A method, device, electronic device and storage medium for querying tax preference information

Abstract

The present invention provides a method, apparatus, electronic device and storage medium for querying tax preference information, which relates to the field of tax information processing. The method includes: obtaining a tax preference document and extracting a taxpaying entity and other characteristic information from the tax preference document; establishing an association relationship between the taxpaying entity and the other characteristic information, and converting the taxpaying entity and the other characteristic information into a radial graph centered on the taxpaying entity according to the association relationship; when receiving a target taxpaying entity input by a user, outputting a target radial graph corresponding to the target taxpaying entity to provide a tax preference information query service by using the target radial graph; being able to extract a tax subject and other characteristic information from the tax preference document and convert them into a visual radial graph, so that the user can use the graph to query tax preference information, effectively coping with problems such as large scale of tax preference documents, fragmented knowledge and loose organizational structure, and further effectively improving the convenience for users to understand tax preference policies.

Description

Technical Field

[0001] The present invention relates to the field of tax information processing, and particularly to a method, device, electronic device and storage medium for querying tax preference information. Background Art

[0002] With the exponential growth of tax preference policies, a large number of tax preference documents come from different channels, and the preferential contents and the targeted preferential objects are also intricate. At the same time, driven by the trend of the Internet, data presents a large-scale, diversified and loosely structured form, posing challenges to taxpayers in obtaining effective tax information and enjoying preferential policies in real time. On the other hand, at present, there are still many taxpayers at risk of fragmented knowledge of tax preference policies. Many policies are not deeply understood, and many preferential policies are often only publicized when they are introduced, but no special publicity channels are held. Therefore, many taxpayers fail to enjoy the preferential policies that they should enjoy, while those who should not enjoy the preferential policies want to apply for them. This not only causes trouble to the taxpayers themselves, but also brings unnecessary trouble to local tax authorities, making it impossible for tax preference policies to be well popularized among the public and unable to truly become a "weapon" for the public to reduce and exempt preferences.

[0003] Therefore, how to propose an effective method for organizing and classifying tax preference documents to effectively address problems such as large-scale, fragmented knowledge and loose organizational structure of tax preference documents in the Internet is a technical problem that those skilled in the art need to face. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device, electronic device and storage medium for querying tax preference information, which can extract feature information from tax preference documents and convert the latter into a visual radial graph to improve the convenience of users in querying tax preference information by using the radial graph.

[0005] To solve the above technical problems, the present invention provides a method for querying tax preference information, including:

[0006] Obtain tax preference documents, and extract taxpaying entities and other feature information from the tax preference documents;

[0007] Establish an association relationship between the taxpaying entity and the other feature information, and convert the taxpaying entity and the other feature information into a radial graph centered on the taxpaying entity according to the association relationship;

[0008] When receiving a target taxpaying entity input by a user, output the target radial graph corresponding to the target taxpaying entity to provide a tax preference information query service by using the target radial graph.

[0009] Optionally, after extracting the taxpayer entity and other feature information from the tax preference document, it further includes:

[0010] Calculating the similarity between the taxpayer entities;

[0011] Correspondingly, after receiving the target taxpayer entity input by the user, it further includes:

[0012] Querying similar taxpayer entities whose similarity with the target taxpayer entity is greater than a preset threshold, and outputting the radial graph corresponding to the similar taxpayer entities.

[0013] Optionally, the calculating the similarity between the taxpayer entities includes:

[0014] Calculating the edit distance between the names of the taxpayer entities, and calculating the similarity by using the length of the names and the edit distance.

[0015] Optionally, the obtaining the tax preference document includes:

[0016] Obtaining the tax preference document in a specified website by using a preset crawler program.

[0017] Optionally, the extracting the taxpayer entity and other feature information from the tax preference document includes:

[0018] Extracting the taxpayer entity and the other feature information from the tax preference document by using regular expressions and / or a neural network model.

[0019] Optionally, after establishing an association relationship between the taxpayer entity and the other feature information, it further includes:

[0020] Saving the association relationship to a relational database.

