Financial statement intelligent issuing management and control method, device and equipment based on artificial intelligence and computer readable storage medium

Abstract

The invention discloses a financial statement intelligent issuing management and control method, device and equipment based on artificial intelligence and a computer readable storage medium, and the method comprises the steps: when there is a financial statement issuing demand, obtaining a plurality of financial statements based on historical issuing information of a plurality of historical issued financial statements; dividing the current financial statement issuing demand into a first financial statement issuing demand and a second financial statement issuing demand; generating a first financial statement issuing control parameter according to the first financial statement issuing demand and the historical issuing information, and generating a first financial statement based on the first financial statement issuing control parameter; generating a second financial statement issuing control parameter according to the second financial statement issuing demand and a financial statement issuing control model which is trained to converge in advance, and generating a second financial statement based on the second financial statement issuing control parameter; and performing fusion operation on the two financial statements to obtain a comprehensive financial statement, so that the intelligent issuing efficiency and the issuing reliability of the financial statements can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based financial statement intelligent issuance control method, device, equipment and computer-readable storage medium. Background Art

[0002] At present, more and more companies are moving towards standardization and formalization, and the control over financial statements is becoming more comprehensive and stricter.

[0003] Generally speaking, most companies have a financial department. When the relevant department needs to issue financial statements, the relevant personnel need to submit an application for the issuance of financial statements. After the application for the issuance of financial statements is reviewed and approved by the relevant authorized personnel, the relevant authorized personnel of the financial department will further issue financial statements according to the pre-established template. It can be seen that the current way of issuing financial statements mainly depends on financial personnel, and the form of financial statements is relatively fixed, which is not only not conducive to improving the efficiency of issuing financial statements, but also not conducive to improving the matching degree between the issued financial statements and actual needs. Summary of the invention

[0004] The present invention provides an artificial intelligence-based intelligent issuance control method, device, equipment and computer-readable storage medium for financial statements, which can solve the problems in related technologies that are not conducive to improving the efficiency of issuing financial statements and not conducive to improving the matching degree between the issued financial statements and actual needs, thereby realizing intelligent issuance control of financial statements, which is conducive to improving the efficiency of issuing financial statements and the matching degree between the issued financial statements and actual needs.

[0005] The technical solution of this application is implemented as follows:

[0006] An artificial intelligence-based intelligent financial statement issuance control method, the method comprising:

[0007] Collect the current multi-dimensional enterprise information of the target controlled enterprise, and determine whether the target controlled enterprise currently meets the pre-set financial statement issuance conditions based on the multi-dimensional enterprise information;

[0008] When it is determined that the target controlled enterprise currently meets the financial statement issuance conditions, target multi-dimensional information associated with the issuance of financial statements is screened from the multi-dimensional enterprise information, and the target multi-dimensional information is input into a financial statement issuance analysis model that has been pre-trained to convergence, to obtain the current financial statement issuance requirements of the target controlled enterprise;

[0009] Based on historical issuance information corresponding to several financial statements that have been issued in the past, the current financial statement issuance requirement is divided into a first financial statement issuance requirement and a second financial statement issuance requirement, wherein the first financial statement issuance requirement includes financial statement issuance requirements whose matching degree with the historical issuance information is greater than or equal to a matching degree threshold, and the second financial statement issuance requirement includes financial statement issuance requirements whose matching degree with the historical issuance information is less than the matching degree threshold;

[0010] Generate a first financial statement issuance control parameter according to the first financial statement issuance requirement and the historical issuance information, and generate a first financial statement based on the first financial statement issuance control parameter;

[0011] Generate a second financial statement issuance control parameter according to the second financial statement issuance requirement and a financial statement issuance control model that has been pre-trained to convergence, and generate a second financial statement based on the second financial statement issuance control parameter;

[0012] A fusion operation is performed on the first financial statement and the second financial statement to obtain a comprehensive financial statement, and the comprehensive financial statement is sent to at least one authorized person.

[0013] As an optional implementation, in the first aspect of the present invention, performing a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement includes:

[0014] Extracting first key report content in the first financial report and second key report content in the second financial report, performing a content fusion operation on the first key report content and the second key report content to obtain fused report content;

[0015] Extracting a first formal attribute corresponding to the first financial statement and a second formal attribute corresponding to the second financial statement, and performing a formal attribute fusion operation on the first formal attribute and the second formal attribute to obtain a fused formal attribute;

[0016] According to the fusion form attributes and the pre-determined visualization requirements, the fusion report content is visualized to obtain a visualized comprehensive financial report.

[0017] As an optional implementation manner, in the first aspect of the present invention, performing a formal attribute fusion operation on the first formal attribute and the second formal attribute to obtain a fused formal attribute includes:

[0018] According to the first formal attribute and the second formal attribute, determining from the first formal attribute and the second formal attribute respectively a first independent formal attribute corresponding to the first formal attribute, a second independent formal attribute corresponding to the second formal attribute, first attribute information corresponding to a formal attribute to be transitioned between the first formal attribute information and the second formal attribute information, and second attribute information corresponding to a formal attribute to be transitioned between the second formal attribute information and the first formal attribute;

[0019] generating transition attribute information corresponding to the attribute in the form to be transitioned based on the first attribute information and the second attribute information corresponding to the attribute in the form to be transitioned;

[0020] Based on the attribute information corresponding to the first independent form attribute, the attribute information corresponding to the second independent form attribute, and the transition attribute information corresponding to the to-be-transitioned form attribute, fused form attribute information is generated.

[0021] As an optional implementation manner, in the first aspect of the present invention, the first independent formal attribute is a formal attribute not included in the second formal attribute; the second independent formal attribute is a formal attribute not included in the first formal attribute;

[0022] The formal attribute to be transitioned includes the first formal attribute and the common formal attribute of the second formal attribute, the first attribute information is the attribute information corresponding to the common formal attribute in the first formal attribute, and the second attribute information is the attribute information corresponding to the common formal attribute in the second formal attribute;

[0023] Among them, the multi-dimensional enterprise information includes all department levels in the target controlled enterprise, department information corresponding to all departments in each department level, personnel information corresponding to all personnel in each department, and current financial planning information of each department; the current financial planning information of each department includes the current established financial planning information of each department and the current emergency financial planning information of each department.

[0024] As an optional implementation manner, in the first aspect of the present invention, the step of generating transition attribute information corresponding to the to-be-transitioned form attribute based on the first attribute information and the second attribute information corresponding to the to-be-transitioned form attribute includes:

[0025] Calculating the attribute information deviation between the first attribute information and the second attribute information, and if the attribute information deviation indicates that both belong to the preset attribute information category, determining the first attribute information or the second attribute information or the average attribute information of the two as the transition attribute information corresponding to the attribute to be transitioned;

[0026] If the attribute information deviation indicates that the two do not belong to the preset attribute information category, generating a first adjustment parameter of the first attribute information and a second adjustment parameter of the second attribute information based on the attribute information deviation;

[0027] performing an adjustment operation on the first attribute information based on the first adjustment parameter to obtain first adjusted attribute information, and performing an adjustment operation on the second attribute information based on the second adjustment parameter to obtain second adjusted attribute information; wherein the first adjusted attribute information and the second adjusted attribute information belong to the preset attribute information category;

[0028] The first adjusted attribute information or the second adjusted attribute information or average adjusted attribute information of the two is determined as transition attribute information corresponding to the attribute to be transitioned.

