Policy matching reverse retrieval method and device based on big data

Abstract

The invention relates to the technical field of policy information services, in particular to a policy matching reverse retrieval method based on big data, which comprises the following steps: presetting an industry keyword dictionary, analyzing objective attributes of each target object, extracting keywords, and generating a first keyword frequency table corresponding to the target object; carrying out statistics on keyword frequencies corresponding to all objects in each industry, and generating a second keyword frequency table corresponding to the industry; and performing policy matching in response to the absence of the object, performing keyword retrieval according to the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located, and generating a policy matching result of the object. By applying the method, enterprise objective attribute information and industry group tendency can be fully utilized, the accuracy and individuation degree of policy matching are improved, and policy information beneficial to growth is pushed to enterprises.

Description

Technical Field

[0001] This application relates to the technical field of policy information services, and particularly to a policy matching reverse retrieval method based on big data. Background Art

[0002] With the advent of the information age, government departments have released a large number of support policies on public service platforms and relevant websites to support the technological R & D innovation of enterprises. However, due to different policy releasing departments, times and sites, policy information is scattered, and enterprise users need to spend a lot of time searching and analyzing, with low efficiency.

[0003] Currently, most policy matching systems retrieve based on keywords input by users, and the quality of the results depends on the quality of the users' input. There are certain problems with this matching method. In many cases, the results that users really want cannot be obtained because it overly relies on the description level of users, does not fully consider the objective attributes of users, and does not effectively utilize the group tendencies of similar users.

[0004] In view of this, how to provide a policy matching reverse retrieval method based on big data to improve the matching quality, reduce the dependence on the quality of users' input, make full use of the tendencies of similar user groups, and quickly collect policy information helpful for the growth of enterprises for enterprises has become an urgent technical problem to be solved currently. Summary of the Invention

[0005] Embodiments of this application provide a policy matching reverse retrieval method based on big data, a policy matching reverse retrieval device based on big data, a computer device, and a computer storage medium, which are used to solve the problems that users can quickly collect policy information helpful for the growth of their own enterprises, the policy matching quality does not strongly depend on the quality of users' input, analyze similar user groups, and the group tendencies can be reflected in the policy matching results.

[0006] In the first aspect of the embodiments of this application, a policy matching reverse retrieval method based on big data is provided, including:

[0007] Preset an industry keyword dictionary, analyze the objective attributes of each target object, extract keywords, and generate a first keyword frequency table corresponding to the target object;

[0008] Statistically calculate the keyword frequencies corresponding to all objects within each industry, and generate a second keyword frequency table corresponding to the industry;

[0009] In response to a policy match for which there is no object, perform keyword retrieval according to the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located, and generate a policy matching result for the object.

[0010] In the second aspect of the embodiments of the present application, a policy matching reverse retrieval device based on big data is provided, including:

[0011] A first generation module, configured to preset an industry keyword dictionary, analyze the objective attributes of each target object, refine keywords, and generate a first keyword frequency table corresponding to the target object;

[0012] A second generation module, configured to count the keyword frequencies corresponding to all objects in each industry, and generate a second keyword frequency table corresponding to the industry;

[0013] A third generation module, configured to respond to the situation where there is no object for policy matching, perform keyword retrieval according to the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located, and generate a policy matching result for the object.

[0014] In the third aspect of the embodiments of the present application, a computing device is provided, including:

[0015] A memory and a processor;

[0016] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned policy matching reverse retrieval method based on big data are implemented.

[0017] According to the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the above-mentioned policy matching reverse retrieval method based on big data are implemented.

[0018] The present application provides a policy matching reverse retrieval method based on big data, including: presetting an industry keyword dictionary, analyzing the objective attributes of each target object, refining keywords, and generating a first keyword frequency table corresponding to the target object; counting the keyword frequencies corresponding to all objects in each industry, and generating a second keyword frequency table corresponding to the industry; responding to the situation where there is no object for policy matching, performing keyword retrieval according to the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located, and generating a policy matching result for the object.