[0021] Optionally, the other feature information includes tax types and clauses. The converting the taxpayer entity and the other feature information into a radial graph centered on the taxpayer entity according to the association relationship includes:

[0022] Querying the target tax type corresponding to the taxpayer entity and the target clauses associated with the target tax type according to the association relationship, and counting the number of target clauses corresponding to each target tax type;

[0023] Generating a central node for the taxpayer entity by using a preset central position and a first preset radius;

[0024] Determine the positions of the first-degree nodes of the target tax type around the central node by using the number of target clauses and the preset central position, generate the first-degree nodes by using the positions of the first-degree nodes and the second preset radius, and connect the first-degree nodes and the central node;

[0025] Determine the positions of the second-degree nodes of the target clause around the corresponding first-degree nodes of the target clause by using the positions of the first-degree nodes, generate the second-degree nodes by using the positions of the second-degree nodes and the third preset radius, and connect the second-degree nodes and the corresponding first-degree nodes to obtain the radial graph.

[0026] The present invention also provides a tax preference information query device, including:

[0027] A feature extraction module, configured to obtain a tax preference document and extract a tax-paying entity and other feature information from the tax preference document;

[0028] A radial graph generation module, configured to establish an association relationship between the tax-paying entity and the other feature information, and convert the tax-paying entity and the other feature information into a radial graph centered on the tax-paying entity according to the association relationship;

[0029] A query service module, configured to output the target radial graph corresponding to the target tax-paying entity when receiving a target tax-paying entity input by a user, so as to provide a tax preference information query service by using the target radial graph.

[0030] The present invention also provides an electronic device, including:

[0031] A memory, configured to store a computer program;

[0032] A processor, configured to implement the tax preference information query method as described above when executing the computer program.

[0033] The present invention also provides a storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the tax preference information query method as described above is implemented.

[0034] The present invention provides a method for querying tax preference information, including: obtaining a tax preference document, and extracting a taxpaying entity and other characteristic information from the tax preference document; establishing an association relationship between the taxpaying entity and the other characteristic information, and converting the taxpaying entity and the other characteristic information into a radial graph centered on the taxpaying entity according to the association relationship; when a target taxpaying entity input by a user is received, outputting a target radial graph corresponding to the target taxpaying entity, so as to provide a tax preference information query service by using the target radial graph.

[0035] It can be seen that the present invention first performs feature extraction on the obtained tax preference document, extracts important taxpaying entity information and other characteristic information in the document to refine the important content in the document; at the same time, the present invention also establishes an association relationship for the extracted taxpaying entity and other characteristic information to clearly mark that these information come from the same document, that is, there is a significant association relationship between each other; further, the present invention will convert the taxpaying entity and other characteristic information into a target radial graph centered on the taxpaying entity according to the previously obtained association relationship, so as to convert the complex and lengthy document content into a clear and visible visualization chart, and clearly mark the connection between the taxpaying entity and other important content in the tax preference document, so that users can understand the specific content of the tax preference policy; finally, when the present invention receives a target taxpaying entity input by a user, it can directly output the target radial graph corresponding to the entity to the user, so that the user can use the graph to query tax preference information, which can effectively cope with problems such as large scale, fragmented knowledge, and loose organizational structure of tax preference documents on the Internet, and further effectively improve the convenience for users to understand the tax preference policy. The present invention also provides a tax preference information query device, an electronic device and a storage medium, which have the above beneficial effects. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0037] Figure 1 It is a flowchart of a method for querying tax preference information provided by an embodiment of the present invention;

[0038] Figure 2 It is a schematic diagram of a radial graph provided by an embodiment of the present invention;

[0039] Figure 3 It is a structural block diagram of a tax preference information query device provided by an embodiment of the present invention. Specific Embodiments

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0041] In the related art, tax preference documents have problems such as large scale, fragmented knowledge, and loose organizational structure, which are not conducive to taxpayers' timely access to and understanding of tax preference policies and are likely to cause trouble to taxpayers. In view of this, the present invention provides a method for querying tax preference information, which can extract characteristic information from tax preference documents and convert the latter into a visual radial diagram to improve the convenience of users' querying tax preference information. Please refer to Figure 1 , Figure 1 which is a flowchart of a method for querying tax preference information provided by an embodiment of the present invention. The method may include:

[0042] S101. Obtain a tax preference document and extract the taxpaying entity and other characteristic information from the tax preference document.

