and combined attribute keyword and each second attribute keyword. The comparison similarity can be a cosine similarity. If the comparison similarity is greater than a pre-set first preset threshold, the corresponding second attribute keyword is added to the keyword network. The first preset threshold is set according to actual use, and this application does not make specific restrictions on this. The keyword network can be understood as a network consisting of several second attribute keywords and the lines connecting the second attribute keywords with an associated relationship. For example, the budget number and the execution number can be used to calculate the budget completion rate, so there is an associated relationship between the budget number and the execution number, with node connections. The degree of association between two second attribute keywords can be obtained by pre-processing data of several different historical analysis types of reports, screening the keywords therein, and calculating the TF-IDF value between the keywords.

[0067] Specifically, if two keywords appear at the same time in a report of the same historical analysis type, and their corresponding TF-IDF values ​​are higher than a preset value set by a user, then the average TF-IDF value of the two keywords is used as the degree of association. Then, by comparing the obtained second attribute keywords and the degree of association between two or more pre-stored second attribute keywords, a keyword network is generated. At the same time, in order to avoid the complexity of the keyword network, the server can also filter the degree of association through a pre-set second preset threshold value, and eliminate node connections with a smaller degree of association. A node connection corresponds to two second attribute keywords, and multiple node connections can correspond to more than two second attribute keywords. There is a common analysis type between the second attribute keywords with node connections. After eliminating the node connections whose degree of association does not meet the requirements, the server will rely on the remaining second attribute keywords and their node connections to generate pending analysis keywords.

[0068] Among them, in one embodiment of the present application, generating a pending analysis keyword according to the second attribute keyword corresponding to each node in the keyword network and the remaining node connection specifically includes:

[0069] First, the server traverses the remaining node lines, and combines the second attribute keywords connected by the remaining node lines in sequence to obtain a pending attribute keyword group. Among them, the pending attribute keyword group includes at least two second attribute keywords. According to the preset analysis type list, determine whether there is a corresponding common analysis type for the pending attribute keyword group. In the case of determining that there is a corresponding common analysis type for the pending attribute keyword group, the pending attribute keyword group is used as the attribute keyword group, and the second attribute keywords in the attribute keyword group are spliced ​​into the first pending analysis keyword. Subsequently, the second attribute keyword corresponding to each node is used as the second pending analysis keyword, and the first pending analysis keyword and the second pending analysis keyword are used as pending analysis keywords.

[0070] That is to say, the server can traverse the second attribute keywords that can be combined through the remaining node connections in sequence to obtain the pending attribute keyword group. For example, the remaining node connections are connected with keyword 1-keyword 2-keyword 3 in sequence, so the pending attribute keyword group is [keyword 1, keyword 2, keyword 3]. The preset analysis type list stores the correspondence between different attribute keyword groups and common analysis types, such as [keyword 1, keyword 2, keyword 3] corresponds to a common analysis type A, and [keyword 1, keyword 2] does not have a common analysis type, and [keyword 1, keyword 2, keyword 3, keyword 4] corresponds to a common analysis type B. If a pending attribute keyword group has a common analysis type, the server will perform keyword splicing to obtain the first pending analysis keyword, otherwise it will not be spliced. At the same time, the server uses each second attribute keyword in the keyword network as the second pending analysis keyword, thereby generating the final pending analysis keyword.

[0071] S103: The server matches the corresponding analysis type according to the pending analysis keyword.

[0072] After obtaining the above pending analysis keywords, the server will match the corresponding analysis type according to the pending analysis keywords, including:

[0073] The pending analysis keyword is input into the preset analysis type list to match the pending analysis keyword with the attribute keyword column in the analysis type list, so as to determine the analysis type in the same row as the matching attribute keyword according to the matched matching attribute keyword.

[0074] In other words, the server matches each pending analysis keyword with the preset analysis type list to obtain each analysis type in the preset analysis type list. Each line of the preset analysis type list is composed of an attribute keyword and its corresponding analysis type, and the specific content can be adjusted during actual use.

[0075] S104: The server determines one or more analysis functions for each analysis type and displays them on the user terminal.

[0076] In the embodiment of the present application, for each analysis type, one or more analysis functions are determined, specifically including:

[0077] Match each analysis type with a preset basic analysis function set respectively. When it is determined that there is a basic analysis function corresponding to the analysis type in the preset basic analysis function set, determine the corresponding analysis type as a primary analysis type, and add the corresponding basic analysis function to the primary analysis type set. When it is determined that the analysis type corresponds to a combined analysis function obtained by combining multiple basic analysis functions in the preset basic analysis function set, determine the corresponding analysis type as a secondary analysis type, and add the corresponding combined analysis function to the secondary analysis type set. When it is determined that the analysis type corresponds to an updated analysis function obtained by modifying the custom item parameters of the basic analysis function or the combined analysis function, determine the corresponding analysis type as a tertiary analysis type, and send parameter update information to the user terminal to add the corresponding combined analysis function to the tertiary analysis type set according to the modification operation from the user terminal. Determine one or more analysis functions based on the analysis functions in the primary analysis type set, the secondary analysis type set, and the tertiary analysis type set.

