阅读说明：本技术 政策文本关联性分析方法及系统 (Policy text relevance analysis method and system ) 是由 孙璐 李向前 刘巍 雷吉成 许卡 巢文涵 郝雅琦 张金言 于 2020-12-15 设计创作，主要内容包括：本发明实施例提供一种政策文本关联性分析方法及系统。其中,方法包括：获取待进行关联性分析的两个政策文本；判断两个政策文本之间是否具有上下级关系,若是,则将不同的政策文本中的任意两个属性相同的单句组成一个单句对,得到若干单句对；对于每一单句对,判断单句对中的两个单句是否相似,若是,则根据两个单句所属的政策文本类别,确定两个单句之间的关联关系并作为单句对对应的关联关系；根据若干单句对对应的若干关联关系,确定两个政策文本之间的关联关系。本发明实施例提供的方法及系统,通过自然语言处理技术,实现政策文本之间的关联性的自动分析,填补了政策文本之间关联性分析的空白。(The embodiment of the invention provides a method and a system for analyzing policy text relevance. The method comprises the following steps: acquiring two policy texts to be subjected to relevance analysis; judging whether the two policy texts have a top-bottom relation, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs; for each single sentence pair, judging whether two single sentences in the single sentence pair are similar, if so, determining the association relation between the two single sentences according to the policy text types to which the two single sentences belong and taking the association relation as the corresponding association relation of the single sentence pair; and determining the association relationship between the two policy texts according to the association relationships corresponding to the single sentence pairs. The method and the system provided by the embodiment of the invention realize the automatic analysis of the relevance between the policy texts through the natural language processing technology, and fill the blank of the relevance analysis between the policy texts.)

1. A method for analyzing relevance of policy text is characterized by comprising the following steps:

acquiring two policy texts to be subjected to relevance analysis;

judging whether the two policy texts have a superior-subordinate relation or not, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs;

for each single sentence pair, judging whether two single sentences in the single sentence pair are similar, if so, determining an association relation between the two single sentences according to the policy text types to which the two single sentences belong, and taking the association relation as the association relation corresponding to the single sentence pair;

and determining the association relationship between the two policy texts according to a plurality of association relationships corresponding to the plurality of single sentence pairs.

2. The method of claim 1, wherein determining whether the two policy texts have a context relationship comprises:

judging whether the two policy texts belong to the same field;

if yes, judging whether the two policy texts are issued by the same mechanism or not;

if yes, judging that the two policy texts have a superior-subordinate relation; if not, judging whether the two policy texts are respectively issued by the center and the local;

if yes, judging that the two policy texts have a superior-subordinate relation; if not, judging whether the two policy texts are respectively issued by a superior mechanism and a subordinate mechanism;

if yes, judging that the two policy texts have a superior-subordinate relation.

3. The method of claim 1, wherein any two sentences with the same attribute in different policy texts are combined into a sentence pair, and the method further comprises:

for each single sentence in the two policy texts, inputting the single sentence into a trained neural network model, and acquiring the policy text type to which the single sentence output by the trained neural network model belongs and the attribute of the single sentence;

the trained neural network model is obtained by training based on a training set, wherein the training set comprises a plurality of sample single sentences, sample policy text categories to which the sample single sentences belong and sample attributes of the sample single sentences.

4. The method of claim 3 wherein the neural network model is a BERT model.

5. The method of claim 1, wherein determining whether two of the single sentences in the pair of single sentences are similar comprises:

and respectively carrying out syntactic analysis on the two single sentences in the single sentence pair, extracting verbs and corresponding nouns in each single sentence, and judging that the two single sentences are similar if the verbs and the nouns of the two single sentences are matched.

6. The method of claim 1, wherein determining whether two of the single sentences in the pair of single sentences are similar comprises:

and calculating the similarity between the two single sentences by adopting bleu1 or word2vec sentence vectors, and if the similarity is greater than a preset threshold value, judging that the two single sentences are similar.

7. The method of claim 1, wherein determining the association between two policy texts according to a plurality of associations corresponding to a plurality of sentence pairs comprises:

classifying a plurality of association relations corresponding to the plurality of single sentences to obtain a plurality of association relation groups; the incidence relations in the same incidence relation group are the same, and the incidence relations in different incidence relation groups are different;

and counting the number of the association relations in each association relation group, and taking any association relation in the association relation group with the largest number of the association relations as the association relation between the two policy texts.