[0019] Applying the policy matching reverse retrieval method based on big data provided by the embodiments of the present application has the following

[0020] Beneficial effects:

[0021] 1. Make full use of the objective attribute information of enterprises, such as enterprise name, industry classification, company profile, company business scope, etc., and form an enterprise keyword frequency table through keyword extraction and frequency statistics, reducing the dependence on the quality of user input and improving the accuracy of policy matching;

[0022] 2. Conduct keyword frequency analysis on enterprises in the same industry to form an industry keyword frequency table, which can effectively reflect the tendencies of similar user groups and provide personalized policy matching services for different groups;

[0023] 3. Through keyword retrieval and matching between the enterprise keyword frequency table and the keyword frequency table of the affiliated industry, it is possible to quickly and efficiently push policy information conducive to the growth of enterprises to improve the intelligent recommendation ability of policy information;

[0024] 4. The enterprise keyword frequency table can be dynamically updated to timely reflect the development and changes of enterprises and improve the accuracy of policy matching;

[0025] 5. The policy matching method based on the keyword frequency table can fully explore the policy content, improve the in-depth analysis and understanding ability of policy information, and optimize the matching results.

[0026] The above description is only an overview of the technical solution of this application. In order to more clearly understand the technical means of this application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Description of the Drawings

[0027] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered as a limitation of this application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0028] Figure 1 It is a flowchart of a method for reverse retrieval of policy matching based on big data provided by an embodiment of this application;

[0029] Figure 2 It is a flowchart of another method for reverse retrieval of policy matching based on big data provided by an embodiment of this application;

[0030] Figure 3 It is a block diagram of a device for reverse retrieval of policy matching based on big data provided by an embodiment of this application;

[0031] Figure 4 It is a block diagram of a computing device provided by an embodiment of this application. Detailed Embodiments

[0032] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0033] Some of the existing technologies currently provided for solving the problems that users can quickly collect policy information helpful for the growth of their own enterprises, the quality of policy matching is not strong and depends on the quality of user input, and the analysis of similar user groups is carried out, and the group tendency can be reflected in the policy matching results include: On the one hand, it can be an enterprise policy matching method based on label similarity, including steps such as automatically constructing enterprise labels, automatically constructing policy labels, and policy matching based on label similarity. This method can quickly and efficiently obtain policy information and accurately match the policy supply side and demand side, ensure the implementation effect of policies, and improve the quality of government administrative services. However, this patent still has problems such as further mining and screening of keywords, in-depth analysis and understanding of policy information, and personalization and differentiation of policy push; on the other hand, it can be a method and system for matching policies and enterprises based on big data, using big data to collect information released by various government departments, screening and classifying the collected information to determine the information categories of policy information, and at the same time classifying each enterprise to determine the enterprise categories of the enterprises, matching the information categories with the enterprise categories to determine the enterprises that match the policy information, and further pushing the policy information to the matching enterprises. However, this patent still has problems such as intelligent recommendation of policy information, update of enterprise categories, and personalized recommendation of enterprise services.

[0034] However, the existing technologies have the following disadvantages: 1. Policy matching overly relies on the quality of user input, and differences in user description levels will lead to deviations in matching results, and the objective attribute information of enterprises cannot be fully utilized; 2. There is a lack of analysis and utilization of the tendencies of similar user groups, and personalized policy matching services cannot be provided for different groups; 3. The intelligent recommendation ability of policy information is insufficient, and it is difficult to quickly and efficiently push policy information helpful for the growth of enterprises; 4. The enterprise category division lacks a dynamic update mechanism and cannot timely reflect the development and changes of enterprises, affecting the accuracy of policy matching; 5. The in-depth analysis and understanding ability of policy information is limited, and the policy content cannot be fully mined, resulting in poor matching results.

[0035] In the prior art, there are problems such as over - reliance on the quality of user input for policy matching, lack of analysis and utilization of the tendencies of similar user groups, insufficient intelligent recommendation ability of policy information, lack of a dynamic update mechanism for enterprise category division, and limited ability to deeply analyze and understand policy information. Therefore, in order to solve the above problems, the present invention provides a reverse retrieval method for policy matching based on big data.

[0036] See Figure 1 , Figure 1 which is a schematic flowchart of a reverse retrieval method for policy matching based on big data provided by an embodiment of the present application. Specifically, it includes the following steps.

