Conformance report generation method and device, equipment and storage medium

Abstract

The invention provides a compliance report generation method and device, equipment and a storage medium, and relates to the technical field of data processing, in particular to the technical field of artificial intelligence. According to the specific implementation scheme, in response to a processing template selection operation of a compliance task, a first processing agent of each compliance check item defined by a selected target template is loaded, and a processing logic of the compliance check item is integrated in the first processing agent of each compliance check item; for each compliance check item, inputting to-be-analyzed data of the compliance check item into a first processing agent of the compliance check item to obtain a processing result output after the first processing agent analyzes the to-be-analyzed data; and generating a compliance report based on the processing result of each compliance check item. By applying the scheme provided by the embodiment of the invention, the compliance report of the compliance task can be generated.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to the field of artificial intelligence technology. Background Art

[0002] With the continuous improvement of market regulations and the gradual updating of various laws and regulations, enterprises need to regularly carry out various compliance tasks such as data security assessments, risk detection and compliance audits to ensure the compliance of their own operations and avoid various potential risks.

[0003] Currently, when enterprises handle compliance tasks, they generally need internal business experts and external compliance experts to collaborate with each other to analyze whether the enterprise meets the compliance requirements of the compliance tasks and generate compliance reports. Summary of the invention

[0004] The present disclosure provides a compliance report generation method, apparatus, device and storage medium.

[0005] According to a first aspect of the present disclosure, a compliance report generation method is provided, comprising:

[0006] In response to a processing template selection operation of a compliance task, a first processing agent of each compliance check item defined by the selected target template is loaded, wherein the first processing agent of each compliance check item integrates the processing logic of the compliance check item;

[0007] For each compliance check item, input the data to be analyzed of the compliance check item into the first processing agent of the compliance check item, and obtain the processing result output by the first processing agent after analyzing the data to be analyzed;

[0008] Generate a compliance report based on the processing results of each compliance check item.

[0009] According to a second aspect of the present disclosure, there is provided a compliance report generating device, comprising:

[0010] A first agent loading module is used to load the first processing agent of each compliance check item defined by the selected target template in response to the processing template selection operation of the compliance task, wherein the first processing agent of each compliance check item integrates the processing logic of the compliance check item;

[0011] A processing result obtaining module is used to input the data to be analyzed of the compliance check item into the first processing agent of the compliance check item for each compliance check item, and obtain the processing result output by the first processing agent after analyzing the data to be analyzed;

[0012] The report generation module is used to generate a compliance report based on the processing results of each compliance check item.

[0013] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0017] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect.

[0018] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method described in the first aspect when executed by a processor.

[0019] As can be seen from the above, when the scheme provided by the embodiment of the present disclosure is applied to generate a compliance report for a compliance task, the electronic device can load the first processing agent of each compliance check item defined by the selected target template in response to the processing template selection operation of the compliance task. Then, for each compliance check item, the data to be analyzed of the compliance check item is input into the first processing agent of the compliance check item, and the processing result output by the first processing agent after analyzing the data to be analyzed is obtained. Finally, based on the processing results of each compliance check item, a compliance report is successfully generated.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 A flowchart of a compliance report generation method provided in an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of an intelligent agent provided by an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram of a first processing template provided in an embodiment of the present disclosure;

[0025] Figure 4A schematic diagram of a node result correction interface provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of a second processing template provided in an embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of an intelligent agent processing flow provided by an embodiment of the present disclosure;

[0028] Figure 7 A schematic diagram of the structure of a compliance report generating device provided by an embodiment of the present disclosure;

[0029] Figure 8 The present invention is a block diagram of an electronic device for implementing the compliance report generation method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0031] The following is a detailed description of the compliance report generation solution provided in the embodiment of the present disclosure.

[0032] See also Figure 1 , which is a flow chart of a first compliance report generation method provided in an embodiment of the present disclosure, the method includes the following steps S101-S103.

[0033] Step S101: In response to a processing template selection operation of a compliance task, a first processing agent of each compliance check item defined by the selected target template is loaded.

[0034] First, the compliance tasks are introduced.

[0035] In the solution provided by the embodiments of the present disclosure, the compliance task may refer to any type of task used to evaluate or detect the compliance status of an enterprise, such as data security assessment, compliance audit, compliance evaluation, etc.

[0036] For example, it may include security assessment tasks, such as Personal Information Protection Impact Assessment (PIA) tasks, data security risk assessment tasks, and cross-border data assessment tasks.

[0037] It may also include compliance audit tasks, such as Personal Information Protection Law audit tasks, Information Technology (IT) audit tasks, and data audit tasks.

[0038] It can also include compliance assessment tasks, such as Data Management Capability Maturity Model (DCMM) assessment tasks, communication network security protection classification and filing assessment tasks, cryptographic application security assessment tasks, cryptographic application transformation assessment tasks, network security level protection assessment tasks, etc.

[0039] A compliance task may include multiple compliance check items. By determining whether an enterprise meets each compliance check item, it is possible to determine whether the enterprise meets the compliance requirements. Compliance check items may also be referred to as check items, assessment items, etc.

[0040] The above processing template is a predefined compliance task processing template. Each compliance task corresponds to a processing template, which can be called a compliance template, an intelligent template, etc. The processing template defines various compliance check items required by the compliance task and a first processing agent for processing each compliance check item.

