An intelligent retrieval method and system based on water affairs government data

Abstract

The present application involves an intelligent retrieval method and system based on water affairs government affairs data. By collecting the associated retrieval logs of the files to be retrieved of the water affairs government affairs data, when the number of files to be retrieved belonging to the retrieval index of the similar semantic matching interval value is greater than the first threshold value, the corresponding correlation degree is determined as the correlation degree of the water affairs government affairs data. According to the level, the associated retrieval log library of the files to be retrieved based on the water affairs government affairs data is graded to obtain a set of water affairs government affairs data files corresponding to the correlation degree, and information association filtering is performed to determine whether it belongs to a positive or non-positive association, and determine the similar semantic matching interval value corresponding to the correlation degree. This scheme only needs to collect the current associated retrieval logs of the water affairs government affairs data, and can directly determine the correlation degree of the water affairs government affairs data through the matching interval value. It can be achieved without running a complex model, which is more efficient and accurate, and can reduce the calculation complexity while further reducing misidentification or missed identification.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an intelligent retrieval method and system based on water affairs government affairs data. Background Art

[0002] Over the past 10 years, the government affairs system has accumulated a large amount of government affairs data (about 700G, mainly WORD, TIF, and PDF files) in daily office work, but has lacked effective use of the data. It has only implemented simple queries based on single conditions such as title and document number, and is unable to find the specific content of most files (especially the content of unstructured format files such as PDF and TIF). The information in the files lacks correlation and is independent of each other, and has little to do with business work. The files you want to find cannot be found or found accurately, and the information you want to find cannot be located. The source and source of the information you want to check cannot be located, and the support for the business is very limited.

[0003] Using OCR technology to convert, identify, and extract files can help business personnel find files quickly and accurately, quickly associate and match corresponding documents for important information, and associate corresponding historical files and related cases in the process of document approval. At the same time, it can further mine government data, extract key content such as leadership instructions, indicator data, business information, etc. from the files, and form a corresponding content list to assist office work, decision-making support, performance supervision, etc., thereby enhancing the intelligent capabilities of government systems. Summary of the invention

[0004] To achieve the above objectives, this application provides the following technical solutions:

[0005] According to a first aspect of the present invention, the present invention claims protection for an intelligent retrieval method based on water affairs government affairs data, comprising:

[0006] Collecting the associated search log of the to-be-searched files of water affairs government affairs data, wherein the associated search log includes a plurality of search indicators;

[0007] When the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the multiple retrieval indexes is greater than a first threshold, the relevance corresponding to the similar semantic matching interval value is determined as the relevance of the water affairs government affairs data.

[0008] Furthermore, the multiple search indices are used to indicate the proportion of unstructured data and / or index indices;

[0009] The relevance includes the approval process relevance or the water environment protection relevance, and the similar semantic matching interval value corresponds to the approval process relevance or the water environment protection relevance;

[0010] The similar semantic matching interval value is obtained by the following operation:

[0011] Based on the associated search log library of the to-be-searched files of the water affairs government affairs data, classification is performed to obtain a set of water affairs government affairs data files corresponding to the degree of association, wherein the associated search log library of the to-be-searched files of the water affairs government affairs data contains the associated search logs of the to-be-searched files of the water affairs government affairs data obtained in advance;

[0012] Performing information association filtering on the water affairs government affairs data file set to determine whether the information association of the water affairs government affairs data file set is a positive association or a non-positive association;

[0013] According to the information association of the water affairs government affairs data file set, a similar semantic matching interval value corresponding to the association degree is determined.

[0014] Furthermore, the information association filtering of the water affairs government affairs data file set specifically includes:

[0015] Dividing the associated search logs in the water affairs government affairs data file set into keyword nodes to obtain a plurality of keyword nodes, wherein each of the plurality of keyword nodes has the same number of keywords;

[0016] The keyword node with the largest number of keywords among the multiple keyword nodes is used as the mean value interval of the water affairs government affairs data file set;

[0017] When the number of keywords of the water affairs government affairs data file set in the first interval is equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a positive association;

[0018] When the number of keywords of the water affairs government affairs data file set in the first interval is not equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a non-positive association;

[0019] The first interval and the second interval are obtained by dividing the information interval of the water affairs government affairs data file set according to the mean interval.

[0020] Further, the method further comprises: when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the multiple retrieval indexes is not greater than the first threshold value, determining the relevance of the water affairs government affairs data according to the semantic distance between the associated retrieval log and the first water affairs government affairs data reference associated index value;

[0021] The determining the relevance of the water affairs government affairs data according to the semantic distance between the relevance search log and the first water affairs government affairs data reference relevance index value includes:

[0022] Of the two first water affairs and government affairs data reference correlation index values, the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closer to the correlation search log is determined as the correlation degree of water affairs and government affairs data; or,

[0023] Among three or more of the first water affairs and government affairs data reference correlation index values, determine the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closest to the correlation search log as the correlation degree of the water affairs and government affairs data;

[0024] The determining the relevance of the water affairs government affairs data according to the semantic distance between the relevance search log and the first water affairs government affairs data reference relevance index value includes:

[0025] When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is greater than the average of the first semantic distance and the second semantic distance, determining that the correlation is the approval process correlation;

[0026] When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is not greater than the average of the first semantic distance and the second semantic distance, determining that the association degree is a water environment protection association degree;

[0027] The first semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with the approval process, and the second semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with water environment protection.

[0028] Furthermore, it also includes:

[0029] When the attribution degree of the associated search log of the to-be-searched file of the water affairs government data is greater than or equal to the third threshold, the associated search log whose number of to-be-searched files belonging to the search index of the similar semantic matching interval value is not greater than the first threshold is added to the associated search log library of the to-be-searched files of the water affairs government data;

[0030] When the duration of the association degree being the water environment protection association degree is greater than or equal to the second threshold, the association degree is controlled by using one or more control strategies including the following operations: unstructured data low-proportion operation, approval process association clarification operation;

[0031] The control strategy is determined according to the water environment protection order of the water affairs government data, and the water environment protection order is determined according to the association retrieval log and the similar semantic matching interval value corresponding to the association degree;

[0032] re-determining the first water environment protection order of the water affairs government data after the first period, the first period corresponding to the first water environment protection order;

[0033] The operations in the control strategy are selected randomly.

[0034] According to a second aspect of the present invention, the present invention claims protection for an intelligent retrieval system based on water affairs government affairs data, comprising:

[0035] A collection unit, used for collecting associated search logs of files to be searched for water affairs government data, wherein the associated search logs include multiple search indicators;

[0036] The determination unit is used to determine the relevance corresponding to the similar semantic matching interval value as the relevance of water affairs government data when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the multiple retrieval indexes is greater than a first threshold.

[0037] Furthermore, the multiple search indices are used to indicate the proportion of unstructured data and / or index indices;

[0038] The relevance includes the approval process relevance and the water environment protection relevance, and the similar semantic matching interval value corresponds to the approval process relevance or the water environment protection relevance;

[0039] A computing unit, the computing unit being configured to:

[0040] Based on the associated search log library of the to-be-searched files of the water affairs government affairs data, classification is performed to obtain a set of water affairs government affairs data files corresponding to the degree of association, wherein the associated search log library of the to-be-searched files of the water affairs government affairs data contains the associated search logs of the to-be-searched files of the water affairs government affairs data obtained in advance;

[0041] Performing information association filtering on the water affairs government affairs data file set to determine whether the information association of the water affairs government affairs data file set is a positive association or a non-positive association;

[0042] According to the information association of the water affairs government affairs data file set, a similar semantic matching interval value corresponding to the association degree is determined.

[0043] Furthermore, the computing unit is specifically used for:

[0044] Dividing the associated search logs in the water affairs government affairs data file set into keyword nodes to obtain a plurality of keyword nodes, wherein each of the plurality of keyword nodes has the same number of keywords;

[0045] The keyword node with the largest number of keywords among the multiple keyword nodes is used as the mean value interval of the water affairs government affairs data file set;

[0046] When the number of keywords of the water affairs government affairs data file set in the first interval is equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a positive association;

[0047] When the number of keywords of the water affairs government affairs data file set in the first interval is not equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a non-positive association;

[0048] The first interval and the second interval are obtained by dividing the information interval of the water affairs government affairs data file set according to the mean interval.