[0043] A tax preference document is a document containing various tax preference policy information, such as it may include a taxpaying entity, tax types and clause contents related to the taxpaying entity, etc. In the embodiments of the present invention, the taxpaying entity may be an individual or an enterprise, and of course, it may also involve specific occupations or enterprise types. For example, a specific individual taxpaying entity may be a teacher. In addition, the other characteristic information refers to tax preference information related to the taxpaying entity, such as the above-mentioned tax types and clause contents. The embodiments of the present invention do not limit the specific other characteristic information. Besides the above two types of information, it may further include a title, document number, exemption method, exemption type, tax type, policy type, time, etc., which can be selected according to the contents covered in the specific tax preference document and actual application requirements.

[0044] Furthermore, it should be noted that the embodiments of the present invention do not limit the method for obtaining a tax preference document. For example, it can be downloaded manually. Of course, to improve the acquisition efficiency, a preset crawler program can also be used to obtain the document on a specified website (such as the website of the State Taxation Administration or the websites of local tax branches), where the crawler program is a program or script that automatically crawls information on the World Wide Web according to certain rules. The embodiments of the present invention also do not limit the specific crawler program, and relevant technologies of the Python language and crawler program frameworks can be referred to.

[0045] In a possible scenario, obtaining tax preference documents may include:

[0046] Step 11: Use a preset crawler program to obtain tax preference documents from a specified website.

[0047] Furthermore, the embodiments of the present invention do not limit how to extract the taxpayer entity and other characteristic information from the tax preference documents. Since the documents usually have significant structural characteristics, regular expressions can be used for extracting characteristic information; of course, for the characteristic information in the documents that does not have significant structural characteristics, a pre-trained neural network model can also be used for extraction. It should be noted that the embodiments of the present invention do not limit the specific regular expressions and neural network models, which can be set with reference to related technologies and combined with actual application requirements.

[0048] In a possible scenario, extracting the taxpayer entity and other characteristic information from the tax preference documents may include:

[0049] Step 21: Use regular expressions and / or a neural network model to extract the taxpayer entity and other characteristic information from the tax preference documents.

[0050] S102: Establish an association relationship between the taxpayer entity and other characteristic information, and convert the taxpayer entity and other characteristic information into a radial graph centered on the taxpayer entity according to the association relationship.

[0051] Since the taxpayer entity and other characteristic information are extracted from the same tax preference document and have a strong correlation, the embodiments of the present invention can directly establish an association relationship for the above information. Further, after the relationship is established, the embodiments of the present invention can further use this relationship to convert the taxpayer entity and other characteristic information into a radial graph centered on the taxpayer entity, where the radial graph can use a radial layout to arrange information with association relationships and hierarchical relationships, which can facilitate users to query information associated with the taxpayer entity. Hereinafter, the embodiments of the present invention will introduce the generation process of the radial graph with specific characteristic information. Since the tax types and clauses are the most relevant information to the taxpayer entity, in the embodiments of the present invention, the taxpayer entity, tax types, and clauses can be used to generate the radial graph.

[0052] In a possible scenario, other characteristic information includes tax types and clauses. Converting the taxpayer entity and other characteristic information into a radial graph centered on the taxpayer entity according to the association relationship may include:

[0053] Step 31: Query the target tax types corresponding to the taxpayer entity and the target clauses associated with the target tax types according to the association relationship, and count the number of target clauses corresponding to each target tax type.

[0054] Step 32: Generate a central node for the taxpayer using the preset central position and the first preset radius.