[0037] Step S102: Preset an industry keyword dictionary, analyze the objective attributes of each target object, refine keywords, and generate a first keyword frequency table corresponding to the target object.

[0038] Step S104: Count the keyword frequencies corresponding to all objects within each industry, and generate a second keyword frequency table corresponding to the industry.

[0039] Step S106: In response to the situation that there is no object for policy matching, perform keyword retrieval according to the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located, and generate a policy matching result for the object.

[0040] In another embodiment, the method further includes: in response to the situation that there is an object that matches the policy, update the first keyword frequency table corresponding to the object.

[0041] In the embodiment of the present application, the presetting of the industry keyword dictionary, analyzing the objective attributes of each target object, and refining keywords to generate a first keyword frequency table corresponding to the target object includes: presetting an industry keyword dictionary, analyzing the objective attributes of each target object, and refining the enterprise objective attribute information corresponding to each target object, where the enterprise objective attribute information includes enterprise name, industry division, company profile, and company business scope; according to the preset industry keyword dictionary, refining keywords from the enterprise objective attribute information to generate a first keyword frequency table corresponding to a single target object; and dynamically updating the first keyword frequency table.

[0042] In practical applications, information such as enterprise name, industry division, company profile, and company business scope is extracted from the objective attributes of the enterprise. For example, the above - mentioned information is obtained from channels such as the enterprise's business license and company website.

[0043] According to the preset industry keyword dictionary, extract keywords from the objective attribute information of enterprises to form a keyword frequency table for a single enterprise. The preset industry keyword dictionary can include professional terms in the policy field, industry terms, etc., and keyword extraction can be achieved using natural language processing technology. For example, for an enterprise producing electronic products, extract keywords such as "electronic", "chip", "display screen", etc. from its company profile, and count the frequency of each keyword occurrence to form the keyword frequency table of this enterprise.

[0044] Dynamically update the keyword frequency table of a single enterprise to promptly reflect the development and changes of the enterprise. For example, when an enterprise updates its company profile or business scope, re-extract keywords and update the keyword frequency table.

[0045] In the embodiment of this application, the step of statistically calculating the keyword frequencies corresponding to all objects in each industry to generate the second keyword frequency table corresponding to the industry includes:

[0046] Obtain the first keyword frequency tables corresponding to all objects in the same industry;

[0047] Perform combined statistics on the first keyword frequency tables corresponding to all objects to generate the second keyword frequency table corresponding to the industry.

[0048] In practical applications, collect the keyword frequency tables of all enterprises in the same industry.

[0049] Perform combined statistics on the keyword frequency tables of all enterprises to obtain the keyword frequency table of this industry. For example, for the electronics industry, count the number of occurrences of keywords in the keyword frequency tables of all electronics enterprises to form the keyword frequency table of the electronics industry.

[0050] In the embodiment of this application, the step of, in response to the absence of an object for policy matching, performing keyword retrieval based on the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located to generate the policy matching result of the object includes:

[0051] Based on the first keyword frequency table, perform keyword retrieval on the policy information to generate the first retrieval result;

[0052] Based on the second keyword frequency table, perform keyword retrieval on the policy information to generate the second retrieval result;

[0053] Based on the first retrieval result and the second retrieval result, generate the policy matching result of the object;

[0054] According to the historical query records and feedback information of the target object, adjust the policy matching result to obtain the target policy matching result.

[0055] In practical applications, based on the keyword frequency table of an enterprise, keyword retrieval is performed on policy information to obtain a first retrieval result. For example, the high-frequency keywords in the enterprise keyword frequency table are used as retrieval terms to retrieve relevant policies in the policy database.

[0056] Based on the keyword frequency table of the affiliated industry, keyword retrieval is performed on policy information to obtain a second retrieval result. For example, the high-frequency keywords in the industry keyword frequency table are used as retrieval terms to retrieve relevant policies in the policy database.

[0057] The first retrieval result and the second retrieval result are fused to obtain a final policy matching result. The retrieval results can be sorted and filtered according to indicators such as keyword matching degree and policy relevance.