8. A policy text relevance analysis system, comprising:

the policy text acquisition module is used for acquiring two policy texts to be subjected to relevance analysis;

the single sentence pair obtaining module is used for judging whether the two policy texts have a top-bottom relationship or not, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs;

a single sentence association relation obtaining module, configured to determine, for each single sentence pair, whether two single sentences in the single sentence pair are similar, and if so, determine an association relation between the two single sentences according to policy text categories to which the two single sentences belong, and use the association relation as an association relation corresponding to the single sentence pair;

and the policy text association relation acquisition module is used for determining the association relation between the two policy texts according to a plurality of association relations corresponding to the plurality of single sentence pairs.

9. An electronic device comprising a memory and a processor; wherein the memory has stored therein a computer program; the processor configured to execute the computer program to implement the policy text relevance analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the policy text relevance analysis method according to any one of claims 1-7.

Technical Field

The invention relates to the technical field of computers, in particular to a method and a system for analyzing relevance of policy texts.

Background

With the rapid development of computer technologies such as internet, artificial intelligence, big data and the like in various industries, more and more policy texts in the computer field are promulgated to standardize and promote the development of the computer technologies.

Currently, research on the policy texts focuses more on a single policy text, which is only to extract topics and keywords from the policy text to analyze emotional tendency, application fields and the like of the policy text, and ignores the association between the policy texts and the inheritance and supplement of the policy text in the formulation. However, the relevance between the analysis policy texts is beneficial to helping a policy maker to better make a new round of policy texts, is beneficial to scientifically analyzing the development context change of the policy texts by a policy researcher, and is beneficial to a policy applicator to better learn the policy texts.

Since the association between policy texts is not currently studied, it is highly desirable to provide a method capable of analyzing the association between policy texts.

Disclosure of Invention

Aiming at the problems in the prior art, the embodiment of the invention provides a policy text relevance analysis method and system.

In a first aspect, an embodiment of the present invention provides a policy text relevance analysis method, including:

acquiring two policy texts to be subjected to relevance analysis;

judging whether the two policy texts have a superior-subordinate relation or not, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs;

for each single sentence pair, judging whether two single sentences in the single sentence pair are similar, if so, determining an association relation between the two single sentences according to the policy text types to which the two single sentences belong, and taking the association relation as the association relation corresponding to the single sentence pair;

and determining the association relationship between the two policy texts according to a plurality of association relationships corresponding to the plurality of single sentence pairs.

In some embodiments, determining whether there is a contextual relationship between two of the policy texts comprises:

judging whether the two policy texts belong to the same field;

if yes, judging whether the two policy texts are issued by the same mechanism or not;

if yes, judging that the two policy texts have a superior-subordinate relation; if not, judging whether the two policy texts are respectively issued by the center and the local;

if yes, judging that the two policy texts have a superior-subordinate relation; if not, judging whether the two policy texts are respectively issued by a superior mechanism and a subordinate mechanism;

if yes, judging that the two policy texts have a superior-subordinate relation.

In some embodiments, any two sentences with the same attribute in different policy texts are combined into a single sentence pair, and the method further includes:

for each single sentence in the two policy texts, inputting the single sentence into a trained neural network model, and acquiring the policy text type to which the single sentence output by the trained neural network model belongs and the attribute of the single sentence;

the trained neural network model is obtained by training based on a training set, wherein the training set comprises a plurality of sample single sentences, sample policy text categories to which the sample single sentences belong and sample attributes of the sample single sentences.

In some embodiments, the neural network model is a BERT model.

In some embodiments, determining whether two of the single sentences in the pair of single sentences are similar comprises:

and respectively carrying out syntactic analysis on the two single sentences in the single sentence pair, extracting verbs and corresponding nouns in each single sentence, and judging that the two single sentences are similar if the verbs and the nouns of the two single sentences are matched.

In some embodiments, determining whether two of the single sentences in the pair of single sentences are similar comprises:

and calculating the similarity between the two single sentences by adopting bleu1 or word2vec sentence vectors, and if the similarity is greater than a preset threshold value, judging that the two single sentences are similar.