[0049] Furthermore, the determination unit is further configured to determine the relevance of the water affairs government affairs data according to the semantic distance between the associated search log and the first water affairs government affairs data reference associated indicator value when the number of to-be-retrieved files of the retrieval indicator belonging to the similar semantic matching interval value among the multiple retrieval indicators is not greater than the first threshold value;

[0050] The determining unit is specifically configured to:

[0051] Of the two first water affairs and government affairs data reference correlation index values, the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closer to the correlation search log is determined as the correlation degree of water affairs and government affairs data; or,

[0052] Among three or more of the first water affairs and government affairs data reference correlation index values, determine the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closest to the correlation search log as the correlation degree of the water affairs and government affairs data;

[0053] The determining unit is specifically configured to:

[0054] When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is greater than the average of the first semantic distance and the second semantic distance, determining that the correlation is the approval process correlation;

[0055] When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is not greater than the average of the first semantic distance and the second semantic distance, determining that the association degree is a water environment protection association degree;

[0056] The first semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with the approval process, and the second semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with water environment protection.

[0057] Furthermore, it also includes:

[0058] An information base updating unit is used to: when the attribution degree of the associated retrieval log of the to-be-retrieved file of the water affairs government affairs data is greater than or equal to a third threshold, add the associated retrieval log whose number of to-be-retrieved files belonging to the retrieval index of the similar semantic matching interval value is not greater than the first threshold to the associated retrieval log library of the to-be-retrieved files of the water affairs government affairs data;

[0059] A control unit, for controlling the correlation degree by using one or more control strategies including the following operations when the duration of the correlation degree being the water environment protection correlation degree is greater than or equal to a second threshold: unstructured data low-proportion operation, approval process correlation clarification operation;

[0060] The control strategy is determined according to the water environment protection order of the water affairs government data, and the water environment protection order is determined according to the association retrieval log and the similar semantic matching interval value corresponding to the association degree;

[0061] The control unit is further used to re-determine a first water environment protection order of the water affairs government data after a first period, the first period corresponding to the first water environment protection order;

[0062] The operations in the control strategy are randomly selected by the control unit.

[0063] The present application involves an intelligent retrieval method and system based on water affairs government affairs data, which collects the associated retrieval logs of the files to be retrieved of the water affairs government affairs data. When the number of files to be retrieved belonging to the retrieval index of the similar semantic matching interval value is greater than the first threshold, the corresponding correlation degree is determined as the correlation degree of the water affairs government affairs data. According to the level, the associated retrieval log library of the files to be retrieved based on the water affairs government affairs data is graded to obtain a set of water affairs government affairs data files corresponding to the correlation degree, and information association filtering is performed to determine whether it belongs to a positive or non-positive association, and determine the similar semantic matching interval value corresponding to the correlation degree. This scheme only needs to collect the current associated retrieval logs of the water affairs government affairs data, and can directly determine the correlation degree of the water affairs government affairs data through the matching interval value. It can be achieved without running a complex model, which is more efficient and accurate, and can reduce the calculation complexity while further reducing misidentification or missed identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A workflow diagram of an intelligent retrieval method based on water affairs government affairs data as claimed in an embodiment of the present application;

[0065] Figure 2 An exemplary structural diagram of an intelligent retrieval system based on water affairs government affairs data as claimed in an embodiment of the present application;

[0066] Figure 3 An exemplary flow chart of a relevance search of an intelligent search method based on water affairs government affairs data claimed in an embodiment of the present application;

[0067] Figure 4 This is an exemplary flowchart of the association of filtering information for an intelligent retrieval method based on water affairs government affairs data as claimed in an embodiment of the present application. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0069] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0070] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0071] The implementation method of the embodiment of the present application is described in detail below using water affairs government affairs data as an example.

[0072] Figure 1The exemplary process of the intelligent retrieval method based on water affairs government data in the embodiment of the present application is shown. Figure 1 As shown, the intelligent retrieval method based on water affairs government affairs data in the embodiment of the present application may include:

[0073] Step S101, collecting the associated search log of the to-be-searched file of the water affairs government affairs data, the associated search log including a plurality of search indicators;

[0074] The index corresponding to the retrieval index can characterize a feature in the water affairs government data that affects the processing efficiency. The feature that affects the processing efficiency may include, but is not limited to, unstructured data proportion features, index index features, language features, or any other features related to the state of the water affairs government data in the water affairs government data process. In practical applications, the index can be pre-associated, selected in real time, or selected in response to water affairs government data operations based on the needs of specific application scenarios, water affairs government data conditions, water affairs government data needs, retrieval accuracy requirements, or other factors. For example, for different categories of water affairs government data, due to different needs for water affairs government data retrieval, the index needs to be adjusted according to different water affairs government data index indicators.

[0075] The retrieval index can be information obtained after pre-matching such as real-time cleaning and normalization through the index retrieval instructions collected in real time. In some examples, if the matching interval value is a probability value of [0,1], the retrieval index can be a normalized value obtained based on the index retrieval instruction collected in real time, and the value of the normalized value is between [0,1]. In this way, it is not only conducive to the device (for example, the computing device below) to efficiently determine whether the retrieval index belongs to the matching interval value, but also the number of keywords is small and the calculation complexity is low. In other examples, the retrieval index can also be an integer value obtained based on the index retrieval instruction collected in real time. In this way, it is not only conducive to efficiently judging whether the retrieval index belongs to the corresponding matching interval value, but also has low requirements on hardware performance such as matchers, which can further reduce hardware costs.

[0076] In at least some embodiments, the index may include but is not limited to an unstructured data ratio index, an index index, etc. In this embodiment, the characteristics of the water affairs government data affecting the processing efficiency can be comprehensively and accurately perceived through a variety of indicators, and a correlation retrieval log that can reflect the comprehensive characteristics of the water affairs government data affecting the processing efficiency can be obtained, thereby efficiently and accurately determining the correlation of the water affairs government data.

[0077] The unstructured data ratio index may indicate the status of water affairs and government affairs data retrieval instructions related to OCR conversion. The unstructured data ratio index retrieval instructions may be collected by a water affairs and government affairs data retrieval instruction retrieval detector. Here, the water affairs and government affairs data retrieval instruction retrieval detector may provide these retrieval instructions to a device (e.g., a computing device described below) through various wireless OCR conversion operations, or may provide these retrieval instructions to a device (e.g., a computing device described below) in the form of electrical retrieval instructions through a wired connection with the device.

[0078] The indicators of water affairs government data may also include language indicators. The retrieval indicators of speech may include frequency values, amplitude values, etc. of the language indicators. The language indicator retrieval instructions may be collected by speech detectors such as microphone arrays.

[0079] The associated search log is a collection of various search indicators at the same time. The associated search log has at least two dimensions, and its dimensions correspond to the indicators one by one. It can reflect the comprehensive characteristics of the impact of water affairs government data on processing efficiency at a certain time. For example, taking the pre-selected 6 indicators as an example, the 6 indicators include scene conversion, association, unstructured data, water affairs government data file retrieval score, and water affairs government data file length. The corresponding associated search log can have 6 dimensions, which represent the above 6 indicators respectively. The associated search log at the i-th moment can be expressed as {ai, bi, ci, di, ei}, ai represents the scene conversion value at the i-th moment, bi represents the association value at the i-th moment, ci represents the unstructured data value at the i-th moment, di represents the water affairs government data file retrieval score value at the i-th moment, and ei represents the water affairs government data file length value at the i-th moment. It should be noted that the "same moment" here not only includes strict time synchronization, but also includes the situation where the acquisition cycle is less than a predetermined threshold, and the predetermined threshold can be determined by the performance indicators of each detector. In practical applications, the threshold can be an empirical value or a set value.