[0058] According to the historical query records and feedback information of the enterprise, personalized adjustment is performed on the policy matching result. For example, a higher weight is assigned to the policy types frequently queried by the enterprise, and the weight of policies that the enterprise feedbacks as irrelevant is reduced.

[0059] See Figure 2 , Figure 2 which is a schematic flowchart of another method for reverse retrieval of policy matching based on big data provided by an embodiment of the present application.

[0060] Through the above method, the present invention can make full use of the objective attribute information of enterprises and the tendency of the industry group, improve the accuracy and personalization of policy matching, and push policy information helpful for the growth of enterprises.

[0061] Corresponding to the above method embodiment, this specification also provides an embodiment of a device for reverse retrieval of policy matching based on big data. Figure 3 which is a block diagram of a device for reverse retrieval of policy matching based on big data provided by an embodiment of the present application. As Figure 3 shown, it specifically includes the following modules.

[0062] The first generation module 302 is configured to preset an industry keyword dictionary, analyze the objective attributes of each target object, extract keywords, and generate a first keyword frequency table corresponding to the target object;

[0063] The second generation module 304 is configured to count the keyword frequencies corresponding to all objects in each industry and generate a second keyword frequency table corresponding to the industry;

[0064] The third generation module 306 is configured to respond to the situation where there is no object for policy matching, perform keyword retrieval according to the first keyword frequency table corresponding to the object and the second keyword frequency table corresponding to the industry where the object is located, and generate a policy matching result for the object.

[0065] In an alternative embodiment, the device further includes:

[0066] A fourth generation module 308, configured to update the first keyword frequency table corresponding to the object in response to the presence of an object that matches the policy.

[0067] In an alternative embodiment, the first generation module 302 is further configured to:

[0068] Preset an industry keyword dictionary, and by analyzing the objective attributes of each target object, refine the enterprise objective attribute information corresponding to each target object, where the enterprise objective attribute information includes enterprise name, industry classification, company profile, and company business scope;

[0069] According to the preset industry keyword dictionary, refine keywords from the enterprise objective attribute information to generate a first keyword frequency table corresponding to a single target object;

[0070] Dynamically update the first keyword frequency table.

[0071] In an alternative embodiment, the second generation module 304 is further configured to:

[0072] Obtain the first keyword frequency tables corresponding to all objects in the same industry;

[0073] Merge and statistically analyze the first keyword frequency tables corresponding to all objects to generate a second keyword frequency table corresponding to the industry.

[0074] In an alternative embodiment, the third generation module 306 is further configured to:

[0075] Based on the first keyword frequency table, perform keyword retrieval on the policy information to generate a first retrieval result;

[0076] Based on the second keyword frequency table, perform keyword retrieval on the policy information to generate a second retrieval result;

[0077] Based on the first retrieval result and the second retrieval result, generate a policy matching result for the object;

[0078] According to the historical query records and feedback information of the target object, adjust the policy matching result to obtain a target policy matching result.

[0079] Through the above device, the present invention can make full use of enterprise objective attribute information and industry group tendencies to improve the accuracy and personalization of policy matching, and push policy information that is helpful for the growth of enterprises.

[0080] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the big data-based policy matching reverse retrieval device, since it is basically similar to the big data-based policy matching reverse retrieval method embodiment, the description is relatively simple, and reference can be made to the relevant part of the big data-based policy matching reverse retrieval method embodiment for the relevant content.

[0081] Figure 4 This is a structural block diagram of a computing device provided by an embodiment of the present application. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 through a bus 430, and a database 450 is used to store data.

[0082] The computing device 400 further includes an access device 440, which enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC).

[0083] In an embodiment of this specification, the above components of the computing device 400 and Figure 4 other components not shown may also be connected to each other, for example, through a bus. It should be understood that Figure 4 the shown structural block diagram of the computing device is only for illustrative purposes and is not a limitation on the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0084] The computing device 400 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 400 can also be a mobile or stationary server.

[0085] Wherein, the processor 420 is configured to execute the following computer-executable instructions, which when executed by the processor implement the steps of the above-mentioned big data-based policy matching reverse retrieval method.