[0055] In the embodiments of the present invention, taxpayers, tax types, and terms can be represented by circular nodes of different sizes. For the central node, the preset central position refers to the position of the center of the central node in the display area. The embodiments of the present invention do not limit the specific values of the preset central position and the first preset radius, which can be selected according to actual application requirements. Specifically, the central node can be represented in the following way:

[0056] P e :(x e ,y e ),d e =R1

[0057] where e represents the central node, P e represents the center of the central node, x e and y e respectively represent the abscissa and ordinate of the center coordinate of the central node, d e represents the radius of the central node, and R1 represents the first preset radius.

[0058] Step 33: Use the number of target terms and the preset central position to determine the positions of the first-degree nodes of the target tax type around the central node, generate the first-degree nodes using the positions of the first-degree nodes and the second preset radius, and connect the first-degree nodes and the central node.

[0059] In the embodiments of the present invention, the first-degree nodes are the nodes directly connected to the central node and are used to represent the target tax types; the second-degree nodes are the nodes directly connected to the first-degree nodes and are used to represent the target terms. It can be understood that since the number of target terms corresponding to different target tax types is different, that is, the number of second-degree nodes to be connected to each first-degree node is different, in order to avoid mutual interference, in the embodiments of the present invention, the positions of the first-degree nodes corresponding to each target tax type around the central node will be determined according to the number of target terms corresponding to each target tax type. Specifically, the first-degree nodes can be represented in the following way:

[0060]

[0061] where t represents the first-degree node, represents the center of the first-degree node of the i-th target tax type, and respectively represent the abscissa and ordinate of the center of the i-th first-degree node, d tR1 represents the radius of the first-degree node, and R2 represents the second preset radius. It should be noted that the embodiments of the present invention do not limit the specific value of the second preset radius, which can be set according to actual application requirements. Further, the position of the first-degree node can be determined in the following manner:

[0062]

[0063]

[0064]

[0065] where k represents the unit offset angle of the first-degree node relative to the central node, and n t represents the number of target tax types, and α is a preset parameter for adjusting the distance ratio. It can be seen that the distance between the first-degree node and the central node is positively correlated with the number of second-degree nodes (the number of target clauses) corresponding to this node. Of course, in order to avoid the central node and the first-degree node from overlapping with each other, the radii of the two nodes can be further restricted by the following conditions:

[0066]

[0067] where min(·) represents the minimum value function.

[0068] Step 34: Using the position of the first-degree node, determine the position of the second-degree node of the target clause around the first-degree node corresponding to the target clause. Generate the second-degree node using the position of the second-degree node and the third preset radius, and connect the second-degree node and the first-degree node corresponding to the second-degree node to obtain a radial graph.

[0069] The second-degree node can be represented in the following manner:

[0070]

[0071] where q represents the second-degree node, represents the center of the circle of the second-degree node of the jth target clause, and represent the abscissa and ordinate of the center of the circle of the jth second-degree node respectively, and d q represents the radius of the second-degree node, and R3 represents the third preset radius. It should be noted that the embodiments of the present invention do not limit the specific value of the third preset radius, which can be set according to actual application requirements. Specifically, the position of the second-degree node can be determined in the following manner:

[0072]

[0073]

[0074]

[0075]

[0076] Among them, u represents the unit offset angle of the second-degree node relative to the first-degree node. represents the number of target clauses corresponding to the i-th target tax type. For ease of understanding, please refer to Figure 2 , Figure 2 FIG.

[0077] Further, for the convenience of querying the taxpaying entity and other characteristic information, after establishing the association relationship between the taxpaying entity and other characteristic information, the association relationship can be saved to a relational database. The embodiments of the present invention do not limit the specific relational database. For example, the MySQL database can be used to store the association relationship, where MySQL is a commonly used relational database.

[0078] In a possible case, after establishing the association relationship between the taxpaying entity and other characteristic information, it may further include:

[0079] Step 41: Save the association relationship to a relational database.

[0080] S103. When receiving the target taxpaying entity input by the user, output the target radial graph corresponding to the target taxpaying entity, so as to provide a tax preference information query service by using the target radial graph.

