Government affair intelligent management system based on knowledge graph

Abstract

The application discloses a government affair intelligent management system based on a knowledge graph, which is used for improving the efficiency and accuracy of government affair intelligent management. A process entity node is determined in an initial layer knowledge graph according to a government affair request. An ant colony process path model is constructed according to the process entity node. The corresponding process entity node of each image information in the government affair request in the ant colony process path model is determined. The execution progress of the corresponding process entity node is generated through image features. The historical use priority of each process entity node is calculated. The priority of each process entity node is valued according to the ant colony algorithm, the execution progress and the historical use priority, and a first target ant colony process path is determined. A sub-layer knowledge graph is selected according to the first target ant colony process path and the government affair request. A new ant colony process path model is generated according to the sub-layer knowledge graph and the government affair request, and a second target ant colony process path is generated. The government affair request is processed according to the second target ant colony process path.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of government affairs processing, and in particular to a government affair intelligent management system based on a knowledge graph. BACKGROUND

[0002] Existing government affairs services need to be formed by government affair data, and the large quantity, multiple systems and multiple levels of government affair data bring difficulties to government management systems. Nowadays, a knowledge graph can be used to assist management, and the knowledge graph can effectively integrate government affair data.

[0003] The knowledge graph organizes the knowledge in the government affairs field in a structured manner, covering information such as policies and regulations, procedures, department responsibilities, etc. When a user raises a consultation or handles a business, the system can quickly locate the relevant information in the knowledge graph, realize accurate query and rapid response. In addition, the core of the knowledge graph in government affairs services is to select the most suitable process entity node to form a process service path, and the knowledge graph can intelligently guide the user to complete the business handling process according to the user's demand and input information. By analyzing the logical relationship and rules in the knowledge graph, the system can automatically determine the current handling stage of the user, and accurately analyze the next operation and required materials.

[0004] However, the current knowledge graph government management system still has some problems. In a government request, there are usually many types of information, including text information and image information. The existing knowledge graph only determines the process entity node in the knowledge graph after analyzing the text information by a semantic analysis model, and does not use the image information. Secondly, in the existing knowledge graph, the same process entity node can lead to different process entity nodes, i.e. the same government request may have many process service paths, but the required materials for each process service path are not the same, which makes the knowledge graph unable to determine the optimal process service path for the user, reducing the efficiency and accuracy of government intelligent management. Secondly, the knowledge graph in the government affairs field is composed of many government files. These government files are generally government files issued by the upper level, but in the lower level area, the upper government files are usually refined to generate more specific lower government files, i.e. each area can refine the policies of the region according to the policies of the upper level, which makes it impossible for a knowledge graph of the upper level to obtain the lower government files of the region in time, and it is also impossible to update the knowledge graph according to the lower government files of the region, which further leads to the fact that the government request cannot be processed according to the process entity nodes specific to the region, increasing the processing time and difficulty, and further reducing the efficiency and accuracy of government intelligent management. SUMMARY

[0005] The application discloses a government affair intelligent management system based on a knowledge graph, and aims to improve the efficiency and accuracy of government affair intelligent management.

[0006] In a first aspect, the embodiments of the application provide a government affair intelligent management system based on a knowledge graph, comprising:

[0007] The government affair intelligent management system determines a plurality of process entity nodes in the primary layer knowledge graph according to text information in the government affair request;

[0008] The government affair intelligent management system constructs an ant colony process path model according to the process sequence of the plurality of process entity nodes, and the ant colony process path model comprises a plurality of process paths composed of the plurality of process entity nodes;

[0009] The government affair intelligent management system determines the corresponding process entity node of each image information in the government affair request in the ant colony process path model;

[0010] The government affair intelligent management system extracts image features in the image information, and generates the execution progress of the corresponding process entity node through the image features;

[0011] The government affair intelligent management system calculates the historical use priority of each process entity node;

[0012] The government affair intelligent management system assigns priority to each process entity node according to the ant colony algorithm, the execution progress and the historical use priority, determines a first target ant colony process path from the ant colony process path model, and the sum of the priority assignments of all the process entity nodes in the first target ant colony process path is higher than that of other process paths;

[0013] The government affair intelligent management system selects a sub-layer knowledge graph according to the first target ant colony process path and the government affair request;

[0014] The government affair intelligent management system generates a new ant colony process path model according to the sub-layer knowledge graph and the government affair request, assigns priority to the process entity nodes in the ant colony process path model, and generates a second target ant colony process path;

[0015] The government affair intelligent management system processes the government affair request according to the second target ant colony process path.

