CN111274349A - Public security data hierarchical indexing method and device based on information entropy - Google Patents

Abstract

Embodiments of the present invention provide a hierarchical indexing method and device for public safety data based on information entropy. The method includes: obtaining keywords for public safety data to be queried; indexing the keywords according to a preset index structure; wherein, The preset index structure is a hierarchical index structure determined based on the amount of mutual information represented by information entropy and representing the degree of association between keywords. The device executes the above method. The public safety data hierarchical indexing method and device based on information entropy provided by the embodiments of the present invention can index the keywords of public safety data through a hierarchical index structure determined by the amount of mutual information represented by information entropy, which can improve public safety data indexing. indexing speed.

Description

A method and device for hierarchical indexing of public safety data based on information entropy

technical field

The present invention relates to the technical field of data indexing, in particular to a method and device for hierarchical indexing of public safety data based on information entropy.

Background technique

Internet social networks and public websites contain a large amount of public safety data. However, the collected data is disorganized and in a disordered state. Querying these data will consume too much manpower and material resources. Existing data file systems have bottlenecks in the storage and retrieval of a large amount of multi-source heterogeneous data. The data is uniformly stored and managed by the data center. When a large amount of data is stored, the data processing efficiency is not high. Therefore, it is of great significance to propose a hierarchical indexing method suitable for fast retrieval of public safety data.

SUMMARY OF THE INVENTION

In view of the problems existing in the prior art, the embodiments of the present invention provide a method and device for hierarchical indexing of public security data based on information entropy.

An embodiment of the present invention provides a method for hierarchical indexing of public security data based on information entropy, including:

Get keywords for public safety data to be queried;

The keywords are indexed according to a preset index structure; wherein, the preset index structure is a hierarchical index structure determined according to the amount of mutual information represented by the information entropy and characterizing the degree of association between the keywords.

Wherein, the indexing of the keywords according to the preset index structure includes:

From the root node of the preset index structure, the keywords are traversed step by step and indexed.

Wherein, pre-constructing the preset index structure specifically includes:

Acquiring word frequency tables respectively represented by each root node keyword; the word frequency table records the word frequencies of each data keyword belonging to the same root node keyword;

According to the number of word frequency tables corresponding to each root node keyword and the word frequency number of each data keyword belonging to the same root node keyword, determine the information entropy corresponding to each data keyword respectively;

Determine the mutual information amount according to the information entropy corresponding to each data keyword respectively;

Determine that each root node keyword is a root node in the preset index structure, and according to the mutual information, determine that the data keyword corresponding to the mutual information is a hierarchical node under the root node, and according to All hierarchical nodes build the preset index structure.

Wherein, determining the information entropy corresponding to each data keyword according to the number of word frequency tables corresponding to each root node keyword and the word frequency of each data keyword belonging to the same root node keyword, including:

Determine the weights corresponding to all data keywords belonging to the same root node keyword according to the number of word frequency tables corresponding to each root node keyword;

According to the word frequency of each data keyword belonging to the same root node keyword, determine the probability of each data keyword appearing in the word frequency table represented by its corresponding root node keyword;

According to the weight and the probability, the information entropy corresponding to each data keyword is determined.

Wherein, determining the information entropy corresponding to each data keyword according to the weight and the probability includes:

Calculate the information entropy corresponding to each data keyword according to the following formula:

Wherein, H(X) is the information entropy corresponding to the keyword x, λ is the weight, P(x) is the probability, x is the keyword, and X is the keyword set including the word frequency table .

Wherein, determining the mutual information amount according to the information entropy corresponding to each data keyword includes:

The mutual information is determined according to the following formula:

I(X;Y)=H(Y)-H(Y|X)

Wherein, I(X; Y) is the amount of mutual information, H(Y) is the information entropy corresponding to the keyword y associated with the keyword x, and H(Y|X) is calculated according to the following formula:

Among them, H(Y|X) is the expectation of y for x, p(x,y) is the probability that the keyword x and the keyword y appear at the same time in the word frequency table represented by the corresponding root node keyword, p( y|x) is the probability that the keyword y appears under the condition that the keyword x appears in the word frequency table represented by the corresponding root node keyword.