[0041] The first processing agent of each compliance check item integrates the processing logic of the compliance check item, and the above processing logic can also be called a workflow, work process, etc. That is, in the solution provided by the embodiment of the present disclosure, the processing logic of the compliance check item is called the first processing agent. The first processing agent integrates a pre-trained large model, such as a large language model.

[0042] The first processing agent is introduced below.

[0043] In one embodiment of the present disclosure, the first processing agent may include: a plurality of processing nodes for performing one or more processing on data and an execution order between these processing nodes. The processing nodes and the execution order between these processing nodes actually represent the processing logic of the compliance check items.

[0044] It should be noted that the specific type of the above-mentioned processing node or the implemented function can be flexibly set according to the needs of the actual scenario, and the embodiments of the present disclosure are not limited to this.

[0045] For an example introduction to the processing node, please refer to the subsequent embodiments, which will not be described in detail here.

[0046] Combine the following Figure 2 , an intuitive introduction to the first processing agent of the compliance check item.

[0047] Figure 2In the example, the first processing agent includes 7 processing nodes, namely, processing node A to processing node G. The execution order between the processing nodes is: A→(B, C, D)→(E, F)→G, where the nodes in the brackets represent nodes that are executed in parallel. Specifically, processing node A is executed first to obtain the output of processing node A; then, the output of processing node A is used as the input of processing node BD to obtain the output of processing node BD; the outputs of processing nodes B and C are used as the input of processing node E, and the output of processing node D is used as the input of processing node F to obtain the outputs of processing nodes E and F; finally, the outputs of processing nodes E and F are used as the input of processing node G to obtain the output of processing node G.

[0048] Among them, processing node A can be a data input node, used to input the data to be analyzed for the compliance check item; processing node G can be a data output node, and the output of processing node G is the processing result of the compliance check item; processing node B-processing node F can be various types of nodes used to perform specific data processing operations, including large model nodes.

[0049] It can be seen that the processing nodes and the execution order of the processing nodes can conveniently and efficiently represent the processing logic of the compliance check items, and then the first processing agent can be efficiently constructed based on the processing nodes.

[0050] Of course, various other forms may also be used to construct the first processing agent that integrates the processing logic of the compliance check items, and the embodiments of the present disclosure are not limited to this.

[0051] In summary, each compliance task corresponds to a processing template, and each processing template defines a plurality of first processing agents for processing a plurality of compliance check items in the processing template, such as Figure 3 As shown, Figure 3 The dashed box in the middle represents the first processing agent, and the circle in the dashed box represents the processing node. Figure 3 A processing template T1 of a certain compliance task is shown, in which compliance check items 1 to compliance check items N included in the processing template are defined, and first processing agents I1 to first processing agents IN for compliance check items 1 to compliance check items N are defined respectively, and each first processing agent includes several processing nodes.

[0052] The staff in the enterprise can trigger the above processing template selection operation according to the actual compliance tasks to be processed by the enterprise, so as to select a processing template that matches the above compliance tasks to be processed, that is, a target template, from various predefined processing templates.

[0053] In this way, the electronic device can load the first processing agent of each compliance check item defined by the target template in response to the above-mentioned processing template selection operation.

[0054] Step S102: For each compliance check item, the data to be analyzed of the compliance check item is input into the first processing agent of the compliance check item, and a processing result output by the first processing agent after analyzing the data to be analyzed is obtained.

[0055] According to the above description, the first processing agent is used to analyze and process the compliance check items. Therefore, by inputting the data to be analyzed of the compliance check items into the first processing agent, the processing result output by the first processing agent after analyzing the data to be analyzed can be obtained. The above processing result is used to indicate whether the compliance check items have passed the inspection.

[0056] In one case, when the first processing agent includes multiple processing nodes and the multiple processing nodes have a set execution order, the following steps can be used to obtain the processing results obtained after analyzing the data to be analyzed for the compliance check items.

[0057] Step A: input the data to be analyzed of the compliance check item into the first processing node in the first processing agent of the compliance check item, and obtain the intermediate processing result output by the first processing node.

[0058] The first processing node is a data input node in the processing nodes included in the first processing agent, that is, the data to be analyzed of the compliance check item is input into the data input node in the first processing agent.

[0059] The data input node can perform set preprocessing on the data to be analyzed to obtain the above-mentioned intermediate processing results.

[0060] Step B: Input the intermediate processing result to an adjacent processing node whose execution order is after the target processing node, and obtain a new intermediate processing result output by the adjacent processing node.

[0061] The target processing node is initially the first processing node.

[0062] That is, firstly, the intermediate processing result of the first processing node is input into the adjacent processing node whose execution order is after the first processing node, so as to obtain a new intermediate processing result output by the adjacent processing node.

[0063] Step C: If the adjacent processing node is the second processing node, the new intermediate processing result is determined as the processing result of the compliance check item; otherwise, the target processing node is updated to the adjacent processing node, and the process returns to step B.

[0064] The second processing node is: a data output node among the processing nodes included in the first processing agent.