[0029] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0030] After sending the consolidated financial statements to at least one of the authorized persons, monitoring the adjustment operations of an authorized person on the consolidated financial statements;

[0031] Determining the type of object that the authorized person wants to adjust according to the adjustment operation, the object type includes a report content type and / or a report form type; wherein the report content type is used to indicate that the object that the authorized person wants to adjust is the target content of the comprehensive financial statement, and the report form type is used to indicate that the object that the authorized person wants to adjust is the form attribute of the comprehensive financial statement;

[0032] When the object type is the report content type and the certain authorized person has the adjustment authority for the target content, a target information set is collected when the certain authorized person triggers the adjustment operation, and the information set includes the triggering location when the certain authorized person triggers the adjustment operation, the triggering time when the certain authorized person triggers the adjustment operation, the personnel information of the accompanying person when the certain authorized person triggers the adjustment operation, the issuance of the adjustment instruction corresponding to the target content when the certain authorized person triggers the adjustment operation, the facial expression information when the certain authorized person triggers the adjustment operation, the operation speed information when the certain authorized person triggers the adjustment operation, the historical operation speed information when the certain authorized person triggers the same adjustment operation in the past, and the interaction information between the certain authorized person and the accompanying person when the certain authorized person triggers the adjustment operation;

[0033] Determining, based on the target information set, whether the negative impact of the adjustment operation triggered by the certain authorized person on the comprehensive financial statements is greater than or equal to a preset degree threshold;

[0034] When the degree of negative impact is greater than or equal to the preset degree threshold, a locking operation is performed on the operation authority of the comprehensive financial statement, and it is determined whether there is any associated report content in the comprehensive financial statement that has a vested interest in the target content. If there is such associated report content, a content hiding operation is performed on the associated report content after locking the comprehensive financial statement; the content hiding operation includes a direct hiding operation of not displaying the associated report content or an indirect hiding operation of converting the associated report content into preset characters.

[0035] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0036] After generating the comprehensive financial statements, determining whether the comprehensive financial statements need to be displayed externally;

[0037] If the comprehensive financial statements need to be displayed externally, determine the display target of the comprehensive financial statements;

[0038] Based on the display-oriented object, determining the financial statement reading habits of the display-oriented object and the highly concerned statement contents of the display-oriented object;

[0039] According to the financial statement reading habits and the high-attention statement contents, matching optimization operations are performed on the comprehensive financial statements to generate target financial statements for the display-oriented object.

[0040] The second aspect of the present invention discloses an intelligent financial statement issuance control device based on artificial intelligence, the device comprising:

[0041] A demand judgment module is used to collect the current multi-dimensional enterprise information of the target controlled enterprise, and judge whether the target controlled enterprise currently meets the pre-set financial statement issuance conditions based on the multi-dimensional enterprise information;

[0042] An information screening module, configured to screen target multi-dimensional information associated with the issuance of financial statements from the multi-dimensional enterprise information when the demand judgment module determines that the target controlled enterprise currently meets the conditions for issuing financial statements;

[0043] The issuance control module is used to input the target multi-dimensional information into the financial statement issuance analysis model that has been pre-trained to convergence, and obtain the current financial statement issuance requirements of the target controlled enterprise;

[0044] The issuance control module is further used to divide the current financial statement issuance demand into a first financial statement issuance demand and a second financial statement issuance demand based on historical issuance information corresponding to several financial statements that have been issued in the past, wherein the first financial statement issuance demand includes financial statement issuance demands whose matching degree with the historical issuance information is greater than or equal to a matching degree threshold, and the second financial statement issuance demand includes financial statement issuance demands whose matching degree with the historical issuance information is less than the matching degree threshold; and, based on the first financial statement issuance demand and the historical issuance information, generate a first financial statement issuance control parameter, and generate a first financial statement based on the first financial statement issuance control parameter; and, based on the second financial statement issuance demand and a financial statement issuance control model pre-trained to convergence, generate a second financial statement issuance control parameter, and generate a second financial statement based on the second financial statement issuance control parameter;

[0045] A fusion control module, used for performing a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement;

[0046] The report providing module is used to send the comprehensive financial report to at least one authorized person.

[0047] As an optional implementation, in the second aspect of the present invention, the specific manner in which the fusion control module performs a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement includes:

[0048] Extracting first key report content in the first financial report and second key report content in the second financial report, performing a content fusion operation on the first key report content and the second key report content to obtain fused report content;

[0049] Extracting a first formal attribute corresponding to the first financial statement and a second formal attribute corresponding to the second financial statement, and performing a formal attribute fusion operation on the first formal attribute and the second formal attribute to obtain a fused formal attribute;

[0050] According to the fusion form attributes and the pre-determined visualization requirements, the fusion report content is visualized to obtain a visualized comprehensive financial report.

[0051] As an optional implementation, in the second aspect of the present invention, the fusion control module performs a form attribute fusion operation on the first form attribute and the second form attribute to obtain the fused form attribute in a specific manner including:

[0052] According to the first formal attribute and the second formal attribute, determining from the first formal attribute and the second formal attribute respectively a first independent formal attribute corresponding to the first formal attribute, a second independent formal attribute corresponding to the second formal attribute, first attribute information corresponding to a formal attribute to be transitioned between the first formal attribute information and the second formal attribute information, and second attribute information corresponding to a formal attribute to be transitioned between the second formal attribute information and the first formal attribute;

[0053] generating transition attribute information corresponding to the attribute in the form to be transitioned based on the first attribute information and the second attribute information corresponding to the attribute in the form to be transitioned;

[0054] Based on the attribute information corresponding to the first independent form attribute, the attribute information corresponding to the second independent form attribute, and the transition attribute information corresponding to the to-be-transitioned form attribute, fused form attribute information is generated.

[0055] As an optional implementation manner, in the second aspect of the present invention, the first independent formal attribute is a formal attribute not included in the second formal attribute; the second independent formal attribute is a formal attribute not included in the first formal attribute;

[0056] The formal attribute to be transitioned includes the first formal attribute and the common formal attribute of the second formal attribute, the first attribute information is the attribute information corresponding to the common formal attribute in the first formal attribute, and the second attribute information is the attribute information corresponding to the common formal attribute in the second formal attribute;

[0057] Among them, the multi-dimensional enterprise information includes all department levels in the target controlled enterprise, department information corresponding to all departments in each department level, personnel information corresponding to all personnel in each department, and current financial planning information of each department; the current financial planning information of each department includes the current established financial planning information of each department and the current emergency financial planning information of each department.

[0058] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the fusion control module generates the transition attribute information corresponding to the to-be-transitioned form attribute based on the first attribute information and the second attribute information corresponding to the to-be-transitioned form attribute includes:

[0059] Calculating the attribute information deviation between the first attribute information and the second attribute information, and if the attribute information deviation indicates that both belong to the preset attribute information category, determining the first attribute information or the second attribute information or the average attribute information of the two as the transition attribute information corresponding to the attribute to be transitioned;

[0060] If the attribute information deviation indicates that the two do not belong to the preset attribute information category, generating a first adjustment parameter of the first attribute information and a second adjustment parameter of the second attribute information based on the attribute information deviation;

[0061] performing an adjustment operation on the first attribute information based on the first adjustment parameter to obtain first adjusted attribute information, and performing an adjustment operation on the second attribute information based on the second adjustment parameter to obtain second adjusted attribute information; wherein the first adjusted attribute information and the second adjusted attribute information belong to the preset attribute information category;

[0062] The first adjusted attribute information or the second adjusted attribute information or average adjusted attribute information of the two is determined as transition attribute information corresponding to the attribute to be transitioned.