[0081] After obtaining the radial graph corresponding to the taxpaying entity, the embodiments of the present invention can use the radial graph to provide a query service for the user, so as to facilitate the user to understand the tax preference policy.

[0082] Based on the above embodiments, the present invention first extracts features from the obtained tax preference documents, extracts important taxpayer information and other feature information in the documents to refine the important content in the documents. At the same time, the present invention also establishes an association relationship for the extracted taxpayer and other feature information to clearly mark that these information come from the same document, that is, there is a significant association relationship between each other. Further, the present invention will convert the taxpayer and other feature information into a target radial graph centered on the taxpayer according to the previously obtained association relationship, so as to convert the complex and lengthy document content into a clear visual chart, and clearly mark the connection between the taxpayer and other important content in the tax preference document, so that users can understand the specific content of the tax preference policy. Finally, when the present invention receives the target taxpayer input by the user, it can directly output the target radial graph corresponding to the taxpayer to the user, so that the user can use the graph to query tax preference information, which can effectively address the problems of large-scale tax preference documents, fragmented knowledge, and loose organizational structure in the Internet, and then can effectively improve the convenience for users to understand the tax preference policy.

[0083] Based on the above embodiments, to facilitate users to understand the tax preference policies of other taxpayers related to the taxpayer they input, the present invention can also additionally calculate the similarity between taxpayers. Further, after outputting the radial graph of the target taxpayer required by the user, it can also output the radial graphs of other taxpayers similar to the target taxpayer for the user to consult. In a possible situation, after extracting the taxpayer and other feature information from the tax preference document, it may further include:

[0084] S201. Calculate the similarity between taxpayers.

[0085] It should be noted that the embodiments of the present invention do not limit the calculation method of the similarity between taxpayers. For example, the similarity between the tax preference clauses of each taxpayer can be calculated. Of course, for the convenience of calculation, the similarity between taxpayer strings can also be directly calculated. The embodiments of the present invention do not limit the specific method of calculating the similarity between taxpayer strings. For example, the edit distance (Levenshtein Distance) between taxpayer names can be calculated, and the similarity between taxpayer names can be calculated using the edit distance. The edit distance is a kind of feature information to measure the similarity between two strings. The smaller the edit distance, the higher the similarity between the two strings.

[0086] In a possible situation, calculating the similarity between taxpayers may include:

[0087] Step 51. Calculate the edit distance between the names of taxpayers, and calculate the similarity using the length of the names and the edit distance.

[0088] It should be noted that the embodiments of the present invention do not limit the calculation method of the edit distance, and related technologies of the edit distance can be referred to. Specifically, after obtaining the edit distance, the similarity between the names of taxpaying entities can be calculated in the following manner:

[0089] Similarity = (Max(x, y) - Levenshtein) / Max(x, y)

[0090] Where Similarity represents the similarity, x and y respectively represent the names of two taxpaying entities, Max(·) represents the maximum value function, which is used to find the maximum value of the lengths of the two strings x and y, and Levenshtein represents the edit distance between the two strings x and y.

[0091] Correspondingly, after receiving the target taxpaying entity input by the user, it may further include:

[0092] S202. Query similar taxpaying entities whose similarity to the target taxpaying entity is greater than a preset threshold, and output a radial graph corresponding to the similar taxpaying entity.

[0093] It should be noted that the embodiments of the present invention do not limit the specific value of the preset threshold, which can be set according to actual application requirements.

[0094] Based on the above embodiments, the present invention can also additionally calculate the similarity between taxpaying entities. Furthermore, after outputting the radial graph of the target taxpaying entity required by the user, it can also output the radial graphs of other taxpaying entities similar to the target taxpaying entity, thereby effectively improving the user experience.

[0095] Next, a tax preference information query device, an electronic device, and a storage medium provided by the embodiments of the present invention will be introduced. The tax preference information query device, the electronic device, and the storage medium described below can be correspondingly referred to the tax preference information query method described above.