[0065] That is, if the adjacent processing node is a data output node, the output result of the data output node is determined as the processing result of the compliance check item; otherwise, the intermediate processing result of the adjacent processing node continues to be input into the next processing node until the output result of the data output node is obtained.

[0066] In this way, the above-mentioned processing nodes can be executed in sequence in an event-driven manner, realizing the full process asynchronization. Among them, the working state of each processing node in the first processing agent can be managed by a state machine, which will not be repeated here.

[0067] It can be seen that by orderly executing various processing nodes, the data to be analyzed for the compliance check items can be efficiently analyzed, and then the processing results of the compliance check items can be obtained.

[0068] In one embodiment of the present disclosure, when the processing results of the compliance check items are obtained in the above manner, the intermediate processing results output by the processing nodes set in the first processing agent of the compliance check items can also be displayed, and in response to the corrective operation on the displayed intermediate processing results, the displayed intermediate processing results are updated, and then return to step B.

[0069] The processing nodes set above may be processing nodes with higher importance determined according to actual scenario requirements and / or experience, such as processing nodes with higher data processing complexity or processing nodes that are prone to outputting erroneous results.

[0070] See below Figure 4 , an intuitive introduction to the situation of correcting the intermediate processing results is given.

[0071] Figure 4 A schematic diagram of a correction interface of an intermediate processing result is shown. Processing nodes N1 to N3 in the correction interface are set processing nodes, and the correction interface displays function introductions and output boxes of processing nodes N1 to N3, which are introduced below.

[0072] For processing node N1:

[0073] The function of processing node N1 is introduced as "input the audit team members and their corresponding technical field codes". The output of node N1 is the auditor's technical field code. The specific content in the output box is "Auditor A's technical field code: XXXX; Auditor B's technical field code: XXXX".

[0074] For processing node N2:

[0075] The function of processing node N2 is introduced as "input the name string of the audit team members and return the split member name list". The output of processing node N2 is the auditor's name, and the specific content in the output box is "Auditor A, Auditor B..."

[0076] For processing node N3:

[0077] The function of processing node N3 is described as "inputting the technical capability code and auditor technical field code required for the second-stage audit plan to determine whether the professional scope can be fully covered". The output of processing node N3 includes professional categories and judgment results. Among them, the specific content in the output box of professional categories is "information security, information technology services"; the specific content in the output box of judgment results is "XXXXXXXXX".

[0078] In this way, the staff can intuitively understand the functions of processing nodes N1-processing node N3 and the intermediate results of the output, and then verify whether the intermediate results of processing nodes N1-processing node N3 are accurate. If inaccurate, they can manually adjust the intermediate results in the output boxes of processing nodes N1-processing node N3, and click the "Save and Regenerate" button, then the electronic device will input the corrected intermediate results of the processing node into the subsequent processing node.

[0079] In this way, after displaying the intermediate results output by the processing nodes set above, the output content of the key nodes is white-boxed, which is convenient for staff to check. When the staff checks the intermediate results and finds that the intermediate results are wrong, they can easily correct the intermediate results; further, after the electronic device updates the displayed intermediate processing results, the corrected intermediate processing results can be input into the subsequent processing nodes to eliminate the errors generated by the processing nodes in time and ensure the correct processing results. In addition, after the staff corrects the intermediate processing results, there is no need to re-run the workflow of the first processing agent, but to run the workflow from the corrected processing node, which improves the processing efficiency.

[0080] Step S103: Generate a compliance report based on the processing results of each compliance check item.

[0081] For compliance tasks, after obtaining the processing results of each compliance check item included in the compliance task, a compliance report can be generated.

[0082] The above-mentioned compliance report may only include the processing results indicating whether each compliance inspection item has passed the inspection, or may include a summary, conclusion, transition and the like, which is not limited in the embodiments of the present disclosure.

[0083] As can be seen from the above, when the scheme provided by the embodiment of the present disclosure is applied to generate a compliance report for a compliance task, the electronic device can load the first processing agent of each compliance check item defined by the selected target template in response to the processing template selection operation of the compliance task. Then, for each compliance check item, the data to be analyzed of the compliance check item is input into the first processing agent of the compliance check item, and the processing result output by the first processing agent after analyzing the data to be analyzed is obtained. Finally, based on the processing results of each compliance check item, a compliance report is successfully generated.

[0084] Among them, for the staff within the enterprise who have to process compliance tasks, they can conveniently select a target template from multiple processing templates according to the actual compliance tasks to be processed through the processing template selection operation. Furthermore, the electronic device can load a first processing agent for processing each compliance inspection item included in the compliance task, and automatically generate a compliance report based on the first processing agent. It can be seen that the solution provided by the embodiment of the present disclosure reduces the dependence on business personnel and compliance experts when processing compliance tasks, reduces the manpower cost consumed when processing compliance tasks, and can achieve the rapid start of compliance projects, thereby improving the processing efficiency of compliance tasks.

[0085] In addition, by defining various processing templates, staff can configure the processing logic of compliance tasks online, achieve flexible adaptation to various compliance tasks, meet the compliance task processing needs of different enterprises, and improve the flexibility in handling compliance tasks.

[0086] The following is an example of the processing node mentioned above.

[0087] In one embodiment of the present disclosure, the processing nodes may include at least two of the following nodes:

[0088] Data input node, data output node, large language model node, data retrieval node, vector embedding node, logical expression node, function call node, character recognition node, document node.