[0063] As an optional implementation, in the second aspect of the present invention, the device further includes a report management module, and the report management module is used to:

[0064] After sending the consolidated financial statements to at least one of the authorized persons, monitoring the adjustment operations of an authorized person on the consolidated financial statements;

[0065] Determining the type of object that the authorized person wants to adjust according to the adjustment operation, the object type includes a report content type and / or a report form type; wherein the report content type is used to indicate that the object that the authorized person wants to adjust is the target content of the comprehensive financial statement, and the report form type is used to indicate that the object that the authorized person wants to adjust is the form attribute of the comprehensive financial statement;

[0066] When the object type is the report content type and the certain authorized person has the adjustment authority for the target content, a target information set is collected when the certain authorized person triggers the adjustment operation, and the information set includes the triggering location when the certain authorized person triggers the adjustment operation, the triggering time when the certain authorized person triggers the adjustment operation, the personnel information of the accompanying person when the certain authorized person triggers the adjustment operation, the issuance of the adjustment instruction corresponding to the target content when the certain authorized person triggers the adjustment operation, the facial expression information when the certain authorized person triggers the adjustment operation, the operation speed information when the certain authorized person triggers the adjustment operation, the historical operation speed information when the certain authorized person triggers the same adjustment operation in the past, and the interaction information between the certain authorized person and the accompanying person when the certain authorized person triggers the adjustment operation;

[0067] Determining, based on the target information set, whether the negative impact of the adjustment operation triggered by the certain authorized person on the comprehensive financial statements is greater than or equal to a preset degree threshold;

[0068] When the degree of negative impact is greater than or equal to the preset degree threshold, a locking operation is performed on the operation authority of the comprehensive financial statement, and it is determined whether there is any associated report content in the comprehensive financial statement that has a vested interest in the target content. If there is such associated report content, a content hiding operation is performed on the associated report content after locking the comprehensive financial statement; the content hiding operation includes a direct hiding operation of not displaying the associated report content or an indirect hiding operation of converting the associated report content into preset characters.

[0069] As an optional implementation, in the second aspect of the present invention, the device further includes a report optimization module, and the report optimization module is used to:

[0070] After generating the comprehensive financial statements, determining whether the comprehensive financial statements need to be displayed externally;

[0071] If the comprehensive financial statements need to be displayed externally, determine the display target of the comprehensive financial statements;

[0072] Based on the display-oriented object, determining the financial statement reading habits of the display-oriented object and the highly concerned statement contents of the display-oriented object;

[0073] According to the financial statement reading habits and the high-attention statement contents, matching optimization operations are performed on the comprehensive financial statements to generate target financial statements for the display-oriented object.

[0074] The third aspect of the present invention discloses another intelligent financial statement issuance control device based on artificial intelligence, the device comprising:

[0075] A memory storing executable program code;

[0076] a processor coupled to the memory;

[0077] The processor calls the executable program code stored in the memory to execute part or all of the steps in the intelligent issuance and control method of financial statements based on artificial intelligence disclosed in the first aspect of the present invention.

[0078] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the intelligent issuance and control method of financial statements based on artificial intelligence disclosed in the first aspect of the present invention.

[0079] Compared with the prior art, the method, device, equipment and computer-readable storage medium for intelligent issuance and control of financial statements based on artificial intelligence provided by the present invention have the following beneficial effects: for any target controlled enterprise, it is possible to realize intelligent judgment on whether it has a demand for issuing financial statements based on the multi-dimensional information of the target controlled enterprise, without waiting for the manual application of relevant personnel, which is conducive to improving the timeliness and convenience of issuing financial statements; in addition, it is also possible to automatically analyze the current financial statement issuance needs of the enterprise based on the multi-dimensional information of the enterprise that has a correlation with the issuance of financial statements, and input it into the financial statement issuance analysis model, so as to improve the analysis efficiency and accuracy of the financial statement issuance needs; in addition, after analyzing the current financial statement issuance needs of the enterprise, it is also possible to classify the financial statement issuance needs based on the historical statement issuance information, and then generate corresponding statement issuance control parameters according to the classification results, and then generate corresponding financial statements based on the statement issuance control parameters, and then merge multiple financial statements, which is not only conducive to improving the generation efficiency and convenience of financial statements, but also conducive to improving the matching degree between the generated financial statements and actual needs. Furthermore, when merging the two major financial statements, the report content and report form attributes can be merged separately, which is conducive to improving the fusion efficiency and fusion reliability of the financial statements; further, when merging the formal attributes of the financial statements, the different formal attributes of different financial tables and the transition attributes of different financial tables can be considered separately, which is conducive to improving the fusion reliability of the report form attributes and reducing the readability of the financial tables due to conflicts in the form attributes of the tables or unnatural transitions; further, it is also possible to intelligently generate transition attribute information based on the correspondence between the deviations between the attribute information and the preset attribute information category, thereby realizing the intelligent determination of the transition attribute information, which is conducive to improving the accuracy and reliability of the generated transition attribute information, and further to improving the accuracy of the fused attribute information. Accuracy and reliability; in addition, after the generated comprehensive financial statements are sent to the authorized personnel, it is also possible to implement supervision of the financial statement adjustment operations for the authorized personnel, and comprehensively judge the negative impact of the authorized personnel's adjustment of the financial statements based on the multi-dimensional information when the authorized personnel who triggered the financial statement adjustment operation triggered the financial statement adjustment operation, thereby improving the accuracy and comprehensiveness of the control over the authorized personnel's financial statement adjustment behavior, which is beneficial to improving the security of the financial statements; in addition, when the authorized personnel adjust the financial statements, they can further make an intelligent judgment on the content of the associated statements with a stake, and then perform content hiding operations on the content of the associated statements with a stake based on the judgment results, thereby realizing the linkage control of the content of the associated statements when there is a risk in adjusting the financial statements, which can further improve the security of the financial statements.Furthermore, after the comprehensive financial statements are generated, if the comprehensive financial statements need to be displayed externally, adaptive optimization operations are performed on the comprehensive financial statements based on the financial statement reading habits and high-attention report content of the display-oriented objects of the comprehensive financial statements. This is conducive to expanding the application scenarios of the intelligent financial statement issuance method, and can also improve the matching degree between the optimized financial statements and the reference needs of their display-oriented objects, which is conducive to improving the convenience and efficiency of the display-oriented objects in consulting the optimized financial statements. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0081] Figure 1 It is a flowchart of an artificial intelligence-based intelligent issuance and control method for financial statements provided by an embodiment of the present invention;

[0082] Figure 2 It is a structural schematic diagram of an intelligent financial statement issuance control device based on artificial intelligence provided by an embodiment of the present invention;

[0083] Figure 3 It is a structural schematic diagram of another intelligent financial statement issuance control device based on artificial intelligence provided by an embodiment of the present invention;

[0084] Figure 4 It is a structural diagram of another artificial intelligence-based financial statement intelligent issuance control device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0086] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0087] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0088] The present invention provides a method, device, equipment and computer-readable storage medium for intelligent issuance and control of financial statements based on artificial intelligence, which can realize intelligent judgment on whether the target controlled enterprise has a demand for issuing financial statements according to its multi-dimensional information, without waiting for the relevant personnel to manually apply, which is conducive to improving the timeliness and convenience of issuing financial statements; in addition, it can also be based on the multi-dimensional information of the enterprise that has a correlation with the issuance of financial statements, and input it into the financial statement issuance analysis model to automatically analyze the current financial statement issuance needs of the enterprise, which is conducive to improving the analysis efficiency and accuracy of the financial statement issuance needs; in addition, after analyzing the current financial statement issuance needs of the enterprise, it can also classify the financial statement issuance needs based on the historical statement issuance information, and then generate corresponding statement issuance control parameters according to the classification results, and then generate corresponding financial statements based on the statement issuance control parameters, and then merge multiple financial statements, which is not only conducive to improving the generation efficiency and convenience of financial statements, but also conducive to improving the matching degree between the generated financial statements and actual needs. The following are detailed descriptions.