[0016] Optionally, the government affair intelligent management system determines the corresponding process entity node of each image information in the ant colony process path model, comprising:

[0017] The government affair intelligent management system determines an attachment type label of the image information;

[0018] The government affair intelligent management system determines the material demand type label of each process entity node according to the primary knowledge graph, and each process entity node comprises at least one material demand type label;

[0019] The government affair intelligent management system matches the attachment type label and the material demand type label, so that each image information is matched to the corresponding process entity node in the ant colony process path model.

[0020] Optionally, the government affair intelligent management system extracts image features in the image information, and generates the execution progress of the corresponding process entity node through the image features, comprising:

[0021] The government affair intelligent management system determines the verification feature recognition model and the reference verification data according to the primary knowledge graph and the material demand type label;

[0022] The government affair intelligent management system analyzes the image features in the image information and the reference verification data through the verification feature recognition model, and generates a verification result for all image information in each process entity node;

[0023] The government affair intelligent management system generates node simulation path parameters for each process entity node according to all verification results in each process entity node;

[0024] The government affair intelligent management system adjusts the execution progress of the process entity node according to the node simulation path parameters.

[0025] Optionally, the government affair intelligent management system calculates the historical use priority of each process entity node, comprising:

[0026] The government affair intelligent management system determines the running history information of each process entity node from the primary knowledge graph;

[0027] The government affair intelligent management system generates a use rate parameter for each process entity node according to the running history information of each process entity node;

[0028] The government affair intelligent management system adjusts the historical use priority of each process entity node according to the use rate parameter.

[0029] Optionally, the government affair intelligent management system selects a sub-layer knowledge graph according to the first target ant colony process path and the government affair request, comprising:

[0030] The government affair intelligent management system determines the upper reference data for constructing the primary knowledge graph according to the first target ant colony process path;

[0031] The government affair intelligent management system determines the lower reference data in the primary knowledge graph according to the upper reference data and the government affair area information of the government affair request;

[0032] The government affair intelligent management system selects a sub-layer knowledge graph with the largest correlation degree according to the reference data of the lower level.

[0033] Optionally, the government affair intelligent management system determines a plurality of process entity nodes in the initial layer knowledge graph according to the text information in the government affair request, including:

[0034] The government affair intelligent management system performs semantic analysis on the text information in the government affair request, and determines a plurality of initial entity processing nodes from the initial layer knowledge graph.

[0035] The government affair intelligent management system performs sibling node expansion processing according to the initial entity processing nodes.

[0036] The government affair intelligent management system performs one-time process entity node expansion according to the initial entity processing nodes, determines next-level process entity nodes, and repeatedly performs process entity node expansion on the process entity nodes to generate a process entity node set.

[0037] The government affair intelligent management system combines the plurality of initial entity processing nodes and the process entity node set to generate a plurality of process entity nodes.

[0038] In a second aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium has a program saved thereon, and the program performs the method according to the first aspect and any optional government affair intelligent management system of the first aspect when executed on a computer.

[0039] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0040] The government affair intelligent management system first determines a plurality of process entity nodes in the initial layer knowledge graph according to the text information in the government affair request. Next, the government affair intelligent management system constructs an ant colony process path model according to the plurality of process entity nodes, and initializes the parameters of each process entity node in the ant colony process path model according to the ant colony algorithm. The government affair intelligent management system determines the corresponding process entity node of each image information in the government affair request in the ant colony process path model. The government affair intelligent management system extracts the image features in the image information, and adjusts the execution progress of the corresponding process entity node through the image features. The government affair intelligent management system adjusts the historical use priority of each process entity node. The government affair intelligent management system determines a first target ant colony process path through the ant colony algorithm and the ant colony process path model. The government affair intelligent management system selects a sub-layer knowledge graph according to the first target ant colony process path and the government affair request. The government affair intelligent management system generates a sub-layer knowledge graph for the government affair request and processes according to a second target ant colony process path.

[0041] The image feature analysis method and the ant colony algorithm are used to screen the process entity nodes in the ant colony process path model, the optimal first target ant colony process path is determined, then the superior file corresponding to the first target ant colony process path is determined, the subordinate file corresponding to the superior file in the region is determined according to the government affair request, the corresponding sub-layer knowledge graph is found, finally, the government affair intelligent management system generates the government affair request according to the sub-layer knowledge graph and processes the government affair request according to the second target ant colony process path. The image features are reasonably used, the more suitable sub-layer knowledge graph is found according to the first target ant colony process path determined according to the initial layer knowledge graph, finally, the government affair request is processed according to the second target ant colony process path corresponding to the region determined according to the sub-layer knowledge graph, and the efficiency and accuracy of the government affair intelligent management are improved. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 An embodiment schematic diagram of the government affair intelligent management system based on the knowledge graph of the present application;