Wherein, according to the amount of mutual information, determining the data keyword corresponding to the amount of mutual information is a hierarchical node under the root node, and constructing the preset index structure according to all hierarchical nodes, including:

Arrange the mutual information in the order of the mutual information numerical value of the mutual information, and use the keywords corresponding to the first n mutual information as the next-level hierarchical node of the root node;

The keywords corresponding to the m mutual information amounts after the first n mutual information amounts are regarded as the next-level hierarchical node of the next-level hierarchical node, and the execution is repeated until the traversal of the keywords corresponding to all the mutual information amounts is completed.

An embodiment of the present invention provides a public security data hierarchical indexing device based on information entropy, including:

an acquisition unit, used to acquire the keywords of the public safety data to be queried;

an indexing unit, configured to index the keywords according to a preset index structure; wherein, the preset index structure is a hierarchical index determined according to the amount of mutual information represented by the information entropy and characterizing the degree of association between the keywords structure.

An embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein,

When the processor executes the program, the following method steps are implemented:

Get keywords for public safety data to be queried;

The keywords are indexed according to a preset index structure; wherein, the preset index structure is a hierarchical index structure determined according to the amount of mutual information represented by the information entropy and characterizing the degree of association between the keywords.

An embodiment of the present invention provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following method steps are implemented:

Get keywords for public safety data to be queried;

The keywords are indexed according to a preset index structure; wherein, the preset index structure is a hierarchical index structure determined according to the amount of mutual information represented by the information entropy and characterizing the degree of association between the keywords.

The method and device for hierarchical indexing of public security data based on information entropy provided by the embodiments of the present invention index the keywords of public security data through the hierarchical index structure determined by the mutual information amount represented by information entropy, which can improve the performance of public security data indexing. indexing speed.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a flowchart of an embodiment of a method for hierarchical indexing of public safety data based on information entropy according to the present invention;

FIG. 2 is a schematic diagram of a preset index structure according to an embodiment of the present invention;

3 is a schematic structural diagram of an embodiment of an apparatus for hierarchical indexing of public safety data based on information entropy according to the present invention;

FIG. 4 is a schematic diagram of a physical structure of an electronic device according to an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

1 is a flow chart of an embodiment of a method for grading and indexing public safety data based on information entropy according to the present invention. As shown in FIG. 1 , a method for grading and indexing public safety data based on information entropy provided by an embodiment of the present invention includes the following steps:

S101: Obtain a keyword of the public safety data to be queried.

Specifically, the keyword of the public safety data to be queried is obtained. It may be a computer device that performs the method steps, and may specifically be a server. Public safety data includes, but is not limited to, natural disaster data, such as earthquake data, typhoon data, etc. in a certain area. Referring to the above examples, keywords may include earthquakes and typhoons, etc., and may also specifically be natural earthquakes and artificial earthquakes, etc. Further, It can also be specifically tectonic earthquakes, volcanic earthquakes and collapse earthquakes in natural earthquakes.

S102: Index the keywords according to a preset index structure; wherein, the preset index structure is a hierarchical index structure determined according to the amount of mutual information represented by information entropy and representing the degree of association between keywords.