[0089] Among them, the data input node is used to obtain the input content of the staff, including common data types and file types, and can also be used to obtain system context data; the data output node is used to summarize the data and save the data to the set table or field of the database for front-end display; the large model node is used to interact with the large model; the data retrieval node is used to embed the query into a vector and retrieve and recall relevant content from the vector database; the vector embedding node is used to convert the query into a vector through vector embedding, which is generally used in similarity judgment scenarios, such as image similarity judgment scenarios; the logical expression node is used for one-time or low-frequency logical expressions; the function call node is used to call frequently used functions, which can be compliance archive query functions, system library query functions, etc.; the character recognition node is used to interact with the large model after document layout recognition; the document node is used to upload documents related to compliance task processing.

[0090] In this way, processing nodes with rich types are conducive to meeting the processing requirements of different compliance check items, and thus nodes for processing compliance check items of different compliance tasks can be generated efficiently and conveniently.

[0091] In one embodiment of the present disclosure, when generating the above-mentioned processing nodes, the processing operations of the compliance check items can be appropriately abstracted according to the actual scenario requirements to obtain various functional nodes, thereby achieving a balance between the complexity of the workflow and the reusability of the processing nodes.

[0092] A method for generating the first processing agent is introduced below.

[0093] Specifically, a directed acyclic graph (DAG) of each compliance check item included in the set compliance task may be obtained first, and then a first processing agent of each compliance check item may be generated according to the nodes and directed edges included in the DAG of each compliance check item.

[0094] The nodes in the directed acyclic graph above represent processing nodes, and the directed edges between the nodes represent the execution order of the processing nodes corresponding to the connected nodes.

[0095] The above-mentioned directed acyclic graph can be stored in JavaScript Object Notation (JSON) format. In this embodiment, the electronic device can execute the set scheduled task to obtain the JSON data corresponding to the compliance task, convert the JSON data into processing nodes represented by the DAG object and the execution order of the processing nodes, and generate the first processing agent for each compliance check item.

[0096] It can be seen that the directed acyclic graph can intuitively and conveniently represent the processing nodes and the execution order of the processing nodes. Furthermore, based on the directed acyclic graph, the first processing agent of the compliance check item can be generated conveniently and efficiently.

[0097] In one embodiment of the present disclosure, before generating the first processing agent based on the directed acyclic graph, the resulting directed acyclic graph can be updated in response to a staff member's update operation on the directed acyclic graph, and then the first processing agent can be generated based on the updated directed acyclic graph.

[0098] The above update operations include: adding nodes and / or directed edges in the directed acyclic graph, deleting nodes and / or directed edges in the directed acyclic graph, replacing nodes in the directed acyclic graph, and changing the direction of directed edges in the directed acyclic graph.

[0099] In this embodiment, by updating the directed acyclic graph, the processing nodes represented by the directed acyclic graph and the execution order of the processing nodes can be conveniently updated. In other words, the processing logic of the compliance check items represented by the directed acyclic graph can be conveniently updated. Furthermore, according to the updated directed acyclic graph, a new first processing agent can be quickly generated.

[0100] In one embodiment of the present disclosure, the above step S102 can be implemented by following steps C-E:

[0101] Step C: Generate a folder defined by the selected target template.

[0102] The above-mentioned folder is used for enterprise staff to upload auxiliary processing data. The auxiliary processing data may include a project definition form, including relevant information of the compliance task, such as the compliance task name, responsible person, etc.; the auxiliary processing data may also include a project dictionary definition, including compliance laws and regulations data, compliance file data, risk management data, etc., which is not limited in this disclosure.

[0103] Step D: Get the auxiliary processing data uploaded in the folder.

[0104] Step E: For each compliance check item, the data to be analyzed of the compliance check item is input into the first processing agent of the compliance check item, and a processing result output by the first processing agent after analyzing the data to be analyzed based on the auxiliary processing data is obtained.

[0105] In this way, when the first processing agent is running, it can not only read the data in its own process, but also read the legal and regulatory data, compliance file data, risk management data, etc. in the platform, thus realizing a closed loop within the workflow and system service data.

[0106] In this embodiment, the first processing agent can read the auxiliary processing data uploaded in the above-mentioned folder, and perform in-depth analysis on the data to be analyzed based on the above-mentioned auxiliary processing data, thereby further improving the accuracy of the first processing agent in analyzing the data, that is, improving the accuracy of the processing results of the compliance check items obtained by the first processing agent.

[0107] In one embodiment of the present disclosure, the above step S103 can be implemented by following steps F to G:

[0108] Step F: Load the second processing agent of the compliance report defined by the selected target template.

[0109] The meaning and generation method of the second processing agent are similar to those of the first processing agent. The only difference is that the second processing agent integrates the compliance report generation logic, which will not be repeated here.

[0110] Step G: Run the second processing agent so that the second processing agent generates a compliance report based on the processing results of each compliance check item.

[0111] Specifically, the second processing intelligence can fill the processing results of each compliance check item into the corresponding position in the set report template according to the set filling rules to obtain a compliance report.