[0078] That is to say, the analysis type may have different levels of correspondence with the analysis function, and the level is related to the basic analysis function. If the analysis type corresponds to a preset basic analysis function, it means that there is a basic analysis function in the preset basic analysis function set that can be directly used to calculate the analysis type, and the analysis type is determined as a first-level analysis type, and the corresponding basic analysis function is added to the first-level analysis type set. If the analysis type corresponds to a combined analysis function after combining multiple basic analysis functions, the analysis type is determined to be a second-level analysis type, such as combining the basic analysis function for calculating the budget number and the basic analysis function for calculating the execution number to obtain a combined analysis function for calculating the budget completion rate, and obtaining a second-level analysis type set. When there are custom item parameters in the basic analysis function or combined analysis function corresponding to the analysis type, and the custom item parameters need to be modified, the function is determined to be an update analysis function, such as the cumulative budget number @YS (0:1:?) @ existence period custom item parameter (0:1:?), the first parameter 0 represents this year, the second parameter 1 represents the cumulative number starting from January, and the third parameter represents the month accumulated to the current analysis. For example, if February is analyzed, the total data of January + February of this year is taken. The server will send parameter update information to the user terminal, and the user can specify the custom item parameters for modification through the user terminal, thereby generating a three-level analysis type set. The server can display the analysis functions according to the set, and use the functions in the three sets as analysis functions.

[0079] The above basic analysis functions and combined analysis functions have custom item parameters, which are used to select at least the range of the data to be processed for analysis. The range can refer to the above time range, such as the first year parameter of @YS(0:1:?)@, the second cumulative start month parameter, and the third end analysis month parameter.

[0080] In one embodiment of the present application, the analysis functions in the primary analysis type set, the secondary analysis type set and the tertiary analysis type set are displayed on the user terminal, respectively. The preset basic analysis function set can also be updated based on the basic analysis function update operation from the user terminal.

[0081] In other words, the server can display the analysis functions in each set separately according to the set, so that users can clearly know which analysis functions belong to the basic analysis functions in the preset basic analysis function set, which ones need to be determined after the basic analysis functions are combined, and which ones need to be modified by custom item parameters. Users can update the basic analysis functions in the preset basic analysis function set according to their needs, for example, add the combined analysis functions in the secondary analysis type set to the preset basic analysis function set for subsequent direct calls through analysis types.

[0082] S105, after receiving the selected analysis functions selected by the user terminal, the server determines the data analysis results corresponding to the analysis type according to the report to be processed and the selected analysis function, and stores the data analysis results into the report analysis data set.

[0083] That is, the user can select the displayed analysis function as the selected analysis function through the user terminal, and the server uses the selected analysis function to perform data analysis on the report to be processed, obtains the data analysis results, and adds the data analysis results to the report analysis data set for the user to view or use. The data analysis data set can be stored on the server or sent to the user terminal.

[0084] By allowing users to customize analysis functions, flexible report data analysis can be achieved. Users do not need to understand the entire data analysis list to achieve low-time data analysis. This saves labor costs and time costs, and enables efficient data analysis.

[0085] In the embodiment of the present application, after receiving each selected analysis function selected by the user terminal, the method further includes:

[0086] Add each analysis function to the hidden control so that each analysis function can be displayed in combination through the function list in the hidden control.

[0087] That is to say, after determining that the user has selected the selected analysis function, the server can hide the analysis function in the user terminal interface, and when the user clicks the hidden space, the analysis function selection interface pops up again to adjust the selected analysis function. This allows users to adjust the analysis function more flexibly and achieve flexible and efficient data analysis.

[0088] Through the above scheme, the data attribute text in the pending report is used to obtain the pending analysis keywords used to determine the report analysis type, so as to obtain the analysis function for users to select according to actual needs, and then flexibly perform data analysis on the pending report. Flexible data analysis is achieved, and users do not need to understand the full picture of the information in the pending report, and receive adjustment and analysis data, which saves labor costs and can efficiently assist users in completing data analysis.

[0089] Figure 2 A structural diagram of a report data analysis device provided in an embodiment of the present application, such as Figure 2 As shown, the device includes:

[0090] At least one processor; and a memory in communication with the at least one processor. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0091] Get the report to be processed. The report to be processed includes the data to be processed and its corresponding data attribute text. Based on the preset attribute keyword library, determine the pending analysis keywords in the report to be processed. According to the pending analysis keywords, match the corresponding analysis type. For each analysis type, determine one or more analysis functions and display them on the user terminal. After receiving the selected analysis functions selected from the user terminal, determine the data analysis results corresponding to the analysis type according to the report to be processed and the selected analysis function, and store the data analysis results in the report analysis data set.

[0092] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0093] Get the report to be processed. The report to be processed includes the data to be processed and its corresponding data attribute text. Based on the preset attribute keyword library, determine the pending analysis keywords in the report to be processed. According to the pending analysis keywords, match the corresponding analysis type. For each analysis type, determine one or more analysis functions and display them on the user terminal. After receiving the selected analysis functions selected from the user terminal, determine the data analysis results corresponding to the analysis type according to the report to be processed and the selected analysis function, and store the data analysis results in the report analysis data set.