[0080] Step S102: when the number of to-be-searched files of the search index belonging to the similar semantic matching interval value among the multiple search indexes of the associated search log is greater than a first threshold, the correlation degree corresponding to the similar semantic matching interval value is determined as the correlation degree of the water affairs government affairs data.

[0081] Here, the similar semantic matching interval value generally refers to a single-class matching interval value, which can be used to indicate a single degree of association, and can include matching interval values ​​corresponding to each indicator one by one. Detailed technical details can be found in the following description, which will not be repeated here.

[0082] The degree of association may indicate the state related to the water affairs government data that affects the processing efficiency. In the embodiment of the present application, the degree of association may include two or more. In this way, by dividing the multiple degrees of association, it is convenient for the water affairs government data to intuitively understand whether its own state is suitable for water affairs government data, and at the same time, it can reduce the dependence of the state retrieval process on the supervised machine learning model, effectively reducing the computational complexity while improving the accuracy.

[0083] In some implementations, the relevance may include the relevance of the approval process, the relevance of short-water environment protection, the relevance of medium-water environment protection, and the relevance of long-water environment protection. Each water affairs government data may have four types of matching interval values ​​corresponding to the four types of relevance, that is, four similar semantic matching interval values, which correspond to the approval process relevance and the water environment protection relevance. In this example, the relevance of the water affairs government data can be directly determined by multiple types of matching interval values, which can reduce the computational complexity and further reduce misidentification or missed identification.

[0084] In some implementation operations, the relevance may include the approval process relevance and the water environment protection relevance, and the matching interval value of the water affairs government data may include a type of matching interval value corresponding to the approval process relevance and a type of matching interval value corresponding to the water environment protection relevance, that is, two similar semantic matching interval values, which correspond to the approval process relevance and the water environment protection relevance, respectively. In this example, the two types of matching interval values ​​can be used to directly determine whether the relevance of the water affairs government data is to be matched or water environment protection, which reduces the computational complexity and reduces the possibility of misidentification or missed identification.

[0085] In at least some embodiments, each type of matching interval value may include a matching interval value corresponding to an indicator one-to-one, that is, a similar semantic matching interval value may include a matching interval value corresponding to an indicator one-to-one. Thus, the relevance can be determined by comprehensively considering various characteristics affecting the processing efficiency during the OCR conversion of water affairs government affairs data, which can further improve the accuracy of the relevance retrieval of water affairs government affairs data.

[0086] Taking the pre-selected six indicators as an example, the six indicators include scene conversion, association, unstructured data, water affairs government data file retrieval score, water affairs government data file length, and water affairs government data file curling. Assuming that the correlation includes the approval process correlation and the water environment protection correlation, the corresponding matching interval values ​​are divided into two categories. One type of matching interval value corresponds to the approval process correlation, and the other type of matching interval value corresponds to the water environment protection correlation.

[0087] In step S102, if the value of the search index in the associated search log belongs to the matching interval value corresponding to the corresponding index in the similar semantic matching interval value, the search index can be considered to belong to the similar semantic matching interval value. If the number of files to be searched for the search index belonging to the similar semantic matching interval value in an associated search log is greater than the first threshold, the associated search log can be considered to belong to the similar semantic matching interval value of the water affairs government data. In this embodiment, the correlation degree of the water affairs government data can be determined by judging whether a specific value belongs to the corresponding value interval. The algorithm is simple and easy to implement, with low hardware cost, high efficiency and small error.

[0088] After analysis, it is found that even if the water affairs government data relevance is to be matched, some of its search indicators may belong to the similar semantic matching interval value of the corresponding water environment protection relevance. Similarly, when the water affairs government data relevance is water environment protection, some of its search indicators may also fall into the similar semantic matching interval value of the corresponding approval process relevance. Therefore, in the method of the embodiment of the present application, the relevance of water affairs government data is determined by setting a first threshold value in combination with the matching interval value, which is more in line with the actual situation and the determination log is more accurate.

[0089] In at least some embodiments, the intelligent retrieval method based on water affairs government data may also include:

[0090] Step S103, when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the multiple retrieval indexes of the associated retrieval log is not greater than the first threshold, the relevance of the water affairs government data is determined according to the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value.

[0091] Therefore, the semantic distance between the associated retrieval log and the reference associated index value of the first water affairs government data corresponding to different degrees of association can be used to assist in the retrieval of the degree of association, further realizing the real-time, efficient and accurate retrieval of the degree of association of water affairs government data with lower computational complexity.

[0092] The first water affairs and government affairs data reference association index value generally refers to a water affairs and government affairs data reference association index value corresponding to a single association degree, that is, a single-category matching interval value can correspond to a water affairs and government affairs data reference association index value, that is, a similar semantic matching interval value corresponds to a first water affairs and government affairs data reference association index value. In some implementation operations, similar to the matching interval value, each first water affairs and government affairs data reference association index value can correspond to a correlation degree, and the first water affairs and government affairs data reference association index value has at least two values ​​corresponding to multiple indicators one by one, that is, the first water affairs and government affairs data reference association index value can be represented by a multi-dimensional information, and the dimension of the multi-dimensional information is equal to the number of index to be retrieved files. Specifically, each dimension of the first water affairs and government affairs data reference association index value corresponds to an indicator, and the value of each dimension can be used as the mean value of the corresponding indicator. Therefore, the semantic distance from the associated retrieval log to the water affairs and government affairs data reference association index value can be accurately estimated by using the values ​​of each dimension of the water affairs and government affairs data reference association index value and each retrieval index in the associated retrieval log of the water affairs and government affairs data to be retrieved files. In this implementation, the relevance of water affairs government affairs data is determined by the semantic distance between multi-dimensional information. The relevance of water affairs government affairs data can be determined by the comprehensive characteristics that affect the processing efficiency of OCR conversion of water affairs government affairs data, thereby reducing the calculation complexity and improving the accuracy of relevance retrieval.

[0093] In some embodiments, similar to the similar semantic matching interval value, the first water affairs government data reference association index value may include two or more, and each first water affairs government data reference association index value corresponds to a correlation degree. Taking the case where the correlation degree includes the approval process correlation degree and the water environment protection correlation degree as an example, the water affairs government data reference association index value of the water affairs government data may include a water affairs government data reference association index value corresponding to the approval process correlation degree and a water affairs government data reference association index value corresponding to the water environment protection correlation degree, that is, one or two first water affairs government data reference association index values ​​may be set, and these two first water affairs government data reference association index values ​​correspond to the approval process correlation degree and the water environment protection correlation degree, respectively, or in other words, the first water affairs government data reference association index value may correspond to the approval process correlation degree or the water environment protection correlation degree. Therefore, the correlation degree of the water affairs government data can be determined by associating the semantic distance between the retrieval log and the first water affairs government data reference association index value, which can reduce the computational complexity and further reduce the possibility of misidentification or missed identification.

[0094] In some embodiments, in step S103, among the two first water affairs and government affairs data reference correlation index values, the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value that is closer to the associated retrieval log is determined as the correlation degree of the water affairs and government affairs data. Alternatively, among three or more first water affairs and government affairs data reference correlation index values, the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value that is closest to the associated retrieval log is determined as the correlation degree of the water affairs and government affairs data. In this embodiment, the water affairs and government affairs data reference correlation index value that is closest to the associated retrieval log is obtained through the semantic distance between the associated retrieval log and the water affairs and government affairs data reference correlation index value, and then the correlation degree corresponding to the water affairs and government affairs data reference correlation index value that is closest to the associated retrieval log is used as the correlation degree of the water affairs and government affairs data, with low calculation complexity and small error.

[0095] In some embodiments, if there are multiple similar semantic matching interval values, in step S103, when the number of to-be-retrieved files belonging to the retrieval index of each similar semantic matching interval value among the multiple retrieval indexes of the associated retrieval log is not greater than the first threshold value, the relevance of the water affairs government data is determined according to the semantic distance between the associated retrieval log and the reference associated index value of the first water affairs government data. In this way, the relevance can be determined by preferentially using the similar semantic matching interval value and the reference associated index value of the first water affairs government data as auxiliary means, which is conducive to improving efficiency and accuracy.