[0112] In this embodiment, the target template also defines a second processing agent for generating a compliance report. Thus, after loading the second processing agent, the processing results of each compliance check item can be efficiently summarized based on the second processing agent to obtain a compliance report.

[0113] In one case, the second processing agent can replace the part to be replaced in the set report template based on the processing results of each compliance check item to obtain a compliance report.

[0114] That is, the report template includes a common part and a part to be replaced. The second processing agent replaces the part to be replaced in sequence with the processing results of the compliance check items obtained by the first processing agent, and the final compliance report can be obtained.

[0115] It can be seen that after obtaining the processing result of the compliance check item obtained by the first processing agent, a compliance report can be quickly generated by using the above processing result to replace the part to be replaced in the set report template.

[0116] The following is an example of another processing template provided in an embodiment of the present disclosure.

[0117] See also Figure 5 , shows a schematic diagram of another processing template, it can be seen that Figure 3 Compared with the smart template shown, Figure 5The shown intelligent template also defines a project configuration form and a project dictionary definition, so that the first processing agent can better handle compliance tasks based on the project configuration form and the project dictionary definition.

[0118] From the above, it can be seen that the solution provided by the embodiment of the present disclosure can meet the compliance requirements of enterprises for different compliance tasks by configuring the task workflow of the inspection items online. It has high reusability and does not require re-online, thus realizing the decoupling of engineering code and Prompt (task).

[0119] In addition, an intelligent agent is customized for each evaluation item. The workflow integrated in the intelligent agent can finely control the logic and output of each step, achieving the stability and reproducibility of the intelligent agent.

[0120] Furthermore, the smart template also defines an intelligent entity for generating compliance reports. The above intelligent entity can flexibly configure the content generation of different chapters in the compliance report, thereby generating thousands of pages of professional reports suitable for various industries.

[0121] According to the description of the above embodiments, Figure 6 , an example is given to illustrate a specific process of the first processing agent processing compliance check items.

[0122] Figure 6 Except for the closed figures marked with database, each closed figure represents a processing node included in the first processing agent. The processing flow of the processing node can be divided into the following stages:

[0123] Phase 1: Input data.

[0124] The input data includes check items, template preset contents, and project preset contents.

[0125] Among them, inputting inspection items can be understood as inputting inquiry text representing whether the inspection items are met into the data input node. The inquiry text can specifically be "whether the second-stage audit plan fully covers the audit scope and standard clauses."

[0126] The template preset content refers to the content pre-defined in the processing template, such as the chapter information of the relevant standard clauses corresponding to the compliance task; the project preset content refers to the organizational information, personnel information, etc. uploaded by the staff within the enterprise for processing compliance tasks, including the company's organizational structure information.

[0127] Phase 2: Analyze check items and generate query questions.

[0128] First, you can analyze the inspection items and determine the content to be inspected. For example, first determine that the document to be analyzed for the inspection items is the "Phase Two Audit" plan document; then, ask for the audit date and generate clause / department query questions.

[0129] Among them, clause / department query questions can include audit scope coverage query questions and standard clause coverage query questions.

[0130] The audit scope coverage query question is used to inquire whether the departments involved in the second-stage audit plan document fully cover the departments included in the company's organizational structure in the project preset content; the standard clause coverage query question is used to inquire whether the clauses involved in the second-stage audit plan document fully cover the relevant standard clauses in the template preset content.

[0131] Phase 3: Execute the query and make comparisons.

[0132] Regarding the audit scope coverage query, it specifically includes asking daily departments and conducting department coverage comparison based on the company's organizational structure to determine whether the departments involved in the second-stage audit plan document fully cover the departments included in the company's organizational structure in the project preset content.

[0133] For standard clause coverage inquiries, it specifically includes asking about daily clauses, clause analysis, and performing clause coverage comparison based on standard clauses to determine whether the clauses involved in the second-stage audit plan document fully cover the relevant standard clauses in the template preset content.

[0134] Phase 4: Comprehensive judgment of the large model and output of processing results.

[0135] After obtaining the comparison results, the large model node can make a comprehensive judgment on the obtained comparison results, determine the satisfaction of the inspection items according to the judgment results, and then obtain the inspection results of the inspection items, and save the inspection results to the database.

[0136] Corresponding to the above-mentioned compliance report generation method, the embodiment of the present disclosure also provides a compliance report generation device.

[0137] See also Figure 7 , is a schematic diagram of a compliance report generating device provided by an embodiment of the present disclosure, the device comprising:

[0138] The first agent loading module 701 is used to load the first processing agent of each compliance check item defined by the selected target template in response to the processing template selection operation of the compliance task, wherein the first processing agent of each compliance check item integrates the processing logic of the compliance check item;

[0139] The processing result obtaining module 702 is used for inputting the data to be analyzed of the compliance check item into the first processing agent of the compliance check item for each compliance check item, and obtaining the processing result output by the first processing agent after analyzing the data to be analyzed;

[0140] The report generation module 703 is used to generate a compliance report based on the processing results of each compliance check item.

[0141] As can be seen from the above, when the scheme provided by the embodiment of the present disclosure is applied to generate a compliance report for a compliance task, the electronic device can load the first processing agent of each compliance check item defined by the selected target template in response to the processing template selection operation of the compliance task. Then, for each compliance check item, the data to be analyzed of the compliance check item is input into the first processing agent of the compliance check item, and the processing result output by the first processing agent after analyzing the data to be analyzed is obtained. Finally, based on the processing results of each compliance check item, a compliance report is successfully generated.