[0089] Embodiment 1

[0090] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for intelligently issuing and controlling financial statements based on artificial intelligence provided by an embodiment of the present invention. Figure 1The described method is applied to an intelligent management device of an enterprise, which can be integrated in a local server of the enterprise or in a cloud server corresponding to the enterprise. Furthermore, if integrated in a cloud server, the cloud server can be a server for one enterprise or a server for multiple enterprises, which is not limited in the embodiments of the present invention. Figure 1 As shown, the method may include the following operations:

[0091] Step 101: Collect the current multi-dimensional enterprise information of the target controlled enterprise, and determine whether the target controlled enterprise currently meets the pre-set financial statement issuance conditions based on the multi-dimensional enterprise information.

[0092] In an embodiment of the present invention, the multi-dimensional enterprise information includes all departmental levels in the target managed enterprise, departmental information corresponding to all departments in each departmental level, personnel information corresponding to all personnel in each department, and the current financial planning information of each department; the current financial planning information of each department includes the current established financial planning information of each department (such as financial reimbursement planning information, salary payment planning information, enterprise tax payment planning information, etc.) and the current emergency financial planning information of each department (such as employee resignation settlement information, item purchase settlement information, project reward payment information, external cooperation settlement information, etc.).

[0093] Step 102: When it is determined that the target controlled enterprise currently meets the conditions for issuing financial statements, target multi-dimensional information that is associated with issuing financial statements is screened from the multi-dimensional enterprise information, and the target multi-dimensional information is input into a financial statement issuance analysis model that has been pre-trained to convergence to obtain the current financial statement issuance requirements of the target controlled enterprise.

[0094] In an embodiment of the present invention, the financial statement issuance analysis model is obtained by training based on a number of historical financial statement issuance information as training samples. The historical financial statement issuance information may include one or more of historical financial statement issuance request information, financial statement issuance results corresponding to the historical financial statement issuance request information, evaluation information of the financial statement issuance results by the financial statement requester, and authorization adjustment information of the financial statement issuance results by relevant authorized personnel. Furthermore, the financial statement issuance analysis model may specifically include a keyword extraction model, which is used to extract keywords from the multi-dimensional information corresponding to the enterprise and evaluate the degree of financial demand corresponding to the keyword.

[0095] Step 103: Based on the historical issuance information corresponding to several financial statements that have been issued in the past, the current financial statement issuance requirement is divided into a first financial statement issuance requirement and a second financial statement issuance requirement.

[0096] In an embodiment of the present invention, the first financial statement issuance requirement includes a financial statement issuance requirement whose matching degree with historical issuance information is greater than or equal to a matching degree threshold, and the second financial statement issuance requirement includes a financial statement issuance requirement whose matching degree with historical issuance information is less than the matching degree threshold.

[0097] Step 104: Generate first financial statement issuance control parameters according to the first financial statement issuance requirement and historical issuance information, and generate the first financial statement based on the first financial statement issuance control parameters; and generate second financial statement issuance control parameters according to the second financial statement issuance requirement and a financial statement issuance control model that has been pre-trained to convergence, and generate the second financial statement based on the second financial statement issuance control parameters.

[0098] Among them, the financial statement issuance control model is obtained based on a number of historical financial statement issuance control parameters, the corresponding historical financial statement issuance results and the satisfaction level of relevant personnel with the historical financial statement issuance results.

[0099] Step 105: Perform a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement, and send the comprehensive financial statement to at least one authorized person.

[0100] It should be noted that the method described in the embodiment of the present invention can realize intelligent judgment on whether the target controlled enterprise has the demand for issuing financial statements based on the multi-dimensional information of the target controlled enterprise, without waiting for the relevant personnel to apply manually, which is conducive to improving the timeliness and convenience of issuing financial statements; in addition, it can also automatically analyze the current financial statement issuance needs of the enterprise based on the multi-dimensional information of the enterprise that has a correlation with the issuance of financial statements, and input it into the financial statement issuance analysis model, so as to improve the analysis efficiency and accuracy of the financial statement issuance needs; in addition, after analyzing the current financial statement issuance needs of the enterprise, it can also classify the financial statement issuance needs based on the historical statement issuance information, and then generate corresponding statement issuance control parameters according to the classification results, and then generate corresponding financial statements based on the statement issuance control parameters, and then merge multiple financial statements, which is not only conducive to improving the efficiency and convenience of generating financial statements, but also conducive to improving the matching degree between the generated financial statements and actual needs.

[0101] In an optional embodiment, the above-mentioned performing a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement may include:

[0102] Extracting the first key report content in the first financial report and the second key report content in the second financial report, performing content fusion operations (such as report content splicing operations, report content logical operation operations, report content mathematical operation operations, report content merging operations, report content calibration operations, etc.) on the first key report content and the second key report content to obtain fused report content;

[0103] Extracting first formal attributes (such as background color attributes, font size attributes, font color attributes, etc.) corresponding to the first financial statement and second formal attributes corresponding to the second financial statement, and performing a formal attribute fusion operation on the first formal attributes and the second formal attributes to obtain fused formal attributes;

[0104] According to the fusion form attributes and pre-determined visualization requirements, the fusion report content is visualized to obtain a visualized comprehensive financial report.

[0105] It can be seen that this optional embodiment can integrate the report content and report form attributes separately when integrating two major financial statements, which is beneficial to improving the integration efficiency and integration reliability of the financial statements.

[0106] In another optional embodiment, performing the form attribute fusion operation on the first form attribute and the second form attribute to obtain the fused form attribute may include:

[0107] According to the first form attribute and the second form attribute, respectively determine from the first form attribute and the second form attribute a first independent form attribute corresponding to the first form attribute, a second independent form attribute corresponding to the second form attribute, first attribute information corresponding to a form attribute to be transitioned between the first form attribute information and the second form attribute information, and second attribute information corresponding to a form attribute to be transitioned between the second form attribute and the first form attribute (such as color, font size);

[0108] Generate transition attribute information corresponding to the attribute to be transitioned based on the first attribute information and the second attribute information corresponding to the attribute to be transitioned;

[0109] Based on the attribute information corresponding to the first independent form attribute, the attribute information corresponding to the second independent form attribute, and the transition attribute information corresponding to the to-be-transitioned form attribute, the fused form attribute information is generated.