Specifically, the keywords are indexed according to a preset index structure, wherein the preset index structure is a hierarchical index structure determined according to the amount of mutual information represented by information entropy and characterizing the degree of association between the keywords. FIG. 2 is a schematic diagram of a preset index structure according to an embodiment of the present invention. As shown in FIG. 2, N0 is the root node of the preset index structure, which specifically includes k5 and k30. Referring to the above example, k5 can correspond to an earthquake, and k30 can correspond to a typhoon. first grade. Taking earthquakes as an example, natural earthquakes, artificial earthquakes and earthquakes are more closely related, k14 can correspond to natural earthquakes, k21 can correspond to artificial earthquakes, k5, k14 and k21 are used as the second classification, tectonic earthquakes, volcanic earthquakes, collapse earthquakes and natural earthquakes. The degree of correlation between earthquakes is stronger, k16 can correspond to tectonic earthquakes, k19 can correspond to volcanic earthquakes, k15 can correspond to collapse earthquakes, k16, k19 and k15 can be used as the third classification.

That is, the above preset index structure is a three-level index structure, wherein N0 corresponds to the first hierarchical index structure, N1 and N2 correspond to the second hierarchical index structure, and N3 to N8 correspond to the third hierarchical index structure.

Since the information entropy solves the problem of quantitative measurement of information, the preset index structure in the embodiment of the present invention includes the amount of information carried by the data, and at the same time, the preset index structure also includes the information association represented by the amount of mutual information. degree.

The indexing the keywords according to the preset index structure may specifically include: traversing the keywords step by step starting from the root node of the preset index structure, and performing the indexing. That is, it is assumed that when a user searches for a keyword, the algorithm starts searching from the root node according to the preset index structure, starting from N0, and passes through N1 to query the keyword in the node. If the required keyword exists, it will return to the child node of the keyword. All data, the data display and sorting method can be displayed according to the value of mutual information; if the required keyword does not exist in the N1 node, search for the keyword in N3, if there is the required keyword, return the keyword of the keyword All data under the child node, and so on, will not be repeated.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiment of the present invention indexes the keywords of public safety data through a hierarchical index structure determined by the mutual information amount represented by information entropy, which can improve the accuracy of public safety data indexing. indexing speed.

On the basis of the foregoing embodiment, the indexing of the keywords according to the preset index structure includes:

Specifically, starting from the root node of the preset index structure, the keywords are traversed step by step and indexed. The above description may be referred to, and details are not repeated here.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiment of the present invention can further improve the indexing speed when indexing public safety data.

On the basis of the above-mentioned embodiment, the method further includes: constructing the preset index structure in advance, which specifically includes:

Specifically, a word frequency table represented by each root node keyword is obtained; the word frequency table records the word frequency of each data keyword belonging to the same root node keyword. Referring to the above example, earthquake and typhoon are two different root node keywords. Taking earthquake as an example, the word frequency table represented by earthquake records the word frequencies of natural earthquakes and artificial earthquakes, and can also include tectonic earthquakes, volcanic earthquakes and collapses. The word frequency of earthquakes. The same root node keyword can correspond to one or more word frequency tables, and the same data source can correspond to one word frequency table. Referring to the above example, if there are two data sources for earthquakes, there are two word frequency tables, and if there are two data sources for typhoons There are three, corresponding to three word frequency tables.

Specifically, according to the number of word frequency tables corresponding to each root node keyword and the word frequency of each data keyword belonging to the same root node keyword, determine the information entropy corresponding to each data keyword respectively; specifically, it may include:

According to the number of word frequency tables corresponding to each root node keyword, the weights corresponding to all data keywords belonging to the same root node keyword are determined; referring to the above example, earthquake corresponds to two word frequency tables, typhoon corresponds to three word frequency tables, that is, file The system includes a total of five word frequency tables. Therefore, the corresponding weight of all data keywords belonging to the same root node keyword "earthquake" is 2/5. Similarly, all data keywords belonging to the same root node keyword "typhoon" The corresponding weight is 3/5.

According to the word frequency of each data keyword belonging to the same root node keyword, determine the probability of each data keyword appearing in the word frequency table represented by its corresponding root node keyword; For Table 1 and Table 2, for Table 1, the word frequencies of natural earthquakes and artificial earthquakes are 40 and 60, respectively, then the probability of the data keyword "natural earthquake" is 0.4, and the probability of the data keyword "artificial earthquake" is 0.6; for Table 2, the word frequencies of natural earthquakes and artificial earthquakes are 30 and 70, respectively, the probability of the data keyword "natural earthquake" is 0.3, and the probability of the data keyword "artificial earthquake" is 0.7.