[0096] Please refer to Figure 3 , Figure 3 , which is the structural block diagram of a tax preference information query device provided by the embodiments of the present invention. The device may include:

[0097] A feature extraction module 301, configured to obtain a tax preference document and extract taxpaying entities and other feature information from the tax preference document;

[0098] A radial graph generation module 302, configured to establish an association relationship between taxpaying entities and other feature information, and convert the taxpaying entities and other feature information into a radial graph centered on the taxpaying entity according to the association relationship;

[0099] The query service module 303 is configured to output a target radial diagram corresponding to the target taxpayer when receiving the target taxpayer input by the user, so as to provide a tax preference information query service by using the target radial diagram.

[0100] Optionally, the device may further include:

[0101] A similarity calculation module, configured to calculate the similarity between taxpayers;

[0102] Correspondingly, the query service module 303 may further be configured to:

[0103] Query similar taxpayers whose similarity to the target taxpayer is greater than a preset threshold, and output the radial diagrams corresponding to the similar taxpayers.

[0104] Optionally, the similarity calculation module is specifically configured to:

[0105] Calculate the edit distance between the names of taxpayers, and calculate the similarity by using the length of the names and the edit distance.

[0106] Optionally, the feature extraction module 301 may include:

[0107] A document extraction sub-module, configured to obtain tax preference documents in a specified website by using a preset crawler program.

[0108] Optionally, the feature extraction module 301 may include:

[0109] A feature extraction sub-module, configured to extract taxpayers and other feature information from tax preference documents by using regular expressions and / or neural network models.

[0110] Optionally, the device may further include:

[0111] A saving module, configured to save the association relationship to a relational database.

[0112] Optionally, the other feature information includes tax types and clauses. The radial diagram generation module 302 may include:

[0113] A query sub-module, configured to query the target tax type corresponding to the taxpayer and the target clauses associated with the target tax type according to the association relationship, and count the number of target clauses corresponding to each target tax type;

[0114] A first generation sub-module, configured to generate a central node for the taxpayer by using a preset central position and a first preset radius;

[0115] A second generation sub-module, configured to use the number of target clauses and a preset central position to determine the positions of first-degree nodes of the target tax type around the central node, generate first-degree nodes by using the positions of the first-degree nodes and a second preset radius, and connect the first-degree nodes and the central node;

[0116] A third generation sub-module, configured to use the positions of the first-degree nodes to determine the positions of second-degree nodes of the target clause around the first-degree nodes corresponding to the target clause, generate second-degree nodes by using the positions of the second-degree nodes and a third preset radius, and connect the second-degree nodes and the first-degree nodes corresponding to the second-degree nodes to obtain a radial graph.

[0117] An embodiment of the present invention further provides an electronic device, including:

[0118] A memory, configured to store a computer program;

[0119] A processor, configured to implement the steps of the tax preference information query method as described above when executing the computer program.

[0120] Since the embodiments of the electronic device part correspond to the embodiments of the tax preference information query method part, for the descriptions of the embodiments of the electronic device part, please refer to the descriptions of the embodiments of the tax preference information query method part, which will not be elaborated here.

[0121] An embodiment of the present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the tax preference information query method in any of the above embodiments are implemented.

[0122] Since the embodiments of the storage medium part correspond to the embodiments of the tax preference information query method part, for the descriptions of the embodiments of the storage medium part, please refer to the descriptions of the embodiments of the tax preference information query method part, which will not be elaborated here.

[0123] The various embodiments in the specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions in the method part.