[0044] Figure 2 An embodiment schematic diagram of the method for determining the process entity nodes of the government affair intelligent management system of the present application;

[0045] Figure 3 An embodiment schematic diagram of the method for adjusting the execution progress of the government affair intelligent management system of the present application;

[0046] Figure 4 An embodiment schematic diagram of the method for adjusting the historical use priority of the government affair intelligent management system of the present application;

[0047] Figure 5 An embodiment schematic diagram of the method for selecting the sub-layer knowledge graph of the government affair intelligent management system of the present application;

[0048] Figure 6 Another embodiment schematic diagram of the method for determining the process entity nodes of the government affair intelligent management system of the present application. DETAILED DESCRIPTION

[0049] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0050] It is to be understood that the terminology "includes", "has", "holds", "contains" or "comprising", "including", "having" and the like, when used in the present specification and in the accompanying claims, are used in the sense of "including but not limited to", "including but not limited to", "including but not limited to" and "including but not limited to" respectively, and should be construed as specifically setting forth the stated features, integers, steps or components but not precluding one or more additional features, integers, steps, components and / or groups thereof.

[0051] It is also to be understood that the terminology "and / or" as used in the specification and in the claims, means any one of the associated listed items, or a combination of any two or more of the associated listed items, and includes all possible combinations thereof.

[0052] As used in the present specification and in the accompanying claims, the term "if" can be interpreted as meaning "when" or "once" or "in response to a determination" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "once it is determined" or "in response to a determination" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0053] In addition, the terms "first", "second", "third", etc. as used in the description of the specification and the appended claims are not used to denote or imply relative importance but are used to distinguish one element from another.

[0054] Reference throughout this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment" or "in some embodiments" or "in other embodiments" or "in additional embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specified. The terms "comprising", "including", "having" and the like are meant to be interpreted as "including but not limited to" unless otherwise indicated.

[0055] In the prior art, there are still some problems in the government affair management system of the knowledge graph. In a government affair request, there are usually many types of information, including text information and image information. The existing knowledge graph only determines the process entity node in the knowledge graph through semantic analysis of the text information, and does not utilize the image information. Secondly, in the existing knowledge graph, the same process entity node can lead to different process entity nodes, that is, the same government affair request can have many process service paths, but the materials required by each process service path are not the same, which makes the knowledge graph unable to determine the optimal process service path for the user, and reduces the efficiency and accuracy of government affair intelligent management. Secondly, the knowledge graph in the government affair field is composed of many government affair files. These government affair files are generally government affair files issued by the upper level, but in the lower level area, the upper government affair files are usually refined to generate lower government affair files with more specific steps, that is, each area can refine the policies of the region according to the policies of the upper level, which makes it impossible for an upper knowledge graph to obtain the lower government affair files of the region in time, and it is also impossible to update the knowledge graph according to the lower government affair files of the region, thereby causing the government affair request to be unable to process the government affair according to the process entity node specific to the region, increasing the processing time and difficulty, and further reducing the efficiency and accuracy of government affair intelligent management.

[0056] Based on this, the present application discloses a government affair intelligent management system based on a knowledge graph, which is used to improve the efficiency and accuracy of government affair intelligent management.

[0057] The technical solutions in the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0058] The method of the present application can be applied to a server, a device, a terminal or other devices with logical processing capability, and the present application is not limited to this. For convenience of description, the following will be described taking the execution subject as a terminal as an example.

[0059] Please refer to Figure 1 The present application provides an embodiment of a government affair intelligent management system based on a knowledge graph, which comprises:

[0060] 101、The government affair intelligent management system determines a plurality of process entity nodes in the primary layer knowledge graph according to the text information in the government affair request;

[0061] In this embodiment, after the government affair intelligent management system obtains the government affair request, it first obtains semantic information through semantic analysis, and then uses the semantic information to determine a plurality of process entity nodes from the primary knowledge graph. The specific content will be described in detail later.

[0062] 102. The government affair intelligent management system constructs an ant colony process path model according to the process sequence of the plurality of process entity nodes. In the ant colony process path model, there are a plurality of process paths composed of a plurality of process entity nodes.