According to the weight and the probability, the information entropy corresponding to each data keyword is determined, which may specifically include:

Calculate the information entropy corresponding to each data keyword according to the following formula:

Wherein, H(X) is the information entropy corresponding to the keyword x, λ is the weight, P(x) is the probability, x is the keyword, and X is the keyword set including the word frequency table , referring to the above example, for the "natural earthquake" corresponding to "earthquake", there are:

H(X) = -0.4 x (0.4 log ₂ 0.4 + 0.3 log ₂ 0.3).

For the "artificial earthquake" corresponding to "earthquake", there are:

H(Y) = -0.6 x (0.6 log ₂ 0.6 + 0.7 log ₂ 0.7).

It should be noted that: in general, if the information entropy H(X) of a certain data keyword is smaller, it indicates that the amount of data information provided by the data keyword is more, and the uncertainty is less. On the contrary, if the information entropy H(X) of a certain data keyword is larger, it indicates that the amount of data information provided by the data keyword is less, the uncertainty is greater, and the effect in the data set is greater. Small.

Specifically, according to the information entropy corresponding to each data keyword, the mutual information amount is determined; specifically, the amount of mutual information may include:

The mutual information is determined according to the following formula:

I(X;Y)=H(Y)-H(Y|X)

Wherein, I(X; Y) is the amount of mutual information, H(Y) is the information entropy corresponding to the keyword y associated with the keyword x, and H(Y|X) is calculated according to the following formula:

Among them, H(Y|X) is the expectation of y for x, p(x,y) is the probability that the keyword x and the keyword y appear at the same time in the word frequency table represented by the corresponding root node keyword, p( y|x) is the probability that the keyword y appears under the condition that the keyword x appears in the word frequency table represented by the corresponding root node keyword. The calculation of p(x, y) and p(y|x) is a mature technology in the art, and will not be repeated here.

Among them, I(X; Y)=H(Y)-H(Y|X) can be obtained by transforming according to the following formula:

Among them, P(X,Y) represents the probability of the keywords x and y appearing at the same time, P(X), P(Y) represent the probability of the keyword x and the keyword y appearing respectively, the specific transformation method is the mature technology in the field ,No longer.

The amount of mutual information can indicate the strength of the correlation between two keywords. I(X; Y) represents the amount by which the uncertainty in Y is reduced due to the presence of X. The larger the I, the smaller the uncertainty of the appearance of Y after the appearance of X, that is, the appearance of Y is likely to appear, which means that the relationship between X and Y is closer. Therefore, when looking at data containing keyword X, it is likely that you also need to look at data containing keyword Y.

Specifically, each root node key is determined as a root node in the preset index structure, and according to the mutual information, the data key corresponding to the mutual information is determined as a hierarchical node under the root node , and construct the preset index structure according to all hierarchical nodes, which may specifically include:

Arrange the mutual information in the order of the mutual information numerical value of the mutual information, and use the keywords corresponding to the first n mutual information as the next-level hierarchical node of the root node; that is, according to the mutual information The mutual information values are arranged in order from large to small. Referring to FIG. 2 , the value of n is 3.

The keywords corresponding to the m mutual information amounts after the first n mutual information amounts are regarded as the next-level hierarchical node of the next-level hierarchical node, and the execution is repeated until the traversal of the keywords corresponding to all the mutual information amounts is completed. Referring to Figure 2, the value of m is 6. Referring to Figure 2, at this time, the keywords corresponding to all the mutual information are traversed and completed. Therefore, the above steps are not repeated. If the keywords corresponding to all the mutual information are not traversed and completed , then continue to perform the step of using the keywords corresponding to the r mutual information quantities after the first m mutual information quantities as the next-level hierarchical node, until the traversal of the keywords corresponding to all the mutual information quantities is completed.