[0094] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0095] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0096] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0097] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A report data analysis method, It is characterized in that The method comprises: Obtaining a report to be processed; the report to be processed includes the data to be processed and its corresponding data attribute text; Based on a preset attribute keyword library, determining the pending analysis keywords in the report to be processed; According to the pending analysis keyword, matching the corresponding analysis type; For each of the analysis types, one or more analysis functions are determined and displayed on a user terminal; After receiving each selected analysis function selected from the user terminal, determining a data analysis result corresponding to the analysis type according to the report to be processed and the selected analysis function, and storing the data analysis result in a report analysis data set; Wherein, based on the preset attribute keyword library, determining the pending analysis keywords in the pending report to be processed specifically includes: Input the data attribute text into a pre-trained short text recognition model to determine one or more corresponding first attribute keywords; wherein the first attribute keywords represent the attributes of the corresponding data to be processed; Comparing each of the first attribute keywords with each of the second attribute keywords in the attribute keyword library, and comparing a combined attribute keyword corresponding to a plurality of the first attribute keywords with each of the second attribute keywords in the attribute keyword library; According to the comparison result and the attribute keyword library, a keyword network corresponding to each of the second attribute keywords whose comparison similarity is greater than a first preset threshold is determined; wherein the keyword network at least includes the correlation degree between each of the second attribute keywords; the correlation degree is obtained based on the TF-IDF value of the attribute keyword in the report corresponding to the several historical analysis types; Eliminate the node links in the keyword network whose correlation degree is less than a second preset threshold; wherein the node links represent that the plurality of second attribute keywords connected have a common analysis type; The pending analysis keyword is generated according to the second attribute keyword corresponding to each node in the keyword network and the remaining node connections.

2. A report data analysis method according to claim 1, It is characterized in that Generating the pending analysis keyword according to the second attribute keyword corresponding to each node in the keyword network and the remaining node connections specifically includes: Traversing the remaining node links, combining the second attribute keywords connected by the remaining node links in sequence to obtain a pending attribute keyword group; wherein the pending attribute keyword group includes at least two of the second attribute keywords; According to the preset analysis type list, determining whether the pending attribute keyword group has a corresponding common analysis type; If so, the undetermined attribute keyword group is used as an attribute keyword group, and each of the second attribute keywords in the attribute keyword group is spliced ​​into a first undetermined analysis keyword; The second attribute keyword corresponding to each node is used as the second pending analysis keyword, and the first pending analysis keyword and the second pending analysis keyword are used as the pending analysis keywords.

3. A report data analysis method according to claim 1, It is characterized in that According to the pending analysis keywords, the corresponding analysis types are matched, including: The pending analysis keyword is input into a preset analysis type list to match the pending analysis keyword with the attribute keyword column in the analysis type list, so as to determine the analysis type in the same row as the matching attribute keyword according to the matched matching attribute keyword.

4. A report data analysis method according to claim 1, It is characterized in that For each analysis type, one or more analysis functions are determined, specifically including: Matching each of the analysis types with a preset basic analysis function set respectively; In the case where it is determined that a basic analysis function corresponding to the analysis type exists in the preset basic analysis function set, determining that the corresponding analysis type is a primary analysis type, and adding the corresponding basic analysis function to the primary analysis type set; In the case where it is determined that the analysis type corresponds to a combined analysis function obtained by combining a plurality of the basic analysis functions in the preset basic analysis function set, determining that the corresponding analysis type is a secondary analysis type, and adding the corresponding combined analysis function to the secondary analysis type set; In the case where it is determined that the analysis type corresponds to an updated analysis function after modifying the custom item parameters of the basic analysis function or the combined analysis function, determining that the corresponding analysis type is a third-level analysis type, and sending parameter update information to the user terminal to add the corresponding combined analysis function to the third-level analysis type set according to the modification operation from the user terminal; One or more of the analysis functions are determined according to the analysis functions in the primary analysis type set, the secondary analysis type set, and the tertiary analysis type set.

5. A report data analysis method according to claim 4, It is characterized in that The basic analysis function and the combined analysis function have user-defined item parameters, and the user-defined item parameters are at least used to select the range of the data to be processed for analysis.

6. A report data analysis method according to claim 4, It is characterized in that The method further comprises: Displaying the analysis functions in the primary analysis type set, the secondary analysis type set, and the tertiary analysis type set on the user terminal respectively; Based on the basic analysis function update operation from the user terminal, the preset basic analysis function set is updated.

7. A report data analysis method according to claim 1, It is characterized in that After receiving each selected analysis function selected from the user terminal, the method further includes: Each of the analysis functions is added to a hidden control, so that each of the analysis functions can be displayed in combination through a function list in the hidden control.

8. A report data analysis device, It is characterized in that The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a report data analysis method as described in any one of claims 1 to 7.

9. A non-volatile computer storage medium storing computer executable instructions, It is characterized in that The computer executable instructions can execute a report data analysis method as described in any one of claims 1 to 7 above.

Citation Information

Patent Citations

  • Financial statement data processing method and device, computer equipment and storage medium

    CN110674131A