[0142] Among them, for the staff within the enterprise who have to process compliance tasks, they can conveniently select a target template from multiple processing templates according to the actual compliance tasks to be processed through the processing template selection operation. Furthermore, the electronic device can load a first processing agent for processing each compliance inspection item included in the compliance task, and automatically generate a compliance report based on the first processing agent. It can be seen that the solution provided by the embodiment of the present disclosure reduces the dependence on business personnel and compliance experts when processing compliance tasks, reduces the manpower cost consumed when processing compliance tasks, and can achieve the rapid start of compliance projects, thereby improving the processing efficiency of compliance tasks.

[0143] In addition, by defining various processing templates, staff can configure the processing logic of compliance tasks online, achieve flexible adaptation to various compliance tasks, meet the compliance task processing needs of different enterprises, and improve the flexibility in handling compliance tasks.

[0144] In one embodiment of the present disclosure,

[0145] The first processing agent includes: a plurality of processing nodes, and the plurality of processing nodes have a set execution order.

[0146] It can be seen that the processing nodes and the execution order of the processing nodes can conveniently and efficiently represent the processing logic of the compliance check items, and then the intelligent entity can be efficiently constructed based on the processing nodes.

[0147] In one embodiment of the present disclosure, the first processing agent is generated using the following modules:

[0148] A directed acyclic graph acquisition module, used to obtain a directed acyclic graph of each compliance check item included in the set compliance task, wherein the nodes in the directed acyclic graph represent processing nodes, and the directed edges between the nodes represent the execution order of the processing nodes corresponding to the connected nodes;

[0149] The agent generation module is used to generate a first processing agent for each compliance check item based on the nodes and directed edges included in the directed acyclic graph of each compliance check item.

[0150] It can be seen that the directed acyclic graph can intuitively and conveniently represent the processing nodes and the execution order of the processing nodes. Furthermore, based on the directed acyclic graph, the first processing agent of the compliance check item can be generated conveniently and efficiently.

[0151] In one embodiment of the present disclosure, the device further includes:

[0152] An update module is used to update the resulting directed acyclic graph in response to an update operation on the resulting directed acyclic graph, thereby triggering the intelligent agent generation module, wherein the update operation includes: adding nodes and / or directed edges in the directed acyclic graph, deleting nodes and / or directed edges in the directed acyclic graph, replacing nodes in the directed acyclic graph, and changing the direction of directed edges in the directed acyclic graph.

[0153] In this embodiment, by updating the directed acyclic graph, the processing nodes represented by the directed acyclic graph and the execution order of the processing nodes can be conveniently updated. In other words, the processing logic of the compliance check items represented by the directed acyclic graph can be conveniently updated. Furthermore, according to the updated directed acyclic graph, a new first processing agent can be quickly generated.

[0154] In one embodiment of the present disclosure, the processing result obtaining module 702 is specifically used to obtain the processing result of the compliance check item according to the following submodules for each compliance check item:

[0155] A data input submodule, used to input the to-be-analyzed data of the compliance check item into a first processing node in a first processing agent of the compliance check item, and obtain an intermediate processing result output by the first processing node, wherein the first processing node is: a data input node among the processing nodes included in the first processing agent;

[0156] A result input submodule inputs the intermediate processing result into an adjacent processing node whose execution order is after the target processing node, to obtain a new intermediate processing result output by the adjacent processing node, wherein the target processing node is initially the first processing node;

[0157] The judgment submodule is used to determine the new intermediate processing result as the processing result of the compliance check item if the adjacent processing node is the second processing node; otherwise, the target processing node is updated to the adjacent processing node to trigger the result input submodule, wherein the second processing node is: the data output node in the processing node included in the first processing agent.

[0158] It can be seen that by orderly executing various processing nodes, the data to be analyzed for the compliance check items can be efficiently analyzed, and then the processing results of the compliance check items can be obtained.

[0159] In one embodiment of the present disclosure, the device further includes:

[0160] A result display module, used to display the intermediate processing results output by the processing nodes set in the first processing agent of the compliance check item;

[0161] The result updating module is used to update the displayed intermediate processing result in response to the correction operation on the displayed intermediate processing result, and trigger the result input submodule.

[0162] In this way, after displaying the intermediate results output by the processing nodes set above, the output content of the key nodes is white-boxed, which is convenient for staff to check. When the staff checks the intermediate results and finds that the intermediate results are wrong, they can easily correct the intermediate results; further, after the electronic device updates the displayed intermediate processing results, the corrected intermediate processing results can be input into the subsequent processing nodes to eliminate the errors generated by the processing nodes in time and ensure the correct processing results. In addition, after the staff corrects the intermediate processing results, there is no need to re-run the workflow of the first processing agent, but to run the workflow from the corrected processing node, which improves the processing efficiency.

[0163] In one embodiment of the present disclosure, the processing nodes include at least two of the following nodes:

[0164] Data input node, data output node, large language model node, data retrieval node, vector embedding node, logical expression node, function call node, character recognition node, document node.