[0063] In this embodiment, the government affair intelligent management system associates the plurality of process entity nodes obtained, so that the plurality of process entity nodes form at least one process path, constructs an ant colony process path model, and fits each process entity node into a path. Subsequently, according to the ant colony algorithm and the parameters on the process entity nodes, the parameters of each process entity node are initialized to meet the calculation of the ant colony algorithm. Specifically, the execution progress (heuristic information) and the historical use priority (initial information concentration) of each process entity node need to be calculated, and then the information pheromone importance factor and the heuristic information importance factor, the number of ants, the information pheromone evaporation coefficient and the information pheromone intensity are set according to the situation to assist the calculation of the ant colony algorithm.

[0064] 103. The government affair intelligent management system determines the corresponding process entity node of each image information in the government affair request in the ant colony process path model.

[0065] When the terminal initializes the ant colony process path model, it is necessary to determine the corresponding process entity node of each image information in the government affair request in the ant colony process path model. It is necessary to seat according to the label corresponding to the image information, because each process entity node will need at least one type of proof material, and the proof material uploaded by the requester is often of the image type and will be annotated with corresponding labels. At this time, it is necessary to determine whether the image is accurate through the model, and before determining whether it is accurate, it is necessary to determine which nodes the images correspond to, and then use the recognition model corresponding to the node to recognize. For example, a certain process entity node needs the requester to upload a request letter. After receiving the file annotated with "request letter", the file is matched with the process entity node. The specific steps are described in subsequent embodiments.

[0066] 104. The government affair intelligent management system extracts image features from the image information, and generates the execution progress of the corresponding process entity node through the image features.

[0067] The government affair intelligent management system extracts image features in image information and analyzes the image features, and generates an execution progress of a process entity node through an analysis result in the image features. In this way, the completeness of materials required in each process entity node can be determined. When a requester uses a government affair request to reach the process entity node, whether the image data in the government affair request can quickly complete the node so that the government affair request smoothly departs for a next process entity node. The execution progress represents the completion degree of the process entity node. In this way, each node corresponding path in the ant colony process path model is accurately updated, so that the ant colony process path model is more consistent with the difficulty of all process entity nodes in a real processing scenario. This parameter is also an important parameter for subsequent ant colony algorithm. The specific steps are described in detail in subsequent embodiments.

[0068] 105. The government affair intelligent management system calculates a historical use priority of each process entity node.

[0069] In order to make the ant colony process path model more consistent with the real scenario, the historical use priority of each process entity node needs to be calculated according to the government affair processing data (historical data) in the real scenario. The government affair processing data can also be obtained according to the primary knowledge graph. The historical use priority represents the frequency of use of the process entity node by the requester. The specific processing steps are described in detail later.

[0070] 106. The government affair intelligent management system assigns a priority to each process entity node according to the ant colony algorithm, the execution progress and the historical use priority, and determines a first target ant colony process path from the ant colony process path model. The sum of the priority assignments of all process entity nodes in the first target ant colony process path is higher than that of other process paths.

[0071] In this embodiment, when the ant colony process path model completes the update of the execution progress and the historical use priority , the algorithm can be iterated to assign a priority to each process entity node. After the priority assignment is completed, the path selection of the government affair process can be performed, and finally the first target ant colony process path is obtained. There are many process entity nodes in the first target ant colony process path.

[0072] Specifically, first, the probability that a requester will select a node is calculated according to the execution progress and the historical use priority of each node:

[0073]

[0074] wherein the number of process entity nodes belonging to the same level is M, and the execution progress and history of the kth flow entity node are used as priorities, an execution progress weight (pheromone importance), a history priority weight (heuristic information importance), and the execution progress history priority of the flow entity node at the same level is used to calculate the selection probability of the kth flow entity node The probability calculation method described above can also be various, which is not limited here.

[0075] After each flow entity node is calculated, the number of times each flow entity node is selected is calculated through the ant colony algorithm and the initialized model parameters (the number of ants, the pheromone evaporation coefficient, the pheromone intensity, and other information). For example, the number of ants is set to 50000, and each ant leaves a history priority assignment value when passing through a flow entity node, that is, the history priority is increased, so that the probability P of selecting this flow entity node is increased, which affects the selection of subsequent ants. In addition, the pheromone evaporation (after a certain number of ants pass through, the history priority of all flow entity nodes is uniformly reduced by a value, which is less than the assignment value of the history priority increased by the ants) can be set according to the ant colony algorithm to speed up the iteration. When all ants complete the assignment of the flow entity nodes, the current history priority of each flow entity node is determined as the priority assignment value. The priority assignment value sum of each path flow path can be calculated, and the flow path with the maximum priority assignment value sum is selected as the first target ant colony flow path.