[0096] In some implementation operations, determining the relevance of water affairs government data according to the semantic distance between the associated retrieval log and the reference associated index value of the first water affairs government data in step S103 may include: step a1, when the absolute value of the semantic distance between the first semantic distance and the second semantic distance is greater than the average of the first semantic distance and the second semantic distance, determining the relevance as the approval process relevance; step a2, when the absolute value of the semantic distance between the first semantic distance and the second semantic distance is not greater than the average of the first semantic distance and the second semantic distance, determining the relevance as the water environment protection relevance; the first semantic distance is the semantic distance between the associated retrieval log and the reference associated index value of the first water affairs government data corresponding to the approval process relevance, and the second semantic distance is the semantic distance between the associated retrieval log and the reference associated index value of the first water affairs government data corresponding to the water environment protection relevance. Therefore, the semantic distance between the associated retrieval log and the reference associated index value of the first water affairs government data can be determined by a simple algorithm such as calculating the average and the semantic distance, with low computational complexity and small error, which can further reduce hardware costs and improve the accuracy of relevance retrieval.

[0097] In some implementation operations, when the accuracy of the correlation retrieval is relatively low, after estimating the semantic distance between the correlation retrieval log and the reference correlation index value of the first water affairs government data, the correlation corresponding to the reference correlation index value of the first water affairs government data with the smallest semantic distance can be determined as the correlation of the water affairs government data. This implementation operation has lower computational complexity and relatively low hardware overhead.

[0098] In at least some embodiments, similar semantic matching interval values ​​and reference association index values ​​of the first water affairs government data can be obtained synchronously through various applicable algorithms. For example, a classification or other unsupervised learning algorithm can be used to determine the matching interval value of water affairs government data and the reference association index value of water affairs government data. For another example, similar semantic matching interval values ​​and reference association index values ​​of the first water affairs government data can be determined by information analysis and statistics related algorithms. The specific algorithm for determining similar semantic matching interval values ​​and reference association index values ​​of the first water affairs government data is not limited in the embodiments of the present application.

[0099] In some implementation operations, the similar semantic matching interval value and the reference association index value of the first water affairs government affairs data can be obtained based on the association retrieval log library of the water affairs government affairs data itself, and the association retrieval log library contains the association retrieval logs of the to-be-retrieved files of the water affairs government affairs data obtained in advance. In one implementation operation, the similar semantic matching interval value and the reference association index value of the first water affairs government affairs data can be determined by grading the existing association retrieval logs in the association retrieval log library of the water affairs government affairs data. Specifically, the similar semantic matching interval value can be obtained by the following operations: step b1, grading based on the association retrieval log library of the to-be-retrieved files of the water affairs government affairs data to obtain a water affairs government affairs data file set corresponding to the association degree, and the association retrieval log library of the to-be-retrieved files of the water affairs government affairs data contains the association retrieval logs of the to-be-retrieved files of the water affairs government affairs data obtained in advance; step b2, information association filtering of the water affairs government affairs data file set to determine whether the information association of the water affairs government affairs data file set belongs to a positive association or a non-positive association; step b3, according to the information association of the water affairs government affairs data file set, determining the similar semantic matching interval value corresponding to the association degree. In this implementation operation, the water affairs government affairs data reference association index value corresponding to the water affairs government affairs data file set of the association degree is the first water affairs government affairs data reference association index value corresponding to the similar semantic matching interval value, which can be determined in the classification of step b1. In this way, the similar semantic matching interval value and the first water affairs government affairs data reference association index value of the water affairs government affairs data are obtained by classification based on the association search log library of the water affairs government affairs data itself, which not only realizes the setting of the similar semantic matching interval value and the first water affairs government affairs data reference association index value according to the specific type of water affairs government affairs data, but also realizes the personalization or customization of the association degree retrieval, improves the accuracy of the association degree retrieval, and can reduce missed recognition or misrecognition.

[0100] In some implementation operations, information association filtering of the water affairs government affairs data file set can be achieved through the following steps: step c1, keyword node division of the associated retrieval log in the water affairs government affairs data file set to obtain multiple keyword nodes, and the number of keywords of each keyword node in the multiple keyword nodes is the same; step c2, using the keyword node with the largest number of keywords among the multiple keyword nodes as the mean interval of the water affairs government affairs data file set, when the number of keywords of the water affairs government affairs data file set in the first interval is equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is positive association; when the number of keywords of the water affairs government affairs data file set in the first interval is not equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is non-positive association; wherein the first interval and the second interval are obtained by dividing the information interval of the water affairs government affairs data file set according to the mean interval. In this implementation, the interval keyword node division and information counting, as well as the comparison of the number of information on the left and right halves of the mean interval are used to determine whether the water affairs government affairs data file set is positively correlated or non-positively correlated. This has the effects of low complexity and accurate information correlation filtering, which can further reduce hardware costs and improve the accuracy of water affairs government affairs data correlation retrieval.

[0101] In some implementation operations, the process of adjusting the similar semantic matching interval value and the reference correlation index value of the first water affairs government affairs data may include: updating the correlation retrieval log library of the to-be-retrieved files of the water affairs government affairs data according to the newly collected correlation retrieval log, and using the unclassified correlation retrieval logs in the updated correlation retrieval log library to redetermine the similar semantic matching interval value. Here, the unclassified correlation retrieval log refers to the correlation retrieval log in the water affairs government affairs data file set that is not divided into each correlation degree, that is, the correlation retrieval log that does not belong to the similar semantic matching interval value of the water affairs government affairs data. Here, the algorithm used to redetermine the similar semantic matching interval value and the reference correlation index value of the first water affairs government affairs data is the same as the relevant algorithm mentioned above, and will not be repeated. In this embodiment, unclassified associated retrieval logs are used to implement the adjustment of similar semantic matching interval values ​​and reference associated index values ​​of the first water affairs government affairs data. There is no need to repeatedly match all associated retrieval logs of the water affairs government affairs data. The update of similar semantic matching interval values ​​and reference associated index values ​​of the first water affairs government affairs data can be completed with less computational effort and lower computational complexity, thereby achieving dynamic adjustment of similar semantic matching interval values ​​and reference associated index values ​​of the first water affairs government affairs data. That is, the association retrieval can be realized from time to time at a lower hardware cost.

[0102] In some implementation operations, the associated retrieval log of the to-be-retrieved files of the water affairs government affairs data can be stored in the associated retrieval log library of the to-be-retrieved files of the water affairs government affairs data in the form of a time information sequence. The associated retrieval log library can be read and written by verifying preset information, and the preset information can include any information related to identifying specific water affairs government affairs data. The present application does not limit the type of preset information. In addition, the matching interval value of the water affairs government affairs data and the reference associated index value of the water affairs government affairs data can also be stored in the associated retrieval log library of the to-be-retrieved files of the water affairs government affairs data. In this way, the similar semantic matching interval value of the water affairs government affairs data and the reference associated index value of the first water affairs government affairs data can be queried in real time through the preset information of the water affairs government affairs data, and the associated retrieval log of the to-be-retrieved files of the water affairs government affairs data can be updated, thereby realizing the retrieval of the relevance of the water affairs government affairs data at any time and anywhere, without being restricted by the OCR conversion status, water affairs government affairs data and other usage conditions.

[0103] In the embodiment of the present application, the associated retrieval log library can be updated through various applicable operations.

[0104] In some implementation operations, each time a new associated search log is collected, the new associated search log can be directly added to the associated search log library of the to-be-searched files of the water affairs government data. This exemplary implementation operation is conducive to quickly obtaining the associated search log library of the to-be-searched files of the water affairs government data. This exemplary implementation operation is applicable when the attribution degree of the associated search log of the to-be-searched files of the water affairs government data is low or when the associated search log library of the to-be-searched files of the water affairs government data is initially created.