The purpose of the multi-layer hierarchical index is to avoid full table scans, and it is an effective way to improve the efficiency of social and public security risk data management and query. In the multi-layer hierarchical index structure, there is no one-to-one mapping between local data nodes and global indexes, but a specific data node is located through the global index, and then the data is manipulated through the local index of the data node.

The embodiment of the present invention adopts the B+ tree as the data index structure. Among them, the leaf node of the B+ tree stores the relevant public security file information, the internal node is used to store the key of the file, and the key of the internal node helps to complete the indexing process. Each node in the tree stores an information entropy H, and the structure of node N is:

N={num,children[m],H}

Among them, num is the number of the node N; children[m] is the pointer to the child node, m is the order of the B+ tree; H is the vector that stores the information entropy of the node. It should be noted that: for the root node, H stores information entropy, and for hierarchical nodes, H stores information entropy and mutual information.

The index based on B+ tree is completed by inserting data. Each time the data is inserted, it will be inserted into the leaf node. The order of data storage is based on the size of the mutual information value calculated in the previous step. storage. The pointers to the files in the B+ tree are stored in the leaf nodes, and the key value of the upper node is the key shared by multiple leaf nodes.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiment of the present invention helps to improve the indexing speed when indexing public safety data by constructing a preset index structure.

On the basis of the above embodiment, determining the information entropy corresponding to each data keyword according to each root node keyword and the word frequency of each data keyword belonging to the same root node keyword includes:

Specifically, according to the number of word frequency tables corresponding to each root node keyword, the weights corresponding to all data keywords belonging to the same root node keyword are determined; the above description can be referred to, and details are not repeated here.

Specifically, according to the word frequency of each data keyword belonging to the same root node keyword, the probability of each data keyword appearing in the word frequency table represented by its corresponding root node keyword is determined; refer to the above description, and will not repeat it. .

Specifically, the information entropy corresponding to each data keyword is determined according to the weight and the probability. The above description may be referred to, and details are not repeated here.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiments of the present invention further helps to improve the indexing speed when indexing public safety data.

On the basis of the foregoing embodiment, determining the information entropy corresponding to each data keyword according to the weight and the probability includes:

Specifically, the information entropy corresponding to each data keyword is calculated according to the following formula:

Wherein, H(X) is the information entropy corresponding to the keyword x, λ is the weight, P(x) is the probability, x is the keyword, and X is the keyword set including the word frequency table . The above description may be referred to, and details are not repeated here.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiments of the present invention further helps to improve the indexing speed when indexing public safety data.

On the basis of the foregoing embodiment, determining the mutual information amount according to the information entropy corresponding to each data keyword includes:

Specifically, the mutual information amount is determined according to the following formula:

I(X;Y)=H(Y)-H(Y|X)

Wherein, I(X; Y) is the amount of mutual information, H(Y) is the information entropy corresponding to the keyword y associated with the keyword x, and H(Y|X) is calculated according to the following formula:

Among them, H(Y|X) is the expectation of y for x, p(x,y) is the probability that the keyword x and the keyword y appear at the same time in the word frequency table represented by the corresponding root node keyword, p( y|x) is the probability that the keyword y appears under the condition that the keyword x appears in the word frequency table represented by the corresponding root node keyword. The above description may be referred to, and details are not repeated here.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiments of the present invention further helps to improve the indexing speed when indexing public safety data.

On the basis of the above embodiment, the data key corresponding to the mutual information is determined as a hierarchical node under the root node according to the mutual information, and the preset is constructed according to all hierarchical nodes Index structure, including:

Specifically, the mutual information quantities are arranged in the order of the mutual information quantities of the mutual information quantities, and the keywords corresponding to the first n mutual information quantities are used as the next-level hierarchical nodes of the root node; refer to the above description, and will not repeat them.