[0076] 107、The government affair intelligent management system selects a sub-layer knowledge graph according to the first target ant colony flow path and the government affair request;

[0077] In the prior art, when a government affair request is received, although the major project required for processing the government affair request can be roughly determined, the regional policy where the government affair request is located cannot be determined, and thus the appropriate knowledge graph cannot be allocated, because the text information in the government affair request is usually highly regional, and the words used in the government affair files of the upper and lower levels are also different, because the government affair files of the lower level can refine the policies of the government affair files of the upper level, and after the policy refinement processing, the government affair files of the lower level can appear some new words, or the words in the government affair files of the upper level are converted into new words (the words are different but the meanings are the same), that is, the regionalization of words can appear. For example, different nouns are used in the government affair files of the upper and lower levels to refer to the same meaning, and the schemes used in the government affair files of the upper and lower levels after the refinement processing are different from the government affair files of the upper level. This makes the processes of the knowledge graph of the upper level and the knowledge graph of the lower level different, and because of the regionalized words in the government affair request, the service scheme provided by the knowledge graph of the upper level (the primary knowledge graph) for the government affair request is not the most appropriate.

[0078] To solve the above problems, in the embodiment, after the first target ant colony process path is obtained by using the primary knowledge graph combined with the ant algorithm, the first target ant colony process path is not necessarily the most suitable for the government affair request, but in the primary knowledge graph constructed by the upper level policy file, the priority is relatively high, at this time, the corresponding regional and government affair file matching sub-layer knowledge graph needs to be selected according to the first target ant colony process path and the government affair request. The selection of the specific sub-layer knowledge graph is described in the subsequent embodiments.

[0079] 108、The government affair intelligent management system generates a new ant colony process path model according to the sub-layer knowledge graph and the government affair request, and performs priority assignment for the process entity nodes in the ant colony process path model, to generate a second target ant colony process path;

[0080] 109、The government affair intelligent management system processes the government affair request according to the second target ant colony process path.

[0081] In this embodiment, the government affair intelligent management system generates a new ant colony process path model according to the sub-layer knowledge graph and the government affair request, that is, generates a new ant colony process path model based on the sub-layer knowledge graph more in line with the government affair request. This step is similar to the foregoing step 101, and details are not repeated here. Then the government affair intelligent management system determines a plurality of process entity nodes in the primary layer knowledge graph according to the text information in the government affair request, determines the corresponding process entity nodes of each image information in the ant colony process path model in the government affair request, extracts the image features in the image information, generates the execution progress of the corresponding process entity nodes through the image features, calculates the historical use priority of each process entity node, and then assigns a priority to each process entity node according to the ant colony algorithm, the execution progress and the historical use priority. The second target ant colony process path is determined from the ant colony process path model. This way is similar to the foregoing steps 102 to 106, and similar to the refinement of these steps in subsequent embodiments. Please refer to the corresponding analysis content of these steps, and details are not repeated here. Finally, the second target ant colony process path is determined to be a process path more in line with the government affair request. At this time, the service can be provided to the requestor according to each process node of the second target ant colony process path.

[0082] In this embodiment, the government affair intelligent management system first determines a plurality of process entity nodes in the primary layer knowledge graph according to the text information in the government affair request. Next, the government affair intelligent management system constructs an ant colony process path model according to the plurality of process entity nodes, and initializes the parameters of each process entity node in the ant colony process path model according to the ant colony algorithm. The government affair intelligent management system determines the corresponding process entity nodes of each image information in the ant colony process path model in the government affair request. The government affair intelligent management system extracts the image features in the image information, and adjusts the execution progress of the corresponding process entity nodes through the image features. The government affair intelligent management system adjusts the historical use priority of each process entity node. The government affair intelligent management system determines the first target ant colony process path through the ant colony algorithm and the ant colony process path model. The government affair intelligent management system selects the sub-layer knowledge graph according to the first target ant colony process path and the government affair request. The government affair intelligent management system generates the government affair request according to the sub-layer knowledge graph and processes according to the second target ant colony process path.

[0083] The image feature analysis method and the ant colony algorithm are used for screening the process entity nodes in the ant colony process path model, the optimal first target ant colony process path is determined, the upper file corresponding to the first target ant colony process path is determined, then the lower file corresponding to the upper file in the region is determined according to the government affair request, so that the corresponding sub-layer knowledge graph is found, finally the government affair intelligent management system generates the government affair request according to the sub-layer knowledge graph and processes the government affair request according to the second target ant colony process path. The image features are reasonably used, the first target ant colony process path is found according to the initial layer knowledge graph, the more suitable sub-layer knowledge graph is found, finally the second target ant colony process path corresponding to the region is determined for the government affair request to process the government affair request, and the efficiency and accuracy of the government affair intelligent management are improved.