[0124] Those skilled in the art may further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0125] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0126] The above has introduced in detail a method, device, electronic device, and storage medium for querying tax preference information provided by the present invention. Specific examples are used herein to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. A method for querying tax preference information, characterized in that, Including: Obtain tax preference documents, and extract the taxpayer entity and other characteristic information from the tax preference documents; Establish an association relationship between the taxpayer entity and the other characteristic information, and convert the taxpayer entity and the other characteristic information into a radial graph centered on the taxpayer entity according to the association relationship; When receiving the target taxpayer entity input by the user, output the target radial graph corresponding to the target taxpayer entity to provide a tax preference information query service by using the target radial graph; Wherein, the other characteristic information includes tax types and clauses, and the converting the taxpayer entity and the other characteristic information into a radial graph centered on the taxpayer entity according to the association relationship includes: Query the target tax types corresponding to the taxpayer entity and the target clauses associated with the target tax types according to the association relationship, and count the number of target clauses corresponding to each target tax type; Generate a central node for the taxpayer entity by using a preset central position and a first preset radius; Determine the position of the first-degree nodes of the target tax types around the central node by using the number of the target clauses and the preset central position, generate the first-degree nodes by using the position of the first-degree nodes and a second preset radius, and connect the first-degree nodes and the central node; Determine the position of the second-degree nodes of the target clauses around the first-degree nodes corresponding to the target clauses by using the position of the first-degree nodes, generate the second-degree nodes by using the position of the second-degree nodes and a third preset radius, and connect the second-degree nodes and the first-degree nodes corresponding to the second-degree nodes to obtain the radial graph.

2. The tax preference information query method according to claim 1, wherein After extracting the taxpayer entity and other characteristic information from the tax preference documents, it further includes: Calculate the similarity between the taxpayer entities; Correspondingly, after receiving the target taxpayer entity input by the user, it further includes: Query the similar taxpayer entities whose similarity with the target taxpayer entity is greater than a preset threshold, and output the radial graphs corresponding to the similar taxpayer entities.

3. The method for querying tax preference information according to claim 2, wherein The calculating the similarity between the taxpayer entities includes: Calculate the edit distance between the names of the taxpayer entities, and calculate the similarity by using the length of the names and the edit distance.

4. The method for querying tax preference information according to claim 1, wherein The obtaining the tax preference documents includes: Obtain the tax preference documents in a specified website by using a preset crawler program.

5. The method for querying tax preference information according to claim 1, wherein The extracting the taxpayer entity and other characteristic information from the tax preference documents includes: Extract the taxpayer entity and the other characteristic information from the tax preference documents by using regular expressions and / or neural network models.

6. The tax preference information query method according to claim 1, wherein After establishing the association relationship between the taxpayer entity and the other characteristic information, it further includes: Save the association relationship to a relational database.

7. A tax preference information query device, characterized in that Including: A feature extraction module, configured to obtain tax preference documents, and extract the taxpayer entity and other characteristic information from the tax preference documents; A radial graph generation module, configured to establish an association relationship between the taxpayer entity and the other characteristic information, and convert the taxpayer entity and the other characteristic information into a radial graph centered on the taxpayer entity according to the association relationship; A query service module, which is configured to output a target radial diagram corresponding to the target tax subject when receiving the target tax subject input by the user, so as to provide a tax preference information query service by using the target radial diagram; Wherein, the other feature information includes tax types and terms. Correspondingly, the radial diagram generation module includes: A query sub-module, which is configured to query the target tax type corresponding to the tax subject and the target terms associated with the target tax type according to the association relationship, and count the number of target terms corresponding to each target tax type; A first generation sub-module, which is configured to generate a central node for the tax subject by using a preset central position and a first preset radius; A second generation sub-module, which is configured to determine the position of the first-degree nodes of the target tax type around the central node by using the number of target terms and the preset central position, generate first-degree nodes by using the position of the first-degree nodes and a second preset radius, and connect the first-degree nodes and the central node; A third generation sub-module, which is configured to determine the position of the second-degree nodes of the target terms around the first-degree nodes corresponding to the target terms by using the position of the first-degree nodes, generate second-degree nodes by using the position of the second-degree nodes and a third preset radius, and connect the second-degree nodes and the first-degree nodes corresponding to the second-degree nodes to obtain a radial diagram.

8. An electronic device, characterized in that, Including: A memory, which is configured to store a computer program; A processor, which is configured to implement the tax preference information query method according to any one of claims 1 to 6 when executing the computer program.

9. A storage medium, characterized in that, Computer-executable instructions are stored in the storage medium, and when the computer-executable instructions are loaded and executed by the processor, the tax preference information query method according to any one of claims 1 to 6 is implemented.

Images