Specifically, the keywords corresponding to the m mutual information amounts after the first n mutual information amounts are used as the next-level hierarchical node of the next-level hierarchical node, and the execution is repeated until the traversal is completed. keywords. The above description may be referred to, and details are not repeated here.

The method for hierarchical indexing of public safety data based on information entropy provided by the embodiments of the present invention further helps to improve the indexing speed when indexing public safety data.

When using the method provided by the embodiment of the present invention to store the public safety data set, it has the following advantages:

1. Considering the weight of the root node keyword in the file system, the information importance of the file is sorted according to the keyword information entropy, emphasizing the importance of key information, and reducing the processing of useless information;

2. Calculate the amount of mutual information between keywords, understand the degree of correlation between keywords, and be able to clarify the degree of closeness between two pieces of information;

3. The index structure adopts the B+ tree. Compared with the traditional storage mode, the B+ tree makes more full use of the node space and makes the query speed more stable; at the same time, the B+ tree only needs to traverse all the leaf nodes to traverse the entire tree. Useful for full document scanning.

FIG. 3 is a schematic structural diagram of an embodiment of an apparatus for grading and indexing public safety data based on information entropy according to the present invention. As shown in FIG. 3 , an embodiment of the present invention provides an apparatus for grading and indexing public safety data based on information entropy, including an obtaining unit 301 and a Indexing unit 302, where:

The obtaining unit 301 is used for obtaining the keywords of the public safety data to be queried; the indexing unit 302 is used for indexing the keywords according to a preset index structure; A hierarchical index structure determined by the mutual information of the degree of association between keywords.

Specifically, the obtaining unit 301 is configured to obtain the keywords of the public safety data to be queried; the indexing unit 302 is configured to index the keywords according to a preset index structure; wherein, the preset index structure is based on the information entropy represented by the information entropy. It is a hierarchical index structure determined by the amount of mutual information that characterizes the degree of association between keywords.

The apparatus for hierarchical indexing of public safety data based on information entropy provided by the embodiment of the present invention indexes the keywords of public safety data through a hierarchical index structure determined by the mutual information amount represented by information entropy, which can improve the accuracy of public safety data indexing. indexing speed.

The information entropy-based public security data hierarchical indexing apparatus provided in the embodiment of the present invention can be specifically used to execute the processing flow of the above method embodiments, and its functions are not repeated here, and reference may be made to the detailed description of the above method embodiments.

FIG. 4 is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. As shown in FIG. 4 , the electronic device includes: a processor (processor) 401, a memory (memory) 402, and a bus 403;

The processor 401 and the memory 402 communicate with each other through the bus 403;

The processor 401 is configured to call the program instructions in the memory 402 to execute the methods provided by the above method embodiments, for example, including: obtaining the keywords of the public safety data to be queried; The keywords are indexed; wherein, the preset index structure is a hierarchical index structure determined according to the mutual information amount represented by the information entropy and characterizing the degree of association between the keywords.

This embodiment discloses a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer program The methods provided by the above method embodiments can be performed, for example, including: obtaining the keywords of the public safety data to be queried; indexing the keywords according to a preset index structure; wherein, the preset index structure is based on the information provided by the The entropy represents the hierarchical index structure determined by the mutual information that characterizes the degree of association between keywords.

This embodiment provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the methods provided by the foregoing method embodiments, for example, including : obtain the keywords of the public safety data to be queried; index the keywords according to a preset index structure; wherein, the preset index structure is based on the relationship between the degree of association between the keywords represented by the information entropy A hierarchical index structure determined by the amount of information.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by program instructions related to hardware, the aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, execute It includes the steps of the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on this understanding, the above-mentioned technical solutions can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic A disc, an optical disc, etc., includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be The technical solutions described in the foregoing embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A public security data hierarchical index method based on information entropy is characterized by comprising the following steps:

acquiring keywords of public security data to be inquired;

indexing the keywords according to a preset indexing structure; the preset index structure is a hierarchical index structure determined according to mutual information quantity which is represented by information entropy and represents the association degree between the keywords.