[0084] Please refer to Figure 2 An embodiment of a method for determining a process entity node is provided, comprising:

[0085] 201. The government affair intelligent management system determines the attachment type label of the image information;

[0086] In this embodiment, the label information of the uploaded image information in the government affair request is used, for example, an image A is uploaded, and the attachment type label of the image A is a government contract. For another example, an image B is uploaded, and the label is environmental pollution evidence. The label can help to bind the image to the corresponding process entity node.

[0087] 202. The government affair intelligent management system determines the material demand type label of each process entity node according to the initial layer knowledge graph, and each process entity node includes at least one material demand type label;

[0088] In this embodiment, after the government affair intelligent management system determines the attachment type label of the image information, the government affair intelligent management system also needs to determine the corresponding collected file on each process entity node. The government affair intelligent management system can use the initial layer knowledge graph to list the node files, for example, it is determined through the knowledge graph that a process entity node needs to upload image information such as a government contract and a delivery certificate.

[0089] The government affair intelligent management system determines the material demand type label of each process entity node according to the initial layer knowledge graph, and each process entity node includes at least one material demand type label.

[0090] 203. The government affair intelligent management system matches the attachment type label and the material demand type label, so that each image information is matched to the corresponding process entity node in the ant colony process path model.

[0091] When the government affair intelligent management system determines the attachment type label and the material requirement type label of each process entity node, the government affair intelligent management system matches the attachment type label and the material requirement type label, so that each image information is matched to the corresponding process entity node in the ant colony process path model.

[0092] Please refer to Figure 3 An embodiment of the method for adjusting the execution progress is provided, which comprises:

[0093] 301. The government affair intelligent management system determines the verification feature recognition model and the reference verification data according to the primary knowledge graph and the material requirement type label.

[0094] 302. The government affair intelligent management system analyzes the image features in the image information and the reference verification data through the verification feature recognition model, and generates a verification result for all the image information in each process entity node.

[0095] In this embodiment, the government affair intelligent management system first determines the verification feature recognition model and the reference verification data according to the primary knowledge graph and the material requirement type label. That is, the material requirement type label is used as an entity to find the corresponding verification feature recognition model and reference verification data in the primary knowledge graph. For example, when the material requirement type label is a government transaction contract, the location of the verification feature recognition model (government transaction contract recognition model) and the location of the reference verification data (historical government transaction contract) are determined from the primary knowledge graph, the government affair intelligent management system calls the model, and the historical contract data in the database is obtained.

[0096] Next, the government affair intelligent management system analyzes the image features in the image information and the reference verification data through the verification feature recognition model, and determines whether the necessary features of the image information and the reference verification data are complete. If they are complete, it means that the image information is determined to be a qualified image file. According to the above example, it is further explained that the image data is determined to be a government contract.

[0097] The government affair intelligent management system needs to generate a verification result for all the image information in each process entity node, that is, it needs to determine whether each image information on the process entity node meets the requirements. If it does not meet the requirements, it needs to replace the model and the reference verification data for reanalysis, and determine whether each image information in each process entity node has the corresponding file features of the process entity node. If it does not have any corresponding reference file in the process entity node, it needs to give a verification result that the image information does not meet the requirements of the process entity node. If it meets the requirements, it also needs to generate a confidence value of the image information according to the number of feature points that meet the requirements, and put the confidence value into the verification result. The confidence value is a parameter greater than 0 and less than 1.

[0098] 303、The government affair intelligent management system generates node simulation path parameters for each process entity node according to all verification results in each process entity node;

[0099] The government affair intelligent management system generates node simulation path parameters for each process entity node according to all verification results in each process entity node, that is, the confidence data of all image data of each node is analyzed, it is judged whether the data required by each node is complete, and then the completion difficulty of the process entity node is determined, the node simulation path parameters are generated based on the completion difficulty, and the greater the completion difficulty, the greater the node simulation path parameters. For example, the items in a process entity node include a purchase and sale contract, a commission contract and a seal of a related unit, there is one contract, one seal and one blank image (blank image is an unsubmitted item) in the image data, one contract and one seal are verified, it is verified whether the contract is one of the purchase and sale contract or the commission contract, and it is verified whether the seal is the seal of the related unit, and the corresponding verification results are obtained: the probability of the contract being the purchase and sale contract or the commission contract (confidence parameter), and the probability of the seal being the seal of the related unit.

[0100]

[0101] wherein, is the node simulation path parameter, is the number of images with verification results, is the confidence parameter of the i-th image with verification results, is the number of images without verification results, is the parameter of the j-th image without verification results, which is usually directly set to 1, and at this time , but generally it is set to a fixed value higher than 0.95.