[0086] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the computing device, since it is basically similar to the embodiment of the big data-based policy matching reverse retrieval method, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the embodiment of the big data-based policy matching reverse retrieval method.

[0087] An embodiment of this specification also provides a computer-readable storage medium, which stores computer-executable instructions that, when executed by a processor, implement the steps of the above-mentioned big data-based policy matching reverse retrieval method.

[0088] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the computer-readable storage medium, since it is basically similar to the embodiment of the big data-based policy matching reverse retrieval method, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the embodiment of the big data-based policy matching reverse retrieval method.

[0089] An embodiment of this specification also provides a computer program, wherein when the computer program is executed on a computer, the computer is made to execute the steps of the above-mentioned big data-based policy matching reverse retrieval method.

[0090] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the computer program embodiment, since it is basically similar to the embodiment of the policy matching reverse retrieval method based on big data, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the embodiment of the policy matching reverse retrieval method based on big data.

[0091] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The computer instructions include computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0093] It should be noted that the above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this specification.

[0094] In the above embodiments, the descriptions of the embodiments have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, according to the content of the embodiments of the present specification, many modifications and changes can be made. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and utilize this specification. This specification is only limited by the claims and their full scope and equivalents.

[0096] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, according to the content of the embodiments of the present specification, many modifications and changes can be made. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and utilize this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A policy matching reverse retrieval method based on big data, characterized in that: include: Preset an industry keyword dictionary, analyze the objective attributes of each target object, extract keywords, and generate a first keyword frequency table corresponding to the target object; Counting the keyword frequencies corresponding to all objects in each industry, and generating a second keyword frequency table corresponding to the industry; In response to the absence of an object for policy matching, a keyword search is performed based on a first keyword frequency table corresponding to the object and a second keyword frequency table corresponding to the industry to which the object belongs, to generate a policy matching result for the object.

2. The method according to claim 1, characterized in that The method further comprises: In response to the existence of an object matching the policy, a first keyword frequency table corresponding to the object is updated.

3. The method according to claim 1, characterized in that The preset industry keyword dictionary analyzes the objective attributes of each target object, extracts keywords, and generates a first keyword frequency table corresponding to the target object, including: Preset industry keyword dictionary, analyze the objective attributes of each target object, and extract the objective attribute information of the enterprise corresponding to each target object, wherein the objective attribute information of the enterprise includes the enterprise name, industry classification, company profile, and company business scope; According to the preset industry keyword dictionary, keyword extraction is performed on the objective attribute information of the enterprise to generate a first keyword frequency table corresponding to a single target object; The first keyword frequency table is dynamically updated.

4. The method according to claim 1, characterized in that: The counting of keyword frequencies corresponding to all objects in each industry to generate a second keyword frequency table corresponding to the industry includes: Obtain the first keyword frequency table corresponding to all objects in the same industry; The first keyword frequency tables corresponding to all objects are combined and counted to generate a second keyword frequency table corresponding to the industry.

5. The method according to claim 1, characterized in that The policy matching for the object does not exist in response to the object, performing keyword search according to a first keyword frequency table corresponding to the object and a second keyword frequency table corresponding to the industry to which the object belongs, and generating a policy matching result for the object, includes: Based on the first keyword frequency table, keyword search is performed on the policy information to generate a first search result; Based on the second keyword frequency table, keyword search is performed on the policy information to generate a second search result; generating a policy matching result for the object based on the first search result and the second search result; According to the historical query records and feedback information of the target object, the policy matching result is adjusted to obtain the target policy matching result.

6. A policy matching reverse retrieval device based on big data, characterized in that: include: The first generation module is configured to preset an industry keyword dictionary, analyze the objective attributes of each target object, extract keywords, and generate a first keyword frequency table corresponding to the target object; The second generation module is configured to count the keyword frequencies corresponding to all objects in each industry and generate a second keyword frequency table corresponding to the industry; The third generation module is configured to perform policy matching in response to the non-existence of the object, perform keyword search based on a first keyword frequency table corresponding to the object and a second keyword frequency table corresponding to the industry to which the object belongs, and generate a policy matching result for the object.

7. A computer device, characterized in that: The computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to any one of claims 1 to 5 when executing the program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images