[0105] In some implementation operations, when the attribution degree of the associated search log of the to-be-searched file of the water affairs government data is greater than or equal to the third threshold, the associated search log whose number of to-be-searched files belonging to the search index of the similar semantic matching interval value is not greater than the first threshold is added to the associated search log library of the to-be-searched file of the water affairs government data. Therefore, when the similar semantic matching interval value of the water affairs government data and the first water affairs government data reference associated index value are relatively stable, the judgment strategy of adding associated search logs to the information library can be used to reduce invalid or duplicate information, avoid unnecessary repeated calculations, and improve the information completeness of the water affairs government data associated search log library. It can reduce redundant information in the associated search log library, reduce the amount of information calculation and the complexity of calculation while continuously improving the water affairs government data files.

[0106] In the above implementation, the attribution degree of the associated retrieval log refers to: the proportion of the associated retrieval logs belonging to the similar semantic matching interval value to all the associated retrieval logs, and the associated retrieval logs belonging to the similar semantic matching interval value refer to the associated retrieval logs whose number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value is greater than the first threshold. In practical applications, the attribution degree of the associated retrieval logs of the to-be-retrieved files of the water affairs government data can be calculated in real time by counting the associated retrieval logs belonging to the similar semantic matching interval value.

[0107] In practical applications, the specific value of the third threshold can be pre-associated, dynamically determined, or selected in response to water affairs government affairs data operations based on one or more factors such as the needs of specific application scenarios, the requirements of retrieval accuracy, the needs of water affairs government affairs data, and the conditions of water affairs government affairs data. In some embodiments, the third threshold can be an empirical value, a function value of a predefined function with the above factors as variables, etc. The third threshold can be a fixed value, an interval value, or a variable value.

[0108] In at least some embodiments, the calculation and update of the similar semantic matching interval value and the reference correlation index value of the first water affairs government data can be implemented locally at the water affairs government data retrieval end, or can be executed through a cloud server. In some implementation operations, the calculation and update of the similar semantic matching interval value and the reference correlation index value of the first water affairs government data can be obtained through a cloud server and provided to the water affairs government data retrieval end. In this implementation operation, the calculation of the similar semantic matching interval value and the reference correlation index value of the first water affairs government data is executed on the cloud server, and the retrieval of the correlation degree is performed locally at the water affairs government data retrieval end.

[0109] In at least some embodiments, the method of the embodiment of the present application may further include a relevance control step. After the water affairs government data is retrieved to be at the water environment protection relevance, the relevance of the water affairs government data may be controlled through a single operation or a multi-operation retrieval instruction, thereby timely and effectively improving the water environment protection relevance of the water affairs government data.

[0110] In some implementation operations, the above method of the embodiment of the present application may also include:

[0111] Step S104, when the duration of the water environment protection correlation degree reaches a second threshold, the correlation degree is controlled by using one or more control strategies including the following operations: low-proportion operation of unstructured data and operation of clarifying the correlation of approval process.

[0112] In this implementation, the control strategy is triggered after a certain period of time, which can not only achieve timely and effective intervention in the relevance of water environment protection, but also avoid false triggering of the control strategy, thereby improving the water affairs government affairs data experience.

[0113] In practical applications, the specific value of the second threshold can be pre-associated, dynamically determined, or selected in response to water affairs government data operations based on one or more factors such as the needs of specific application scenarios, the requirements of retrieval accuracy, the needs of water affairs government data, and the situation of water affairs government data. In some embodiments, the second threshold can be an empirical value, a function value of a predefined function with the above factors as variables, etc. The second threshold can be a fixed value, an interval value, or a variable value. For example, the second threshold can be 5 seconds, that is, when the duration of the correlation degree of water affairs government data to the water environment protection correlation degree is greater than or equal to 5 seconds, the control strategy for the correlation degree of water affairs government data is triggered.

[0114] In some implementation operations, the control strategy can be determined based on the water environment protection order of water affairs government data, and the water environment protection order of water affairs government data can be determined based on the associated retrieval log of the to-be-retrieved files of the water affairs government data and the similar semantic matching interval value corresponding to its correlation. For different water environment protection orders, the water environment protection order of water affairs government data can be re-determined after different cycles. That is, the first water environment protection order of water affairs government data is re-determined after the first cycle, and the first cycle corresponds to the first water environment protection order. In this way, the state control of different water environment protection associations using appropriate operations can significantly improve the effect of water environment protection association intervention.

[0115] Here, the first water environment protection order generally refers to a single water environment protection order, and the first period generally refers to a period corresponding to or associated with the single water environment protection order.

[0116] In some examples, the similar semantic matching interval value of water affairs government data can be divided into multiple sub-intervals, each sub-interval corresponds to a different water environment protection order, and each water environment protection order is associated with a different control strategy. The water environment protection order corresponding to the sub-interval of the similar semantic matching interval value of the associated retrieval log of the to-be-retrieved file of the water affairs government data is the water environment protection order of the water affairs government data, and the control strategy corresponding to the water environment protection order can be used to control the correlation degree of the water affairs government data.

[0117] In some implementations, the operations in the control strategy can be randomly selected. That is, a single-operation control strategy or a multi-operation control strategy can be adopted, and the specific operation adopted during control can be randomly selected, which can effectively improve the tolerance of the control strategy.

[0118] The intelligent retrieval method based on water affairs government affairs data in the embodiment of the present application collects the associated retrieval logs of the files to be retrieved of the water affairs government affairs data, and directly determines the relevance of the water affairs government affairs data by judging the number of files to be retrieved that belong to the matching interval value among the multiple retrieval indicators of the associated retrieval logs. The method has small computational complexity and easy algorithm implementation, and can accurately, efficiently and in real time retrieve the relevance of the water affairs government affairs data with low computational complexity, while improving the water affairs government affairs data experience and reducing application costs.

[0119] Among them, in this embodiment, based on the B / S architecture, the Spring Boot development framework is adopted, and technologies such as OCR intelligent recognition, NLP natural language processing, and ElasticSearch open source distributed search engine are used to achieve full-text retrieval and intelligent association of water government data.

[0120] Establish a government data retrieval model to realize intelligent associated retrieval. Through NLP natural language processing, weight calculation and other technologies, the retrieval results are made more accurate, which is convenient for users to find the required files and associate various historical files to assist in daily office work. Through OCR intelligent recognition of the layout files (unstructured data) of government data, after identification, NLP natural language processing is performed together with structured data, and the processed data is indexed and inverted indexed and stored in the index library. When searching, through the keyword extraction in the NLP natural language processing of the data governance process, the system will perform word segmentation and associative retrieval on keywords and other information, screen out files with similar keywords, and perform text similarity analysis, calculate the corresponding weight of the files, and sort them on the result page according to the score. At the same time, files with a similarity greater than or equal to 0.75 are counted as associated files.

[0121] Through OCR data recognition, government data retrieval is more comprehensive and easier. Information generated by various government units from 2005 to 2021 can be queried, and the original retrieval of data items such as title, document number, registration time, etc. has been expanded to all contents of forms, texts, and attachments, including previously unrecognizable unstructured data such as PDF and TIF, realizing full-type, full-content, and full-factor retrieval of various types of government information.

[0122] All government data can be turned into readable, searchable, usable and analyzable structured information, and labeled. Government data can be managed like business data. For example, relevant documents such as various matters, certificates, meetings, policies, and official documents of an enterprise involved in the Water Affairs Bureau can be extracted. Ultimately, personal and departmental data portraits are formed for internal managers, and corporate and personal portraits of enterprises and citizens doing business at the Water Affairs Bureau are formed, laying a solid data foundation for future government data mining.

[0123] Figure 2The exemplary structure of the intelligent retrieval system based on water affairs government affairs data provided by the embodiment of the present application is shown. Figure 2 An exemplary intelligent retrieval system based on water affairs government affairs data in the application embodiment shown may include:

[0124] A collection unit 21, used for collecting the associated search log of the to-be-searched file of the water affairs government affairs data, wherein the associated search log includes a plurality of search indicators;

[0125] The determination unit 22 is used to determine the relevance corresponding to the similar semantic matching interval value as the relevance of water affairs government data when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among multiple retrieval indexes is greater than a first threshold.