[0165] In this way, processing nodes with rich types are conducive to meeting the processing requirements of different compliance check items, and thus nodes for processing compliance check items of different compliance tasks can be generated efficiently and conveniently.

[0166] In one embodiment of the present disclosure, the processing result acquisition module 702 is specifically used to generate a folder defined by the selected target template; obtain the auxiliary processing data uploaded in the folder; for each compliance check item, input the data to be analyzed of the compliance check item into the first processing agent of the compliance check item, and obtain the processing result output by the first processing agent after analyzing the data to be analyzed based on the auxiliary processing data.

[0167] In this embodiment, the first processing agent can read the auxiliary processing data uploaded in the above-mentioned folder, and perform in-depth analysis on the data to be analyzed based on the above-mentioned auxiliary processing data, thereby further improving the accuracy of the first processing agent in analyzing the data, that is, improving the accuracy of the processing results of the compliance check items obtained by the first processing agent.

[0168] In one embodiment of the present disclosure, the report generation module 703 includes:

[0169] A second agent loading submodule, used to load a second processing agent of the compliance report defined by the selected target template, wherein the second processing agent integrates the compliance report generation logic;

[0170] The report generation submodule is used to run the second processing agent so that the second processing agent generates a compliance report based on the processing results of each compliance check item.

[0171] In this embodiment, the target template also defines a second processing agent for generating a compliance report. Thus, after loading the second processing agent, the processing results of each compliance check item can be efficiently summarized based on the second processing agent to obtain a compliance report.

[0172] In one embodiment of the present disclosure, the report generation submodule is specifically used to run the second processing agent so that the second processing agent replaces the part to be replaced in the set report template based on the processing results of each compliance check item to obtain a compliance report.

[0173] It can be seen that after obtaining the processing result of the compliance check item obtained by the first processing agent, a compliance report can be quickly generated by using the above processing result to replace the part to be replaced in the set report template.

[0174] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0175] It should be noted that the head model in this embodiment is not a head model for a specific user and cannot reflect the personal information of a specific user.

[0176] It should be noted that the two-dimensional face images in this embodiment come from a public data set.

[0177] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0178] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0179] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0180] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0181] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the compliance report generation method. For example, in some embodiments, the compliance report generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the compliance report generation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the compliance report generation method in any other appropriate manner (e.g., by means of firmware).

[0182] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0183] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0184] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0186] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0187] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0188] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0189] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a compliance report, comprising: In response to a processing template selection operation of a compliance task, loading a first processing agent of each compliance check item defined by the selected target template, wherein the first processing agent of each compliance check item integrates the processing logic of the compliance check item; For each compliance check item, input the data to be analyzed of the compliance check item into the first processing agent of the compliance check item, and obtain the processing result output by the first processing agent after analyzing the data to be analyzed; Generate a compliance report based on the processing results of each compliance check item.

2. The method according to claim 1, wherein: The first processing agent includes: a plurality of processing nodes, and the plurality of processing nodes have a set execution order.

3. The method according to claim 2, wherein: The first processing agent is generated in the following manner: Obtaining a directed acyclic graph of compliance check items included in the set compliance task, wherein the nodes in the directed acyclic graph represent processing nodes, and the directed edges between the nodes represent the execution order of the processing nodes corresponding to the connected nodes; A first processing agent for each compliance check item is generated according to the nodes and directed edges included in the directed acyclic graph of each compliance check item.

4. The method according to claim 3, wherein: Before generating the first processing agent for each compliance check item according to the nodes and directed edges included in the directed acyclic graph of each compliance check item, the method further includes: In response to an update operation on the resulting directed acyclic graph, the resulting directed acyclic graph is updated, wherein the update operation includes: adding nodes and / or directed edges in the directed acyclic graph, deleting nodes and / or directed edges in the directed acyclic graph, replacing nodes in the directed acyclic graph, and changing the direction of directed edges in the directed acyclic graph.

5. The method according to claim 2, wherein: For each compliance check item, inputting the data to be analyzed of the compliance check item into the first processing agent of the compliance check item, and obtaining the processing result output by the first processing agent after analyzing the data to be analyzed, includes: For each compliance check item, the processing result of the compliance check item is obtained in the following manner: Inputting the data to be analyzed of the compliance check item into a first processing node in a first processing agent of the compliance check item, and obtaining an intermediate processing result output by the first processing node, wherein the first processing node is: a data input node among the processing nodes included in the first processing agent; Inputting the intermediate processing result into an adjacent processing node whose execution order is after the target processing node, to obtain a new intermediate processing result output by the adjacent processing node, wherein the target processing node is initially the first processing node; If the adjacent processing node is the second processing node, the new intermediate processing result is determined as the processing result of the compliance check item; otherwise, the target processing node is updated to the adjacent processing node, and the step of inputting the intermediate processing result into the adjacent processing node whose execution order is after the target processing node is returned, wherein the second processing node is: a data output node among the processing nodes included in the first processing agent.

6. The method according to claim 5, wherein: The method further comprises: Displaying the intermediate processing results output by the processing nodes set in the first processing agent of the compliance check item; In response to the correction operation on the displayed intermediate processing result, the displayed intermediate processing result is updated, and the step of inputting the intermediate processing result to the first adjacent processing node after the target processing node in the execution order is returned.