In some embodiments, determining an association relationship between two policy texts according to a plurality of association relationships corresponding to a plurality of single sentence pairs includes:

classifying a plurality of association relations corresponding to the plurality of single sentences to obtain a plurality of association relation groups; the incidence relations in the same incidence relation group are the same, and the incidence relations in different incidence relation groups are different;

and counting the number of the association relations in each association relation group, and taking any association relation in the association relation group with the largest number of the association relations as the association relation between the two policy texts.

In a second aspect, an embodiment of the present invention provides a policy text relevance analysis system, including:

the policy text acquisition module is used for acquiring two policy texts to be subjected to relevance analysis;

the single sentence pair obtaining module is used for judging whether the two policy texts have a top-bottom relationship or not, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs;

a single sentence association relation obtaining module, configured to determine, for each single sentence pair, whether two single sentences in the single sentence pair are similar, and if so, determine an association relation between the two single sentences according to policy text categories to which the two single sentences belong, and use the association relation as an association relation corresponding to the single sentence pair;

and the policy text association relation acquisition module is used for determining the association relation between the two policy texts according to a plurality of association relations corresponding to the plurality of single sentence pairs.

In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor; wherein the memory has stored therein a computer program; the processor is configured to execute the computer program to implement the policy text relevance analysis method as described above.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the policy text relevance analysis method as described above.

According to the method and the system for analyzing the relevance of the policy text, provided by the embodiment of the invention, the policy text is modeled through the most advanced natural language processing technology, so that the automatic analysis of the relation between the policy texts is realized, the automatic judgment of the relation between the policy texts is realized, a policy maker is helped to make a more reasonable policy text, and the blank of the relevance analysis between the policy texts is filled.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a flowchart of a policy text relevance analysis method according to an embodiment of the present invention;

fig. 2 is a flowchart for determining whether two policy texts have a context relationship according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a policy text relevance analysis system according to an embodiment of the present invention;

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

Detailed Description

In order to make the objects, 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 drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

By analyzing the policy texts in the computer fields of the current internet, artificial intelligence, big data and the like, from the perspective of a policy maker, the association relationship between the policy texts is defined, table 1 is an association relationship definition table of the policy texts, please refer to table 1, and the association relationship between the policy texts includes four relationships of theoretical guidance, standard management, system cultivation and support services. The theoretical guidance refers to guidance of policy texts theoretically from the aspects of industrial development, various plans and the like; the standard management refers to the standardization of industry management, various management, regulation, standard establishment and the like; the system cultivation refers to scientific and technological innovation, various innovation projects and scientific and technological innovation support plans; the support service refers to the support cultivation of the development of the field by the exemption/benefit/foster policy text.

Table 1 table of association definitions of policy text

Association relation	Analysis of action	Relationship definition
			Theoretical guidance	The industrial development, various plans and the like theoretically guide the policy text	From higher level to lower level
Specification management	The industry management, various management, regulation, standard establishment and the like standardize the industry	From higher level to lower level
			Systematic cultivation	Scientific and technological innovation, various innovative projects and scientific and technological innovation support plans	Lower level to upper level
Support service	Development of the field is supported and cultivated by the deduction/preference/fostering policy text	Lower level to upper level

Fig. 1 is a flowchart of a policy text relevance analysis method according to an embodiment of the present invention, and as shown in fig. 1, the analysis method includes:

step 101, two policy texts to be subjected to relevance analysis are obtained.

Particularly, with the rapid development of computer technologies such as internet, artificial intelligence, big data and the like in various industries, a great number of policy texts about the computer fields such as internet, artificial intelligence, big data and the like are developed to standardize and promote the development of computer technologies such as internet, artificial intelligence, big data and the like. The policy text in the embodiment of the invention refers to the policy text in the computer fields of Internet, artificial intelligence, big data and the like. For convenience of the following description, the two policy texts acquired here will be referred to as policy text a and policy text B, respectively.

And 102, judging whether the two policy texts have a superior-subordinate relation or not, and if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs.

Specifically, it is determined whether or not the policy text a and the policy text B have a hierarchical relationship.

For example, if both belong to the same domain and are issued by the same organization, it is determined that the two have a hierarchical relationship, and the policy document with the earlier issue time is set as the upper hierarchy and the policy document with the later issue time is set as the lower hierarchy according to the morning and evening of the issue time.