[0110] Optionally, the first independent formal attribute is a formal attribute not included in the second formal attribute; the second independent formal attribute is a formal attribute not included in the first formal attribute. The formal attributes to be transitioned include the first formal attribute and the common formal attributes of the second formal attribute, the first attribute information is the attribute information corresponding to the common formal attribute in the first formal attribute, and the second attribute information is the attribute information corresponding to the common formal attribute in the second formal attribute. Furthermore, the formal attributes to be transitioned may further include the target common formal attributes that affect the content fusion operation in the common formal attributes of the first formal attribute and the second formal attribute. For example, if the content fusion operation is a left-right splicing operation of report content, the target common formal attribute may be the common formal attribute corresponding to the splicing point of the two reports, such as the font size at the splicing point, the table color at the splicing point, etc.

[0111] It can be seen that this optional embodiment can also consider the different formal attributes of different financial tables and the transition attributes of different financial tables when integrating the formal attributes of financial statements, which is beneficial to improving the fusion reliability of the formal attributes of the reports and reducing the readability of the financial tables due to conflicts in the formal attributes of the tables or unnatural transitions.

[0112] In yet another optional embodiment, the above-mentioned generating the transition attribute information corresponding to the to-be-transitioned form attribute based on the first attribute information and the second attribute information corresponding to the to-be-transitioned form attribute may include:

[0113] Calculating the deviation of the attribute information between the first attribute information and the second attribute information, and if the deviation of the attribute information indicates that both belong to the preset attribute information category, determining the first attribute information or the second attribute information or the average attribute information of the two as the transition attribute information corresponding to the attribute to be transitioned;

[0114] If the attribute information deviation indicates that the two do not belong to the preset attribute information category, generating a first adjustment parameter of the first attribute information and a second adjustment parameter of the second attribute information based on the attribute information deviation;

[0115] Performing an adjustment operation on the first attribute information based on the first adjustment parameter to obtain first adjusted attribute information, and performing an adjustment operation on the second attribute information based on the second adjustment parameter to obtain second adjusted attribute information; wherein the first adjusted attribute information and the second adjusted attribute information belong to the category of preset attribute information;

[0116] The first adjusted attribute information or the second adjusted attribute information or the average adjusted attribute information of the two is determined as transition attribute information corresponding to the attribute of the to-be-transitioned form.

[0117] In this optional embodiment, the transition attribute information is used to achieve a smooth transition between the first attribute information and the second attribute information.

[0118] For example, if the attribute to be transitioned is a color attribute, and the color corresponding to the first attribute information and the color corresponding to the second attribute information belong to the same color system, then both belong to the category of preset attribute information; if the color corresponding to the first attribute information and the color corresponding to the second attribute information do not belong to the same color system, which will result in inconsistent colors at the junction of the two tables, then both do not belong to the category of preset attribute information.

[0119] It can be seen that this optional embodiment can also intelligently generate transition attribute information based on the correspondence between the deviation between the attribute information and the preset attribute information category, thereby realizing the intelligent determination of the transition attribute information, which is beneficial to improving the accuracy and reliability of the generated transition attribute information, and further beneficial to improving the accuracy and reliability of the fused attribute information.

[0120] In yet another optional embodiment, the method may further include the following operations:

[0121] After the consolidated financial statements are sent to at least one authorized person, monitor the adjustments made to the consolidated financial statements by an authorized person;

[0122] Determine the type of object that a certain authorized person wants to adjust according to the adjustment operation, and the object type includes a report content type and / or a report form type; wherein the report content type is used to indicate that the object that a certain authorized person wants to adjust is the target content of the comprehensive financial statement, and the report form type is used to indicate that the object that a certain authorized person wants to adjust is the form attribute of the comprehensive financial statement;

[0123] When the object type is a report content type and a certain authorized person has the adjustment authority for the target content, the target information set when the certain authorized person triggers the adjustment operation is collected. The information set includes the triggering location when the certain authorized person triggers the adjustment operation, the triggering time when the certain authorized person triggers the adjustment operation, the personnel information of the accompanying person when the certain authorized person triggers the adjustment operation, the issuance of the adjustment instruction corresponding to the target content when the certain authorized person triggers the adjustment operation, the facial expression information when the certain authorized person triggers the adjustment operation, the operation speed information when the certain authorized person triggers the adjustment operation, the historical operation speed information when the certain authorized person triggers the same adjustment operation in the past, and the interaction information between the certain authorized person and the accompanying person when the adjustment operation is triggered;

[0124] Determine, based on the target information set, whether the negative impact of an adjustment operation triggered by a certain authorized person on the consolidated financial statements is greater than or equal to the preset threshold;

[0125] When the degree of negative impact is greater than or equal to the preset degree threshold, a locking operation is performed on the operation authority of the comprehensive financial statements, and a determination is made as to whether there is any related report content in the comprehensive financial statements that has a conflict of interest with the target content. If there is any related report content, a content hiding operation is performed on the related report content after the comprehensive financial statements are locked; the content hiding operation includes a direct hiding operation of not displaying the related report content or an indirect hiding operation of converting the related report content into preset characters.

[0126] It can be seen that after sending the generated comprehensive financial statements to the authorized personnel, this optional embodiment can also realize the supervision of the financial statement adjustment operations for the authorized personnel, and comprehensively judge the negative impact of the authorized personnel's adjustment of the financial statements based on the multi-dimensional information when the authorized personnel triggers the financial statement adjustment operation, thereby improving the accuracy and comprehensiveness of the control over the authorized personnel's financial statement adjustment behavior, which is beneficial to improving the security of the financial statements; in addition, when the authorized personnel adjust the financial statements, they can further make an intelligent judgment on the content of the associated statements with a conflict of interest, and then perform a content hiding operation on the content of the associated statements with a conflict of interest based on the judgment result, thereby realizing the linkage control of the content of the associated statements when there is a risk in adjusting the financial statements, which can further improve the security of the financial statements.

[0127] In yet another optional embodiment, the method may further include the following operations:

[0128] After generating the consolidated financial statements, determine whether the consolidated financial statements need to be displayed externally;

[0129] If the consolidated financial statements need to be displayed externally, determine the corresponding display objects of the consolidated financial statements;

[0130] Based on the display object, determine the display object's financial statement reading habits and the display object's high-profile report content;

[0131] According to the financial statement reading habits and high-profile report contents, matching optimization operations are performed on the comprehensive financial statements to generate target financial statements for display-oriented objects.

[0132] It can be seen that after the comprehensive financial statements are generated, if it is determined that the comprehensive financial statements need to be displayed externally, this optional embodiment can perform adaptive optimization operations on the comprehensive financial statements based on the financial statement reading habits of the display-oriented objects and the high-attention report content of the comprehensive financial statements. This is conducive to expanding the application scenarios of the intelligent financial statement issuance method, and can also improve the matching degree between the optimized financial statements and the reference requirements of the display-oriented objects, which is conducive to improving the display-oriented objects' reference convenience and reference efficiency for the optimized financial statements.