7. The method according to claim 2, wherein: The processing nodes include at least two of the following nodes: Data input node, data output node, large language model node, data retrieval node, vector embedding node, logical expression node, function call node, character recognition node, document node.

8. The method according to any one of claims 1 to 7, wherein: For each compliance check item, inputting the data to be analyzed of the compliance check item into the first processing agent of the compliance check item, and obtaining the processing result output by the first processing agent after analyzing the data to be analyzed, includes: Generate a folder defined by the selected target template; Obtaining the auxiliary processing data uploaded in the folder; For each compliance check item, the data to be analyzed of the compliance check item is input into the first processing agent of the compliance check item, and a processing result output by the first processing agent after analyzing the data to be analyzed based on the auxiliary processing data is obtained.

9. The method according to any one of claims 1 to 7, wherein: The compliance report generated based on the processing results of each compliance check item includes: A second processing agent loading the compliance report defined by the selected target template, wherein the second processing agent integrates the compliance report generation logic; The second processing agent is run so that the second processing agent generates a compliance report based on the processing results of each compliance check item.

10. The method according to claim 9, wherein: The step of running the second processing agent so that the second processing agent generates a compliance report based on the processing results of each compliance check item includes: The second processing agent is run so that the second processing agent replaces the to-be-replaced part in the set report template based on the processing results of each compliance check item to obtain a compliance report.

11. A compliance report generating device, comprising: A first agent loading module is used to load the first processing agent of each compliance check item defined by the selected target template in response to the processing template selection operation of the compliance task, wherein the first processing agent of each compliance check item integrates the processing logic of the compliance check item; A processing result obtaining module is used to input the data to be analyzed of the compliance check item into the first processing agent of the compliance check item for each compliance check item, and obtain the processing result output by the first processing agent after analyzing the data to be analyzed; The report generation module is used to generate a compliance report based on the processing results of each compliance check item.

12. The device according to claim 11, wherein The first processing agent includes: a plurality of processing nodes, and the plurality of processing nodes have a set execution order.

13. The device according to claim 12, wherein: The first processing agent is generated using the following modules: A directed acyclic graph acquisition module, used to obtain a directed acyclic graph of each compliance check item included in the set compliance task, wherein the nodes in the directed acyclic graph represent processing nodes, and the directed edges between the nodes represent the execution order of the processing nodes corresponding to the connected nodes; The agent generation module is used to generate a first processing agent for each compliance check item based on the nodes and directed edges included in the directed acyclic graph of each compliance check item.

14. The device according to claim 13, wherein: The device also includes: An update module is used to update the resulting directed acyclic graph in response to an update operation on the resulting directed acyclic graph, thereby triggering the intelligent agent generation module, wherein the update operation includes: adding nodes and / or directed edges in the directed acyclic graph, deleting nodes and / or directed edges in the directed acyclic graph, replacing nodes in the directed acyclic graph, and changing the direction of directed edges in the directed acyclic graph.

15. The device according to claim 12, wherein: The processing result obtaining module is specifically used to obtain the processing result of the compliance check item according to the following submodules: A data input submodule, used to input the to-be-analyzed data of the compliance check item into a first processing node in a first processing agent of the compliance check item, and obtain an intermediate processing result output by the first processing node, wherein the first processing node is: a data input node among the processing nodes included in the first processing agent; A result input submodule inputs the intermediate processing result into an adjacent processing node whose execution order is after the target processing node, to obtain a new intermediate processing result output by the adjacent processing node, wherein the target processing node is initially the first processing node; The judgment submodule is used to determine the new intermediate processing result as the processing result of the compliance check item if the adjacent processing node is the second processing node; otherwise, the target processing node is updated to the adjacent processing node to trigger the result input submodule, wherein the second processing node is: the data output node in the processing node included in the first processing agent.

16. The device according to claim 15, wherein: The device also includes: A result display module, used to display the intermediate processing results output by the processing nodes set in the first processing agent of the compliance check item; The result updating module is used to update the displayed intermediate processing result in response to the correction operation on the displayed intermediate processing result, and trigger the result input submodule.

17. The device according to claim 12, wherein: The processing nodes include at least two of the following nodes: Data input node, data output node, large language model node, data retrieval node, vector embedding node, logical expression node, function call node, character recognition node, document node.

18. The device according to any one of claims 11 to 17, wherein: The processing result acquisition module is specifically used to generate a folder defined by the selected target template; obtain the auxiliary processing data uploaded in the folder; for each compliance check item, input the data to be analyzed of the compliance check item into the first processing agent of the compliance check item, and obtain the processing result output by the first processing agent after analyzing the data to be analyzed based on the auxiliary processing data.

19. The device according to any one of claims 11 to 17, wherein: The report generation module comprises: A second agent loading submodule, used to load a second processing agent of the compliance report defined by the selected target template, wherein the second processing agent integrates the compliance report generation logic; The report generation submodule is used to run the second processing agent so that the second processing agent generates a compliance report based on the processing results of each compliance check item.

20. The device according to claim 19, wherein The report generation submodule is specifically used to run the second processing agent so that the second processing agent replaces the to-be-replaced part in the set report template based on the processing results of each compliance check item to obtain a compliance report.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images