[0126] The intelligent retrieval system based on water affairs government affairs data in the embodiment of the present application collects the associated retrieval logs of the files to be retrieved of the water affairs government affairs data, and directly determines the relevance of the water affairs government affairs data by judging the number of files to be retrieved that belong to the matching interval value among the multiple retrieval indicators of the associated retrieval logs. It has a small amount of calculation and is easy to implement the algorithm. It can accurately, efficiently and in real time retrieve the relevance of the water affairs government affairs data with low computational complexity, while improving the water affairs government affairs data experience and reducing application costs.

[0127] In some implementation operations, multiple search indicators are used to indicate the proportion of unstructured data and / or index indicators. In other words, the indicators corresponding to the search indicators include the proportion of unstructured data and / or index indicators. Therefore, through multiple indicators, the impact of water affairs government data on processing efficiency can be fully and accurately perceived, thereby efficiently and accurately determining the relevance of water affairs government data.

[0128] In some implementations, the relevance includes the approval process relevance and the water environment protection relevance, and the similar semantic matching interval value corresponds to the approval process relevance or the water environment protection relevance. Therefore, the two types of matching interval values ​​of water affairs government data can directly determine whether the relevance of water affairs government data is to be matched or water environment protection, which reduces the calculation complexity and reduces misidentification or missed identification.

[0129] In some implementation operations, each type of matching interval value, i.e., each similar semantic matching interval value, may include a matching interval value corresponding to an index corresponding to the search index. Thus, the relevance of the water affairs government affairs data can be determined by comprehensively considering various characteristics affecting the processing efficiency during the OCR conversion of the water affairs government affairs data.

[0130] In some implementation operations, the intelligent retrieval system based on water affairs government affairs data of the embodiment of the present application may also include:

[0131] Calculation unit 23, similar semantic matching interval value is determined by calculation unit 23, and calculation unit 23 can obtain similar semantic matching interval value by associating the following steps: grading based on the associated retrieval log library of the to-be-retrieved files of water affairs and government affairs data to obtain a water affairs and government affairs data file set corresponding to the degree of association, the associated retrieval log library of the to-be-retrieved files of water affairs and government affairs data contains the associated retrieval log of the to-be-retrieved files of water affairs and government affairs data obtained in advance; performing information association filtering on the water affairs and government affairs data file set to determine whether the information association of the water affairs and government affairs data file set belongs to a positive association or a non-positive association; determining the similar semantic matching interval value corresponding to the degree of association according to the information association of the water affairs and government affairs data file set. Thus, the matching interval value and the reference association index value of the water affairs and government affairs data are set according to the specific type of the water affairs and government affairs data, while reducing missed recognition or misrecognition.

[0132] In some implementation operations, the calculation unit 23 can also associate and filter the water affairs government affairs data file set through the following steps: divide the associated retrieval log in the water affairs government affairs data file set into keyword nodes to obtain multiple keyword nodes, and the number of keywords of each keyword node in the multiple keyword nodes is the same; the keyword node with the largest number of keywords among the multiple keyword nodes is used as the mean interval of the water affairs government affairs data file set; when the number of keywords of the water affairs government affairs data file set in the first interval is equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a positive association; when the number of keywords of the water affairs government affairs data file set in the first interval is not equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a non-positive association; wherein the first interval and the second interval are obtained by dividing the information interval of the water affairs government affairs data file set according to the mean interval. Therefore, the intelligent retrieval system based on water affairs government affairs data in the embodiment of the present application determines whether the water affairs government affairs data file set is positively correlated or non-positively correlated through interval keyword node division and information counting, and comparison of the number of information on the left and right halves of the mean interval. It has the effects of low complexity and accurate information correlation filtering, which can further reduce hardware costs and improve the accuracy of water affairs government affairs data correlation retrieval.

[0133] In some implementation operations, the determination unit 22 can also be used to determine the relevance of the water affairs government data based on the semantic distance between the associated retrieval log and the first water affairs government data reference associated indicator value when the number of files to be retrieved for the retrieval indicator belonging to the similar semantic matching interval value among the multiple retrieval indicators of the associated retrieval log is not greater than the first threshold.

[0134] In some embodiments, the first water affairs government data reference association index value may include two or more, and each first water affairs government data reference association index value corresponds to a degree of association. The determination unit 22 is specifically used to determine, among the two first water affairs government data reference association index values, the degree of association corresponding to the first water affairs government data reference association index value that is closer to the associated retrieval log as the degree of association of the water affairs government data; or, among three or more first water affairs government data reference association index values, the degree of association corresponding to the first water affairs government data reference association index value that is closest to the associated retrieval log is determined as the degree of association of the water affairs government data. Thus, the semantic distance from the associated retrieval log of the to-be-retrieved file of the water affairs government data to its water affairs government data reference association index value can assist in the retrieval of the degree of association of the water affairs government data, and achieve real-time, efficient and accurate retrieval of the degree of association of the water affairs government data with lower computational complexity.

[0135] In some implementation operations, the determination unit 22 can be specifically used to: when the semantic distance between the first semantic distance and the second semantic distance is greater than the average of the first semantic distance and the second semantic distance, determine the association degree as the approval process association degree; when the semantic distance between the first semantic distance and the second semantic distance is not greater than the average of the first semantic distance and the second semantic distance, determine the association degree as the water environment protection association degree; the first semantic distance is the semantic distance between the association retrieval log and the first water affairs government data reference association index value corresponding to the approval process association degree, and the second semantic distance is the semantic distance between the association retrieval log and the first water affairs government data reference association index value corresponding to the water environment protection association degree. In this way, the water affairs government data association degree retrieval can be determined based on the semantic distance with lower computational complexity.

[0136] In some implementation operations, the intelligent retrieval system based on water affairs government affairs data of the embodiment of the present application may also include:

[0137] The information base updating unit 24 is used to add the associated search logs whose number of files to be retrieved belonging to the search index of the similar semantic matching interval value is not greater than the first threshold to the associated search log library of the files to be retrieved of the water affairs government data when the attribution degree of the associated search logs of the files to be retrieved of the water affairs government data is greater than or equal to the third threshold. In this way, the redundant information entering the associated search log library can be significantly reduced, and the amount of information calculation and the complexity of calculation can be reduced.

[0138] In some implementation operations, the intelligent retrieval system based on water affairs government affairs data of the embodiment of the present application may also include:

[0139] The control unit 25 is used to control the correlation degree by using one or more control strategies including the following operations when the duration of the correlation degree for water environment protection is greater than or equal to the second threshold: low-proportion operation of unstructured data, and clarification operation of approval process correlation. In this way, timely and effective intervention in the correlation degree of water environment protection of water affairs government data can be achieved, while avoiding false triggering of the control strategy.

[0140] In some implementation operations, the control strategy can be determined according to the water environment protection order of water affairs government data, and the water environment protection order can be determined according to the associated search log of the to-be-retrieved file of the water affairs government data and the similar semantic matching interval value corresponding to the association degree. In this way, the state control is performed by using appropriate operations for different water environment protection associations, which can significantly improve the effect of water environment protection association degree intervention.

[0141] In some implementation operations, the control unit 25 may also be used to re-determine the first water environment protection order of the water affairs government data after the first cycle, and the first cycle corresponds to the first water environment protection order. In this way, re-evaluating different water environment protection associations using different cycles is more in line with the actual situation of improving the association of water affairs government data, and can significantly improve the effect of water environment protection association intervention.

[0142] In some implementations, the operations in the control strategy may be randomly selected by the control unit 25. In this way, the tolerance of the control strategy can be effectively improved.

[0143] Some exemplary specific implementations of the embodiments of the present application are described in detail below. The following implementations may be arbitrarily combined with each other, and the various exemplary implementation operations of each implementation may also be arbitrarily combined as needed. It should be noted that the following implementations and any combination of their exemplary implementation operations are only examples of the above-mentioned methods or systems of the embodiments of the present application, and are not intended to limit the embodiments of the present application.