[0133] Embodiment 2

[0134] See also Figure 2 , Figure 2 This is a schematic diagram of a structure of an intelligent financial statement issuance control device based on artificial intelligence provided by an embodiment of the present invention. Figure 2 The described device can be integrated in the local server of the enterprise, or in the cloud server corresponding to the enterprise. Furthermore, if integrated in the cloud server, the cloud server can be a server for one enterprise or a server for multiple enterprises, which is not limited in the embodiments of the present invention. Figure 2 As shown, the device comprises:

[0135] The demand judgment module 201 is used to collect the current multi-dimensional enterprise information of the target controlled enterprise, and judge whether the target controlled enterprise currently meets the pre-set financial statement issuance conditions based on the multi-dimensional enterprise information;

[0136] The information screening module 202 is used to screen target multi-dimensional information associated with the issuance of financial statements from the multi-dimensional enterprise information when the demand judgment module determines that the target controlled enterprise currently meets the conditions for issuing financial statements;

[0137] The issuance control module 203 is used to input the target multi-dimensional information into the financial statement issuance analysis model that has been pre-trained to convergence, and obtain the current financial statement issuance requirements of the target controlled enterprise;

[0138] The issuance control module 203 is further used to divide the current financial statement issuance demand into a first financial statement issuance demand and a second financial statement issuance demand based on the historical issuance information corresponding to several financial statements that have been issued in the past, the first financial statement issuance demand including the financial statement issuance demand whose matching degree with the historical issuance information is greater than or equal to the matching degree threshold, and the second financial statement issuance demand including the financial statement issuance demand whose matching degree with the historical issuance information is less than the matching degree threshold; and, according to the first financial statement issuance demand and the historical issuance information, generate a first financial statement issuance control parameter, and generate a first financial statement based on the first financial statement issuance control parameter; and, according to the second financial statement issuance demand and the financial statement issuance control model pre-trained to convergence, generate a second financial statement issuance control parameter, and generate a second financial statement based on the second financial statement issuance control parameter;

[0139] A fusion control module 204, configured to perform a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement;

[0140] The report providing module 205 is used to send the comprehensive financial report to at least one authorized person.

[0141] It can be seen that through the implementation Figure 2 The described device can realize intelligent judgment on whether the target controlled enterprise has the demand for issuing financial statements according to the multi-dimensional information of the target controlled enterprise, without waiting for the manual application of the relevant personnel, which is conducive to improving the timeliness and convenience of issuing financial statements; in addition, it can also automatically analyze the current financial statement issuance needs of the enterprise according to the multi-dimensional information of the enterprise that has a correlation with the issuance of financial statements, and input it into the financial statement issuance analysis model, so as to improve the analysis efficiency and accuracy of the financial statement issuance needs; in addition, after analyzing the current financial statement issuance needs of the enterprise, it can also classify the financial statement issuance needs based on the historical statement issuance information, and then generate corresponding statement issuance control parameters according to the classification results, and then generate corresponding financial statements based on the statement issuance control parameters, and then merge multiple financial statements, which is not only conducive to improving the efficiency and convenience of financial statement generation, but also conducive to improving the matching degree between the generated financial statements and actual needs.

[0142] In an optional embodiment, the specific manner in which the fusion control module 204 performs the fusion operation on the first financial statement and the second financial statement to obtain the comprehensive financial statement includes:

[0143] Extracting first key report content in the first financial report and second key report content in the second financial report, performing a content fusion operation on the first key report content and the second key report content, and obtaining fused report content;

[0144] Extracting a first formal attribute corresponding to the first financial statement and a second formal attribute corresponding to the second financial statement, performing a formal attribute fusion operation on the first formal attribute and the second formal attribute to obtain a fused formal attribute;

[0145] According to the fusion form attributes and pre-determined visualization requirements, the fusion report content is visualized to obtain a visualized comprehensive financial report.

[0146] It can be seen that this optional embodiment can integrate the report content and report form attributes separately when integrating two major financial statements, which is beneficial to improving the integration efficiency and integration reliability of the financial statements.

[0147] In this optional embodiment, further optionally, the fusion control module 204 performs a form attribute fusion operation on the first form attribute and the second form attribute, and a specific method of obtaining the fused form attribute includes:

[0148] According to the first formal attribute and the second formal attribute, respectively determining from the first formal attribute and the second formal attribute a first independent formal attribute corresponding to the first formal attribute, a second independent formal attribute corresponding to the second formal attribute, first attribute information corresponding to a formal attribute to be transitioned between the first formal attribute information and the second formal attribute information, and second attribute information corresponding to a formal attribute to be transitioned between the second formal attribute and the first formal attribute;

[0149] Generate transition attribute information corresponding to the attribute to be transitioned based on the first attribute information and the second attribute information corresponding to the attribute to be transitioned;

[0150] Based on the attribute information corresponding to the first independent form attribute, the attribute information corresponding to the second independent form attribute, and the transition attribute information corresponding to the to-be-transitioned form attribute, the fused form attribute information is generated.

[0151] Optionally, the first independent formal attribute is a formal attribute not included in the second formal attribute; the second independent formal attribute is a formal attribute not included in the first formal attribute.

[0152] The formal attributes to be transitioned include the first formal attribute and the common formal attributes of the second formal attribute. The first attribute information is the attribute information corresponding to the common formal attribute in the first formal attribute, and the second attribute information is the attribute information corresponding to the common formal attribute in the second formal attribute.

[0153] It can be seen that this optional embodiment can also consider the different formal attributes of different financial tables and the transition attributes of different financial tables when integrating the formal attributes of financial statements, which is beneficial to improving the fusion reliability of the formal attributes of the reports and reducing the readability of the financial tables due to conflicts in the formal attributes of the tables or unnatural transitions.

[0154] In this optional embodiment, further optionally, the fusion control module 204 generates the transition attribute information corresponding to the to-be-transitioned form attribute based on the first attribute information and the second attribute information corresponding to the to-be-transitioned form attribute in a specific manner including:

[0155] Calculating the deviation of the attribute information between the first attribute information and the second attribute information, and if the deviation of the attribute information indicates that both belong to the preset attribute information category, determining the first attribute information or the second attribute information or the average attribute information of the two as the transition attribute information corresponding to the attribute to be transitioned;

[0156] If the attribute information deviation indicates that the two do not belong to the preset attribute information category, generating a first adjustment parameter of the first attribute information and a second adjustment parameter of the second attribute information based on the attribute information deviation;

[0157] Performing an adjustment operation on the first attribute information based on the first adjustment parameter to obtain first adjusted attribute information, and performing an adjustment operation on the second attribute information based on the second adjustment parameter to obtain second adjusted attribute information; wherein the first adjusted attribute information and the second adjusted attribute information belong to the category of preset attribute information;

[0158] The first adjusted attribute information or the second adjusted attribute information or the average adjusted attribute information of the two is determined as transition attribute information corresponding to the attribute of the to-be-transitioned form.

[0159] It can be seen that this optional embodiment can also intelligently generate transition attribute information based on the correspondence between the deviation between the attribute information and the preset attribute information category, thereby realizing the intelligent determination of the transition attribute information, which is beneficial to improving the accuracy and reliability of the generated transition attribute information, and further beneficial to improving the accuracy and reliability of the fused attribute information.