[0102] 304、The government affair intelligent management system adjusts the execution progress of the process entity node according to the node simulation path parameters.

[0103] The government affair intelligent management system adjusts the execution progress of the process entity node according to the node simulation path parameters, and the formula is as follows:

[0104]

[0105] wherein, is the execution progress, S is the standard value, and all process entity nodes are the same. The execution progress calculated by the image features for each process entity node can better generate an execution progress for each process entity node that is more in line with the current scene, so that the completion difficulty of each process entity node can be highlighted in the subsequent ant algorithm, and a process entity node that is more in line with the government request can be determined.

[0106] Referring to Figure 4 The application provides an embodiment of a method for adjusting historical use priority, comprising:

[0107] 401、The government affair intelligent management system determines the running historical information of each process entity node from the primary knowledge graph;

[0108] 402、The government affair intelligent management system generates the use rate parameter of each process entity node according to the running historical information of each process entity node;

[0109] 403、The government affair intelligent management system adjusts the historical use priority of each process entity node according to the use rate parameter.

[0110] In this embodiment, the government affair intelligent management system determines the running historical information of each process entity node from the primary knowledge graph, and the running historical information of each process entity node can be found through the primary knowledge graph. Then, the applicable frequency of each process entity node is determined according to the running historical information. The higher the applicable frequency is, the greater the use rate parameter of the process entity node is. At this time, only the historical use priority of the process entity node needs to be adjusted according to the size of the use rate parameter, and the government affair intelligent management system can adjust the historical use priority of each process entity node according to the use rate parameter. The formula is as follows:

[0111]

[0112] Wherein, is the historical use priority, is the use rate parameter, which is a value greater than 0 and less than 1, is the initial use priority before adjustment, which is usually set to 1. The historical use priority adjustment method of this embodiment can combine and calculate the applicable data of the process entity node in the knowledge graph of the node, so that the ant colony process path model will be more consistent with the real scene and can determine the process entity node that is more consistent with the government affair request.

[0113] Referring to Figure 5 The application provides an embodiment of a method for selecting a sub-layer knowledge graph, comprising:

[0114] 501、The government affair intelligent management system determines the upper reference data for constructing the primary knowledge graph according to the first target ant colony process path;

[0115] 502、The government affair intelligent management system determines the lower reference data in the primary knowledge graph according to the upper reference data and the government affair area information of the government affair request;

[0116] 503、The government affair intelligent management system selects the sub-layer knowledge graph with the largest correlation degree according to the lower-level reference data.

[0117] In this embodiment, the government affair intelligent management system determines the upper-level reference data for constructing the initial-layer knowledge graph according to the first target ant colony process path, that is, the government affair intelligent management system finds the relevant policy files and other data for constructing the process path from the initial-layer knowledge graph according to the first target ant colony process path, and then determines the government affair region information according to the government affair request, that is, determines the service area of the government affair request, and then finds the lower-level reference data corresponding to the government affair request in the reference files published by the region itself according to the obtained upper-level reference data, and selects the sub-layer knowledge graph with the largest correlation degree according to the lower-level reference data, that is, determines the sub-layer knowledge graph constructed by using the files, and selects the sub-layer knowledge graph with the highest correlation degree, and if there is a knowledge graph constructed by using part or all of the lower-level reference data in the many sub-layer knowledge graphs of the region, the sub-layer knowledge graph with the largest correlation degree is selected, so as to improve the accuracy of subsequent services.

[0118] Please refer to Figure 6 Another embodiment of the method for determining the process entity node provided in the present application comprises the following steps:

[0119] 601、The government affair intelligent management system performs semantic analysis on the text information in the government affair request, and determines a plurality of initial entity processing nodes from the initial-layer knowledge graph;

[0120] 602、The government affair intelligent management system performs same-level node expansion processing according to the initial entity processing node;

[0121] 603、The government affair intelligent management system performs one-time process entity node expansion according to the initial entity processing node, determines the next-level process entity node, and repeatedly performs process entity node expansion on the process entity node to generate a process entity node set;

[0122] 604、The government affair intelligent management system combines the plurality of initial entity processing nodes and the process entity node set to generate a plurality of process entity nodes.