[0144] Figure 3 An exemplary process of relevance retrieval in the second embodiment of the present application is shown. The exemplary process may include the following steps:

[0145] Step S301, during the OCR conversion process of the water affairs government affairs data, the water affairs government affairs data retrieval terminal device installed on the water affairs government affairs data collects preset information of the water affairs government affairs data and numerical retrieval instructions of various unstructured data ratio indicators and index indicators;

[0146] Step S302: the water affairs government affairs data retrieval terminal device performs local pre-matching on various numerical retrieval instructions of the water affairs government affairs data to obtain the associated retrieval log of the water affairs government affairs data at the current moment;

[0147] Here, the associated search log includes search indicators that correspond one to one with the indicators. The search indicators are normalized values. The normalized values ​​are obtained by pre-matching the numerical search instructions of the corresponding indicators. The normalized values ​​are between [0, 1].

[0148] Step S303, the water affairs government affairs data retrieval terminal device locally searches for a matching interval value and a water affairs government affairs data reference correlation index value that match the preset information of the water affairs government affairs data;

[0149] Step S304, the water affairs government data retrieval terminal device determines whether the relevance of the water affairs government data at the current moment meets the high relevance water environment protection according to the matching interval value of the water affairs government data, the reference relevance index value of the water affairs government data and the relevance retrieval log at the current moment;

[0150] Step S305: If it is in compliance, the water affairs government affairs data retrieval terminal device controls the water environment protection relevance of the water affairs government affairs data.

[0151] Step S306, determining whether the water affairs government affairs data retrieval terminal device is currently online;

[0152] Step S307: if offline, the water affairs government affairs data retrieval terminal device locally stores the associated retrieval log of the water affairs government affairs data at the current moment.

[0153] Step S308: If online, the water affairs government data retrieval terminal device uploads the associated retrieval logs and preset information of the to-be-retrieved files of the locally stored water affairs government data to the cloud server through its front-end communication unit.

[0154] In one implementation operation, the local pre-matching in step S302 may include information pre-matching (for example, information cleaning), unified sampling, information normalization, etc. The corresponding associated search logs obtained include search indicators corresponding to the indicators one by one, and each search indicator includes a normalized value, and the value of the normalized value is obtained by performing local pre-matching on the numerical search instruction of the corresponding indicator, and the normalized value is between [0, 1].

[0155] In one implementation operation, step S308 may include steps corresponding to information verification and information base, where information verification may include verifying whether the preset information of the water affairs government data is legal or exists. The steps corresponding to the information base may include: finding an associated search log base corresponding to the preset information of the water affairs government data. After finding the associated search log base of the to-be-searched file of the water affairs government data, the associated search log of the to-be-searched file of the water affairs government data may be stored in its associated search log base.

[0156] In one implementation operation, the associated retrieval log library of the to-be-retrieved files of water affairs government affairs data can store the associated retrieval logs of the to-be-retrieved files of water affairs government affairs data in the form of a time information sequence, and each log in the time information sequence contains the time information of an associated retrieval log and the normalized values ​​of each indicator corresponding to the associated retrieval log.

[0157] In this embodiment, a multi-dimensional correlation retrieval log is obtained through numerical retrieval instructions of multiple indicators, and the correlation degree of water affairs government data is determined in real time based on the multi-dimensional correlation retrieval log. It has low requirements on the collection environment, a small number of keywords, and low requirements on computing power and bandwidth for information matching and transmission. The water affairs government data experience is better and the cost of use is lower.

[0158] This embodiment uses a multi-dimensional information classification method, not a classification method, which can avoid the problem of linear inseparability when the information dimension is high, and the classification log does not directly act on the classification of intermediate features such as brightness and color, but directly characterizes the correlation of water affairs and government affairs data through the classified water affairs and government affairs data file set. In this way, the correlation of water affairs and government affairs data can be directly determined by using the matching interval value of the classified water affairs and government affairs data file set and the reference correlation index value of the water affairs and government affairs data, which reduces the calculation complexity while reducing misidentification or missed identification, thereby improving the accuracy of water affairs and government affairs data correlation retrieval.

[0159] Figure 4 An exemplary flow chart of filtering information association is shown. The exemplary flow chart of filtering information association in this embodiment may include the following steps:

[0160] Step S401, slicing all related search logs in the water affairs government data file set with equal interval keyword numbers to obtain multiple slices with the same keyword numbers;

[0161] Step S402, quickly sorting the slices obtained by dividing the keyword nodes according to the number of keywords, and finding the slice with the largest number of keywords;

[0162] Step S403, determining whether the number of keywords in the first interval of the water affairs government data file is equal to the number of keywords in the second interval, if yes, proceed to step S404, otherwise jump to step S405;

[0163] Step S404, determining that the information association of the water affairs government affairs data file set is a positive association;

[0164] Step S405, determining that the information association of the water affairs government affairs data file set is a non-positive association.

[0165] If the search index in the associated search log has been normalized and matched in the local pre-matching process, the value of each search index in the associated search log will be associated between [0,1], and there is no need to perform normalization matching before step S401 in this process. If the value of the search index is not a normalized value associated between [0,1], it is necessary to add a step of normalizing each associated search log in the water affairs government data file set before step S401.

[0166] In this embodiment, information association is filtered by dividing information through keyword nodes, and different operations are used to calculate matching interval values ​​for different types of information associations, thereby obtaining various types of matching interval values ​​that can accurately characterize the various association boundaries of water affairs government data, providing an accurate judgment basis for accurate retrieval of water affairs government data associations.

[0167] This embodiment describes in detail the exemplary implementation operations for controlling the correlation of water affairs government affairs data.

[0168] In some implementation operations, the triggering process of controlling the relevance of water affairs and government affairs data may include: determining whether the duration of the water affairs and government affairs data being at the water environment protection relevance reaches a preset second threshold, and if so, triggering the control of the relevance of the water affairs and government affairs data, otherwise there is no need to intervene in the relevance of the water affairs and government affairs data. This implementation operation controls the relevance of the water affairs and government affairs data only after the relevance of the water affairs and government affairs data lasts for a period of time, which can avoid the false triggering of the control strategy and improve the experience of water affairs and government affairs data.

[0169] Generally speaking, the higher the water environment protection relevance, the longer it takes to control the state of water affairs government data. Therefore, in at least some embodiments, a step-by-step duration threshold may be used, that is, the first duration is less than the second duration, and the second duration is less than the third duration. The specific values ​​of the first duration, the second duration, and the third duration may be empirical values ​​or dynamically changing values, and may be adjusted according to the characteristics of water affairs government data.

[0170] In some implementation operations, the process of determining the water environment protection association can be: pre-dividing each matching interval value in a type of matching interval value corresponding to the water environment protection association degree into multiple sub-intervals, and these multiple sub-intervals represent multiple gears of different water environment protection associations. By judging which sub-interval of the corresponding matching interval value the mean value of the retrieval index in all associated retrieval logs in the current control period belongs to, the gear of the current water environment protection association of the water affairs government data can be determined. For example, each matching interval value in a type of matching interval value corresponding to the water environment protection association degree is equally divided into three sub-intervals, and these three sub-intervals represent the high, medium and low grades of the water environment protection association, respectively. If the mean value of the same retrieval index of all associated retrieval logs in the first time period belongs to the corresponding sub-interval, then the current water environment protection association of the water affairs government data is determined to be the gear corresponding to the sub-interval.

[0171] The control method of this embodiment has control resistance.

[0172] In this embodiment, when the degree of attribution of a newly generated associated retrieval log is greater than a certain value, the strategy for the associated retrieval log to enter the associated retrieval log library is changed from the original operation of directly sending the associated retrieval log to the associated retrieval log library to "only selecting points that do not have a matching interval value dimension greater than half to enter the information library". In this way, while continuously improving the information files of the water affairs government data status, the redundant information entering the associated retrieval log library can be reduced, thereby reducing the amount of information calculations and reducing the calculation complexity.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed systems, systems and methods can be implemented through other operations. For example, the system embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division operations in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0174] In addition, each functional unit in each embodiment of the present application can be integrated into a matching unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. The above is only an implementation method of the present application, and does not limit the patent range of the present application. Any equivalent structure or equivalent process transformation made using the content of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection range of the present application.