[0160] In yet another optional embodiment, Figure 3 As shown, the device also includes a report control module 206. The report control module 206 is used to:

[0161] After the consolidated financial statements are sent to at least one authorized person, monitor the adjustments made to the consolidated financial statements by an authorized person;

[0162] Determine the type of object that a certain authorized person wants to adjust according to the adjustment operation, and the object type includes a report content type and / or a report form type; wherein the report content type is used to indicate that the object that a certain authorized person wants to adjust is the target content of the comprehensive financial statement, and the report form type is used to indicate that the object that a certain authorized person wants to adjust is the form attribute of the comprehensive financial statement;

[0163] When the object type is a report content type and a certain authorized person has the adjustment authority for the target content, the target information set when the certain authorized person triggers the adjustment operation is collected. The information set includes the triggering location when the certain authorized person triggers the adjustment operation, the triggering time when the certain authorized person triggers the adjustment operation, the personnel information of the accompanying person when the certain authorized person triggers the adjustment operation, the issuance of the adjustment instruction corresponding to the target content when the certain authorized person triggers the adjustment operation, the facial expression information when the certain authorized person triggers the adjustment operation, the operation speed information when the certain authorized person triggers the adjustment operation, the historical operation speed information when the certain authorized person triggers the same adjustment operation in the past, and the interaction information between the certain authorized person and the accompanying person when the adjustment operation is triggered;

[0164] Determine, based on the target information set, whether the negative impact of an adjustment operation triggered by a certain authorized person on the consolidated financial statements is greater than or equal to the preset threshold;

[0165] When the negative impact is greater than or equal to the preset threshold, the operation authority of the comprehensive financial statement is locked, and it is determined whether there is any associated report content in the comprehensive financial statement that has a conflict of interest with the target content. If there is any associated report content, after locking the comprehensive financial statement, a content hiding operation is performed on the associated report content; the content hiding operation includes a direct hiding operation of not displaying the associated report content or an indirect hiding operation of converting the associated report content into preset characters. Optionally, the associated report content that has a conflict of interest with the target content can be used to indicate that the generation of the associated report content depends on the target content, or it can also be used to indicate that the target content and the associated report content work together as a trigger basis for triggering a certain abnormal phenomenon.

[0166] It can be seen that after sending the generated comprehensive financial statements to the authorized personnel, this optional embodiment can also realize the supervision of the financial statement adjustment operations for the authorized personnel, and comprehensively judge the negative impact of the authorized personnel's adjustment of the financial statements based on the multi-dimensional information when the authorized personnel triggers the financial statement adjustment operation, thereby improving the accuracy and comprehensiveness of the control over the authorized personnel's financial statement adjustment behavior, which is beneficial to improving the security of the financial statements; in addition, when the authorized personnel adjust the financial statements, they can further make an intelligent judgment on the content of the associated statements with a conflict of interest, and then perform a content hiding operation on the content of the associated statements with a conflict of interest based on the judgment result, thereby realizing the linkage control of the content of the associated statements when there is a risk in adjusting the financial statements, which can further improve the security of the financial statements.

[0167] In yet another optional embodiment, Figure 3 As shown, the device also includes a report optimization module 207. The report optimization module 207 is used to:

[0168] After generating the consolidated financial statements, determine whether the consolidated financial statements need to be displayed externally;

[0169] If the consolidated financial statements need to be displayed externally, determine the corresponding display objects of the consolidated financial statements;

[0170] Based on the display object, determine the display object's financial statement reading habits and the display object's high-profile report content (such as the focus on the results content or the focus on the process content or the focus on the relevance content, etc.);

[0171] According to the financial statement reading habits and high-profile report contents, matching optimization operations are performed on the comprehensive financial statements to generate target financial statements for display-oriented objects.

[0172] It can be seen that after the comprehensive financial statements are generated, if it is determined that the comprehensive financial statements need to be displayed externally, the comprehensive financial statements can be adaptively optimized based on the financial statement reading habits and high-profile report content of the display-oriented objects of the comprehensive financial statements. This is conducive to expanding the application scenarios of the intelligent financial statement issuance method, and can also improve the matching degree between the optimized financial statements and the reference requirements of the display-oriented objects, thereby facilitating the display-oriented objects to consult the optimized financial statements. The convenience and efficiency of the review.

[0173] Embodiment 3

[0174] See also Figure 4 , Figure 4 This is a structural diagram of another artificial intelligence-based financial statement intelligent issuance control device provided by an embodiment of the present invention. Figure 4 The described device can be integrated in the local server of the enterprise, or in the cloud server corresponding to the enterprise. Furthermore, if integrated in the cloud server, the cloud server can be a server for one enterprise or a server for multiple enterprises, which is not limited in the embodiments of the present invention. Figure 4 As shown, the device comprises:

[0175] A memory 301 storing executable program codes;

[0176] a processor 302 coupled to a memory;

[0177] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in any of the artificial intelligence-based financial statement intelligent issuance and control methods described in Example 1.

[0178] Embodiment 4

[0179] An embodiment of the present invention discloses a computer storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute any step of the method for intelligent issuance and control of financial statements based on artificial intelligence described in Embodiment 1.

[0180] Embodiment 5

[0181] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute any step of the artificial intelligence-based financial statement intelligent issuance and control method described in Example 1.

[0182] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0183] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0184] Finally, it should be noted that the method and device for intelligent issuance and control of financial statements based on artificial intelligence disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions recorded in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for intelligently issuing and controlling financial statements based on artificial intelligence, characterized in that: The method comprises: Collect the current multi-dimensional enterprise information of the target controlled enterprise, and determine whether the target controlled enterprise currently meets the pre-set financial statement issuance conditions based on the multi-dimensional enterprise information; When it is determined that the target controlled enterprise currently meets the financial statement issuance conditions, target multi-dimensional information associated with the issuance of financial statements is screened from the multi-dimensional enterprise information, and the target multi-dimensional information is input into a financial statement issuance analysis model that has been pre-trained to convergence, to obtain the current financial statement issuance requirements of the target controlled enterprise; Based on historical issuance information corresponding to several financial statements that have been issued in the past, the current financial statement issuance requirement is divided into a first financial statement issuance requirement and a second financial statement issuance requirement, wherein the first financial statement issuance requirement includes financial statement issuance requirements whose matching degree with the historical issuance information is greater than or equal to a matching degree threshold, and the second financial statement issuance requirement includes financial statement issuance requirements whose matching degree with the historical issuance information is less than the matching degree threshold; Generate a first financial statement issuance control parameter according to the first financial statement issuance requirement and the historical issuance information, and generate a first financial statement based on the first financial statement issuance control parameter; Generate a second financial statement issuance control parameter according to the second financial statement issuance requirement and a financial statement issuance control model that has been pre-trained to convergence, and generate a second financial statement based on the second financial statement issuance control parameter; A fusion operation is performed on the first financial statement and the second financial statement to obtain a comprehensive financial statement, and the comprehensive financial statement is sent to at least one authorized person.

2. The method for intelligent issuance and control of financial statements based on artificial intelligence according to claim 1 is characterized in that: The performing a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement includes: Extracting first key report content in the first financial report and second key report content in the second financial report, performing a content fusion operation on the first key report content and the second key report content to obtain fused report content; Extracting a first formal attribute corresponding to the first financial statement and a second formal attribute corresponding to the second financial statement, and performing a formal attribute fusion operation on the first formal attribute and the second formal attribute to obtain a fused formal attribute; According to the fusion form attributes and the pre-determined visualization requirements, the fusion report content is visualized to obtain a visualized comprehensive financial report.