[0123] In this embodiment, the government affair intelligent management system performs semantic analysis on the text information in the government affair request, and then determines a plurality of initial entity processing nodes from the primary knowledge graph according to the keywords obtained from the semantic analysis result. Then, the government affair intelligent management system performs sibling node expansion processing according to the initial entity processing nodes, that is, analyzes the initial nodes, judges the existence of the sibling nodes with similar identities, and determines the initial entity processing nodes. Then, the government affair intelligent management system performs a process entity node expansion according to the initial entity processing nodes, determines the next level process entity nodes, and repeatedly performs the process node expansion on the process entity nodes to generate a process entity node set. That is, the process network is constructed for the initial entity processing nodes to determine the government affair process network composed of a plurality of nodes. All the nodes in the government affair process network are integrated, and the government affair intelligent management system combines the plurality of initial entity processing nodes and the process entity node set to generate a plurality of process entity nodes.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0126] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0127] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0128] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

Claims

1. A government affair intelligent management system based on a knowledge graph, characterized in that, The government affair intelligent management system determines a plurality of process entity nodes in the primary knowledge graph according to text information in the government affair request; The government affair intelligent management system constructs an ant colony process path model according to a process sequence of the plurality of process entity nodes, and there are a plurality of process paths composed of the plurality of process entity nodes in the ant colony process path model; The government affair intelligent management system determines a corresponding process entity node of each image information in the government affair request in the ant colony process path model; The government affair intelligent management system determines a corresponding process entity node of each image information in the government affair request in the ant colony process path model, comprising: The government affair intelligent management system determines an attachment type label of the image information, determines a material demand type label of each process entity node according to the primary knowledge graph, each process entity node comprises at least one material demand type label, and matches the attachment type label and the material demand type label, so that each image information is matched to the corresponding process entity node in the ant colony process path model; The government affair intelligent management system extracts image features in the image information, generates an execution progress of a corresponding process entity node through the image features, and determines the completeness of the required materials in each process entity node through the execution progress of the process entity node generated by analyzing the image features. The government affair intelligent management system calculates a historical use priority of each process entity node; The government affair intelligent management system assigns a priority to each process entity node according to an ant colony algorithm, an execution progress and a historical use priority, determines a first target ant colony process path from the ant colony process path model, and the sum of the priority assignments of all process entity nodes in the first target ant colony process path is higher than that of other process paths; The government affair intelligent management system selects a sub-layer knowledge graph according to the first target ant colony process path and the government affair request; The government affair intelligent management system generates a new ant colony process path model according to the sub-layer knowledge graph and the government affair request, assigns a priority to a process entity node in the ant colony process path model, and generates a second target ant colony process path; The government affair intelligent management system processes the government affair request according to the second target ant colony process path. The government affair intelligent management system extracts image features in the image information, generates an execution progress of a corresponding process entity node through the image features, comprising:

2. The government intelligent management system of claim 1, wherein, The government affair intelligent management system determines a verification feature recognition model and reference verification data according to the primary knowledge graph and the material demand type label; The government affair intelligent management system analyzes image features in the image information and the reference verification data through the verification feature recognition model, and generates a verification result for all image information in each process entity node. ​ The government affair intelligent management system generates a node simulation path parameter for each process entity node according to all verification results in each process entity node; The government affair intelligent management system adjusts the execution progress of the process entity node according to the node simulation path parameter.

3. The government intelligent management system of claim 1, wherein, The government affair intelligent management system calculates the historical use priority of each process entity node, including: The government affair intelligent management system determines the running history information of each process entity node from the primary knowledge graph; The government affair intelligent management system generates a use rate parameter for each process entity node according to the running history information of each process entity node; The government affair intelligent management system adjusts the historical use priority of each process entity node according to the use rate parameter.

4. The government intelligence management system according to any one of claims 1 to 3, characterized by, The government affair intelligent management system selects a sub-layer knowledge graph according to the first target ant colony process path and the government affair request, including: The government affair intelligent management system determines the superior reference data for constructing the primary knowledge graph according to the first target ant colony process path; The government affair intelligent management system determines the inferior reference data in the primary knowledge graph according to the superior reference data and the government affair area information of the government affair request; The government affair intelligent management system selects a sub-layer knowledge graph with the largest correlation degree according to the inferior reference data.

5. The government intelligence management system according to any one of claims 1 to 3, wherein, The government affair intelligent management system determines a plurality of process entity nodes in the primary knowledge graph according to the text information in the government affair request, including: The government affair intelligent management system performs semantic analysis on the text information in the government affair request, and determines a plurality of initial entity processing nodes from the primary knowledge graph; The government affair intelligent management system performs same-level node expansion processing according to the initial entity processing nodes; The government affair intelligent management system performs one-time process entity node expansion according to the initial entity processing nodes, determines the next level process entity node, and repeatedly performs process entity node expansion on the process entity node to generate a process entity node set; The government affair intelligent management system combines the plurality of initial entity processing nodes and the process entity node set to generate a plurality of process entity nodes.

Images