[0175] The specific implementation methods of the invention are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. An intelligent retrieval method based on water affairs government data, characterized in that: include: Collecting the associated search log of the to-be-searched files of water affairs government affairs data, wherein the associated search log includes a plurality of search indicators; When the number of to-be-searched files of the search index belonging to the similar semantic matching interval value among the multiple search indexes is greater than the first threshold value, the relevance corresponding to the similar semantic matching interval value is determined as the relevance of the water affairs government affairs data; The multiple search indicators are used to indicate the proportion of unstructured data and / or index indicators; The relevance includes the approval process relevance or the water environment protection relevance, and the similar semantic matching interval value corresponds to the approval process relevance or the water environment protection relevance; The similar semantic matching interval value is obtained by the following operation: Based on the associated search log library of the to-be-searched files of the water affairs government affairs data, classification is performed to obtain a set of water affairs government affairs data files corresponding to the degree of association, wherein the associated search log library of the to-be-searched files of the water affairs government affairs data contains the associated search logs of the to-be-searched files of the water affairs government affairs data obtained in advance; Performing information association filtering on the water affairs government affairs data file set to determine whether the information association of the water affairs government affairs data file set is a positive association or a non-positive association; Determining a similar semantic matching interval value corresponding to the degree of association according to the information association of the water affairs government affairs data file set; The information association filtering of the water affairs government affairs data file set specifically includes: Dividing the associated search logs in the water affairs government affairs data file set into keyword nodes to obtain a plurality of keyword nodes, wherein each of the plurality of keyword nodes has the same number of keywords; The keyword node with the largest number of keywords among the multiple keyword nodes is used as the mean value interval of the water affairs government affairs data file set; When the number of keywords of the water affairs government affairs data file set in the first interval is equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a positive association; When the number of keywords of the water affairs government affairs data file set in the first interval is not equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a non-positive association; The first interval and the second interval are obtained by dividing the information interval of the water affairs government affairs data file set according to the mean interval.

2. The intelligent retrieval method based on water affairs government data according to claim 1 is characterized in that: The method further includes: when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the multiple retrieval indexes is not greater than the first threshold value, determining the relevance of the water affairs government affairs data according to the semantic distance between the associated retrieval log and the first water affairs government affairs data reference associated index value; The determining the relevance of the water affairs government affairs data according to the semantic distance between the relevance search log and the first water affairs government affairs data reference relevance index value includes: Of the two first water affairs and government affairs data reference correlation index values, the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closer to the correlation search log is determined as the correlation degree of water affairs and government affairs data; or, Among three or more of the first water affairs and government affairs data reference correlation index values, determine the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closest to the correlation search log as the correlation degree of the water affairs and government affairs data; The determining the relevance of the water affairs government affairs data according to the semantic distance between the relevance search log and the first water affairs government affairs data reference relevance index value includes: When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is greater than the average of the first semantic distance and the second semantic distance, determining that the correlation is the approval process correlation; When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is not greater than the average of the first semantic distance and the second semantic distance, determining that the association degree is a water environment protection association degree; The first semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with the approval process, and the second semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with water environment protection.

3. The intelligent retrieval method based on water affairs government data according to claim 2 is characterized in that: Also includes: When the attribution degree of the associated search log of the to-be-searched file of the water affairs government data is greater than or equal to the third threshold, the associated search log whose number of to-be-searched files belonging to the search index of the similar semantic matching interval value is not greater than the first threshold is added to the associated search log library of the to-be-searched files of the water affairs government data; When the duration of the association degree being the water environment protection association degree is greater than or equal to the second threshold, the association degree is controlled by using one or more control strategies including the following operations: unstructured data low-proportion operation, approval process association clarification operation; The control strategy is determined according to the water environment protection order of the water affairs government data, and the water environment protection order is determined according to the association retrieval log and the similar semantic matching interval value corresponding to the association degree; re-determining the first water environment protection order of the water affairs government data after the first period, the first period corresponding to the first water environment protection order; The operations in the control strategy are selected randomly.

4. An intelligent retrieval system based on water affairs government data, characterized in that: include: A collection unit, used for collecting associated search logs of files to be searched for water affairs government data, wherein the associated search logs include multiple search indicators; A determination unit, configured to determine, when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the plurality of retrieval indexes is greater than a first threshold, the relevance corresponding to the similar semantic matching interval value as the relevance of the water affairs government affairs data; The multiple search indicators are used to indicate the proportion of unstructured data and / or index indicators; The relevance includes the approval process relevance and the water environment protection relevance, and the similar semantic matching interval value corresponds to the approval process relevance or the water environment protection relevance; A computing unit, the computing unit being configured to: Based on the associated search log library of the to-be-searched files of the water affairs government affairs data, classification is performed to obtain a set of water affairs government affairs data files corresponding to the degree of association, wherein the associated search log library of the to-be-searched files of the water affairs government affairs data contains the associated search logs of the to-be-searched files of the water affairs government affairs data obtained in advance; Performing information association filtering on the water affairs government affairs data file set to determine whether the information association of the water affairs government affairs data file set is a positive association or a non-positive association; Determining a similar semantic matching interval value corresponding to the degree of association according to the information association of the water affairs government affairs data file set; The computing unit is specifically used for: Dividing the associated search logs in the water affairs government affairs data file set into keyword nodes to obtain a plurality of keyword nodes, wherein each of the plurality of keyword nodes has the same number of keywords; The keyword node with the largest number of keywords among the multiple keyword nodes is used as the mean value interval of the water affairs government affairs data file set; When the number of keywords of the water affairs government affairs data file set in the first interval is equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a positive association; When the number of keywords of the water affairs government affairs data file set in the first interval is not equal to the number of keywords of the water affairs government affairs data file set in the second interval, the information association of the water affairs government affairs data file set is a non-positive association; The first interval and the second interval are obtained by dividing the information interval of the water affairs government affairs data file set according to the mean interval.

5. The intelligent retrieval system based on water affairs government data according to claim 4 is characterized in that: The determination unit is further configured to determine the relevance of the water affairs government data according to the semantic distance between the associated search log and the first water affairs government data reference associated index value when the number of to-be-retrieved files of the retrieval index belonging to the similar semantic matching interval value among the multiple retrieval indexes is not greater than the first threshold value; The determining unit is specifically configured to: Of the two first water affairs and government affairs data reference correlation index values, the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closer to the correlation search log is determined as the correlation degree of water affairs and government affairs data; or, Among three or more of the first water affairs and government affairs data reference correlation index values, determine the correlation degree corresponding to the first water affairs and government affairs data reference correlation index value closest to the correlation search log as the correlation degree of the water affairs and government affairs data; The determining unit is specifically configured to: When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is greater than the average of the first semantic distance and the second semantic distance, determining that the correlation is the approval process correlation; When the absolute value of the semantic distance between the first semantic distance and the second semantic distance is not greater than the average of the first semantic distance and the second semantic distance, determining that the association degree is a water environment protection association degree; The first semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with the approval process, and the second semantic distance is the semantic distance between the associated retrieval log and the first water affairs government data reference associated index value corresponding to the degree of association with water environment protection.

6. The intelligent retrieval system based on water affairs government data according to claim 5 is characterized in that: Also includes: An information base updating unit is used to: when the attribution degree of the associated retrieval log of the to-be-retrieved file of the water affairs government affairs data is greater than or equal to a third threshold, add the associated retrieval log whose number of to-be-retrieved files belonging to the retrieval index of the similar semantic matching interval value is not greater than the first threshold to the associated retrieval log library of the to-be-retrieved files of the water affairs government affairs data; A control unit, for controlling the correlation degree by using one or more control strategies including the following operations when the duration of the correlation degree being the water environment protection correlation degree is greater than or equal to a second threshold: unstructured data low-proportion operation, approval process correlation clarification operation; The control strategy is determined according to the water environment protection order of the water affairs government data, and the water environment protection order is determined according to the association retrieval log and the similar semantic matching interval value corresponding to the association degree; The control unit is further used to re-determine a first water environment protection order of the water affairs government data after a first period, the first period corresponding to the first water environment protection order; The operations in the control strategy are randomly selected by the control unit.

Images