3. The method for intelligently issuing and controlling financial statements based on artificial intelligence according to claim 2 is characterized in that: The performing a formal attribute fusion operation on the first formal attribute and the second formal attribute to obtain a fused formal attribute includes: According to the first formal attribute and the second formal attribute, determining from the first formal attribute and the second formal attribute respectively a first independent formal attribute corresponding to the first formal attribute, a second independent formal attribute corresponding to the second formal attribute, first attribute information corresponding to a formal attribute to be transitioned between the first formal attribute information and the second formal attribute information, and second attribute information corresponding to a formal attribute to be transitioned between the second formal attribute information and the first formal attribute; generating transition attribute information corresponding to the attribute in the form to be transitioned based on the first attribute information and the second attribute information corresponding to the attribute in the form to be transitioned; Based on the attribute information corresponding to the first independent form attribute, the attribute information corresponding to the second independent form attribute, and the transition attribute information corresponding to the to-be-transitioned form attribute, fused form attribute information is generated.

4. The method for intelligently issuing and controlling financial statements based on artificial intelligence according to claim 3 is characterized in that: The first independent formal attribute is a formal attribute not included in the second formal attribute; the second independent formal attribute is a formal attribute not included in the first formal attribute; The formal attribute to be transitioned includes the first formal attribute and the common formal attribute of the second formal attribute, the first attribute information is the attribute information corresponding to the common formal attribute in the first formal attribute, and the second attribute information is the attribute information corresponding to the common formal attribute in the second formal attribute; Among them, the multi-dimensional enterprise information includes all department levels in the target controlled enterprise, department information corresponding to all departments in each department level, personnel information corresponding to all personnel in each department, and current financial planning information of each department; the current financial planning information of each department includes the current established financial planning information of each department and the current emergency financial planning information of each department.

5. The method for intelligently issuing and controlling financial statements based on artificial intelligence according to claim 4 is characterized in that: The step of generating transition attribute information corresponding to the attribute to be transitioned based on the first attribute information and the second attribute information corresponding to the attribute to be transitioned comprises: Calculating the attribute information deviation between the first attribute information and the second attribute information, and if the attribute information deviation indicates that both belong to the preset attribute information category, determining the first attribute information or the second attribute information or the average attribute information of the two as the transition attribute information corresponding to the attribute to be transitioned; If the attribute information deviation indicates that the two do not belong to the preset attribute information category, generating a first adjustment parameter of the first attribute information and a second adjustment parameter of the second attribute information based on the attribute information deviation; performing an adjustment operation on the first attribute information based on the first adjustment parameter to obtain first adjusted attribute information, and performing an adjustment operation on the second attribute information based on the second adjustment parameter to obtain second adjusted attribute information; wherein the first adjusted attribute information and the second adjusted attribute information belong to the preset attribute information category; The first adjusted attribute information or the second adjusted attribute information or average adjusted attribute information of the two is determined as transition attribute information corresponding to the attribute to be transitioned.

6. The method for intelligently issuing and controlling financial statements based on artificial intelligence according to any one of claims 1 to 5, characterized in that: After sending the comprehensive financial statements to at least one authorized person, the method further includes: After sending the consolidated financial statements to at least one of the authorized persons, monitoring the adjustment operations of an authorized person on the consolidated financial statements; Determining the type of object that the authorized person wants to adjust according to the adjustment operation, the object type includes a report content type and / or a report form type; wherein the report content type is used to indicate that the object that the authorized person wants to adjust is the target content of the comprehensive financial statement, and the report form type is used to indicate that the object that the authorized person wants to adjust is the form attribute of the comprehensive financial statement; When the object type is the report content type and the certain authorized person has the adjustment authority for the target content, a target information set is collected when the certain authorized person triggers the adjustment operation, and the information set includes the triggering location when the certain authorized person triggers the adjustment operation, the triggering time when the certain authorized person triggers the adjustment operation, the personnel information of the accompanying person when the certain authorized person triggers the adjustment operation, the issuance of the adjustment instruction corresponding to the target content when the certain authorized person triggers the adjustment operation, the facial expression information when the certain authorized person triggers the adjustment operation, the operation speed information when the certain authorized person triggers the adjustment operation, the historical operation speed information when the certain authorized person triggers the same adjustment operation in the past, and the interaction information between the certain authorized person and the accompanying person when the certain authorized person triggers the adjustment operation; Determining, based on the target information set, whether the negative impact of the adjustment operation triggered by the certain authorized person on the comprehensive financial statements is greater than or equal to a preset degree threshold; When the degree of negative impact is greater than or equal to the preset degree threshold, a locking operation is performed on the operation authority of the comprehensive financial statement, and it is determined whether there is any associated report content in the comprehensive financial statement that has a vested interest in the target content. If there is such associated report content, a content hiding operation is performed on the associated report content after locking the comprehensive financial statement; the content hiding operation includes a direct hiding operation of not displaying the associated report content or an indirect hiding operation of converting the associated report content into preset characters.

7. The method for intelligently issuing and controlling financial statements based on artificial intelligence according to claim 6 is characterized in that: After the fusion operation is performed on the first financial statement and the second financial statement to obtain a comprehensive financial statement, the method further includes: After generating the comprehensive financial statements, determining whether the comprehensive financial statements need to be displayed externally; If the comprehensive financial statements need to be displayed externally, determine the display target of the comprehensive financial statements; Based on the display-oriented object, determining the financial statement reading habits of the display-oriented object and the highly concerned statement contents of the display-oriented object; According to the financial statement reading habits and the high-attention statement contents, matching optimization operations are performed on the comprehensive financial statements to generate target financial statements for the display-oriented object.

8. An intelligent financial statement issuance control device based on artificial intelligence, characterized in that: The device comprises: A demand judgment module is used to collect the current multi-dimensional enterprise information of the target controlled enterprise, and judge whether the target controlled enterprise currently meets the pre-set financial statement issuance conditions based on the multi-dimensional enterprise information; An information screening module, configured to screen target multi-dimensional information associated with the issuance of financial statements from the multi-dimensional enterprise information when the demand judgment module determines that the target controlled enterprise currently meets the conditions for issuing financial statements; The issuance control module is used to input the target multi-dimensional information into the financial statement issuance analysis model that has been pre-trained to convergence, and obtain the current financial statement issuance requirements of the target controlled enterprise; The issuance control module is further used to divide the current financial statement issuance demand into a first financial statement issuance demand and a second financial statement issuance demand based on historical issuance information corresponding to several financial statements that have been issued in the past, wherein the first financial statement issuance demand includes financial statement issuance demands whose matching degree with the historical issuance information is greater than or equal to a matching degree threshold, and the second financial statement issuance demand includes financial statement issuance demands whose matching degree with the historical issuance information is less than the matching degree threshold; and, based on the first financial statement issuance demand and the historical issuance information, generate a first financial statement issuance control parameter, and generate a first financial statement based on the first financial statement issuance control parameter; and, based on the second financial statement issuance demand and a financial statement issuance control model pre-trained to convergence, generate a second financial statement issuance control parameter, and generate a second financial statement based on the second financial statement issuance control parameter; A fusion control module, used for performing a fusion operation on the first financial statement and the second financial statement to obtain a comprehensive financial statement; The report providing module is used to send the comprehensive financial report to at least one authorized person.

9. An intelligent financial statement issuance control device based on artificial intelligence, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent issuance and control method of financial statements based on artificial intelligence as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, which, when called, are used to execute the artificial intelligence-based intelligent issuance and control method of financial statements as described in any one of claims 1 to 7.

Images