2. The hierarchical indexing method for public safety data based on information entropy as claimed in claim 1, wherein the indexing the keywords according to a preset indexing structure comprises:

and traversing the keywords step by step from the root node of the preset index structure, and indexing.

3. The method for hierarchical indexing of public security data based on information entropy of claim 1, further comprising:

the pre-constructing of the preset index structure specifically includes:

acquiring a word frequency table respectively represented by each root node keyword; the word frequency table records the word frequency number of each data keyword belonging to the same root node keyword;

determining information entropy respectively corresponding to each data keyword according to the number of word frequency tables corresponding to each root node keyword and the number of word frequencies of each data keyword belonging to the same root node keyword;

determining the mutual information quantity according to the information entropy corresponding to each data keyword;

and determining each root node keyword as a root node in the preset index structure, determining the data keyword corresponding to the mutual information amount as a hierarchical node under the root node according to the mutual information amount, and constructing the preset index structure according to all the hierarchical nodes.

4. The method for hierarchical indexing of public safety data based on information entropy as claimed in claim 3, wherein the determining the information entropy corresponding to each data keyword according to the number of word frequency tables corresponding to each root node keyword and the number of word frequencies of each data keyword belonging to the same root node keyword comprises:

determining weights corresponding to all data keywords belonging to the same root node keyword according to the number of the word frequency tables corresponding to the root node keywords;

determining the probability of each data keyword appearing in the word frequency table represented by the root node keyword corresponding to each data keyword according to the word frequency number of each data keyword belonging to the same root node keyword;

and determining the information entropy corresponding to each data keyword according to the weight and the probability.

5. The method for hierarchical indexing of public security data based on information entropy of claim 4, wherein the determining the information entropy corresponding to each data keyword according to the weight and the probability comprises:

and calculating the information entropy corresponding to each data keyword according to the following formula:

wherein h (X) is an information entropy corresponding to the keyword X, λ is the weight, p (X) is the probability, X is the keyword, and X is a keyword set including the word frequency table.

6. The method for hierarchical indexing of public security data based on information entropy of claim 3, wherein the determining the mutual information amount according to the information entropy corresponding to each data keyword respectively comprises:

determining the mutual information quantity according to the following formula:

I(X；Y)＝H(Y)-H(Y|X)

wherein I (X; Y) is the mutual information quantity, H (Y) is the information entropy corresponding to the keyword Y associated with the keyword X, and H (Y | X) is calculated according to the following formula:

where H (Y | X) is the expectation of Y to X, p (X, Y) is the probability that the keyword X and the keyword Y appear simultaneously in the word frequency table represented by the root node keyword corresponding thereto, and p (Y | X) is the probability that the keyword Y appears under the condition that the keyword X appears in the word frequency table represented by the root node keyword corresponding thereto.

7. The hierarchical indexing method for public safety data based on information entropy of claim 3, wherein the determining, according to the mutual information amount, data keywords corresponding to the mutual information amount as hierarchical nodes under the root node and constructing the preset index structure according to all the hierarchical nodes comprises:

arranging the mutual information quantities according to the numerical value of the mutual information quantities, and taking keywords corresponding to the first n mutual information quantities as next-level hierarchical nodes of the root node;

and taking the keywords corresponding to m mutual information quantities after the first n mutual information quantities as the next-level hierarchical node of the next-level hierarchical node, and repeatedly executing until all the keywords corresponding to the mutual information quantities are traversed.

8. A public security data hierarchical index device based on information entropy is characterized by comprising:

the acquisition unit is used for acquiring keywords of the public security data to be inquired;

the index unit is used for indexing the keywords according to a preset index structure; the preset index structure is a hierarchical index structure determined according to mutual information quantity which is represented by information entropy and represents the association degree between the keywords.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the processor executes the program.

10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.

Images