For another example, if the two belong to the same domain and the two are respectively the central release and the local release, the upper and lower level relationship between the two is determined, and the policy text of the central release is regarded as the upper level and the policy text of the local release is regarded as the lower level.

For example, if both belong to the same field and are delivered to a higher-level organization and a lower-level organization, respectively, it is determined that the upper-level and lower-level relationships exist between the two, and the policy document delivered by the higher-level organization is set as the upper level and the policy document delivered by the lower-level organization is set as the lower level.

It should be noted that, if the two are not in the same field, it is determined that there is no upper-lower relationship between the two, and no subsequent operation is performed.

The attributes of the single sentence summarize the policy text described by the single sentence, and are divided into five categories of management, service, application, main body and technology in order to comprehensively summarize fine-grained information of the policy text.

For convenience of description hereinafter, it is assumed that the policy text a is an upper level and the policy text B is a lower level.

And acquiring a plurality of single sentences in the policy text A and the policy text B, and determining the attribute of each single sentence.

For example, policy text a includes a single sentence 1, a single sentence 2, and a single sentence 3, and policy text B includes a single sentence 4, a single sentence 5, and a single sentence 6, where the attributes of single sentence 1 and single sentence 4 are the same, the attributes of single sentence 2 and single sentence 5 are the same, and the attributes of single sentence 3 and single sentence 6 are the same. In this case, the above-mentioned 3 sentence pairs are obtained by composing sentence 1 and sentence 4 into a sentence pair and designating it as sentence pair 1, composing sentence 2 and sentence 5 into a sentence pair and designating it as sentence pair 2, and composing sentence 3 and sentence 6 into a sentence pair and designating it as sentence pair 3.

And 103, judging whether two single sentences in the single sentence pairs are similar or not for each single sentence pair, if so, determining the association relationship between the two single sentences according to the policy text types to which the two single sentences belong and using the association relationship as the corresponding association relationship of the single sentence pairs.

Specifically, the policy text category to which the single sentence belongs is used for describing the role of the single sentence in the policy text, and the policy text category to which the single sentence belongs is divided into four categories of theoretical guidance, standard management, system cultivation and support service.

For the single sentence pair 1, if the single sentence 1 is similar to the single sentence 2, determining the association relationship between the single sentence 1 and the single sentence 2 according to the policy text type to which the single sentence 1 belongs and the policy text type to which the single sentence 2 belongs, and taking the association relationship as the association relationship 1 corresponding to the single sentence pair 1. For the single sentence pair 2, if the single sentence 3 is similar to the single sentence 4, determining the association relationship between the single sentence 3 and the single sentence 4 according to the policy text type to which the single sentence 3 belongs and the policy text type to which the single sentence 4 belongs, and taking the association relationship as the association relationship 2 corresponding to the single sentence pair 2. For the single sentence pair 3, if the single sentence 5 is similar to the single sentence 6, the association relationship between the single sentence 5 and the single sentence 6 is determined according to the policy text type to which the single sentence 5 belongs and the policy text type to which the single sentence 6 belongs, and the association relationship is used as the association relationship 3 corresponding to the single sentence pair 3.

For example, for the single sentence pair 1, the policy text category to which the single sentence 1 belongs is a theoretical guideline, and the policy text category to which the single sentence 4 belongs is a supporting service, the association relationship between the single sentence 1 and the single sentence 4 is a theoretical guideline relationship (or a supporting service relationship), and the theoretical guideline relationship is taken as the association relationship corresponding to the single sentence pair 1.

And step 104, determining the association relationship between the two policy texts according to the association relationships corresponding to the single sentence pairs.

Specifically, the association relationship between the policy text a and the policy text B is determined according to the association relationship 1, the association relationship 2, and the association relationship 3. For example, the association relationship 1 is theoretical guidance, the association relationship 2 is theoretical guidance, and the association relationship 3 is standard management, and the association relationship between the policy text a and the policy text B is determined as theoretical guidance according to the principle that minority is subject to majority.

According to the policy text relevance analysis method provided by the embodiment of the invention, the policy text is modeled through the most advanced natural language processing technology, so that the automatic analysis of the relation between the policy texts is realized, the automatic judgment of the relation between the policy texts is realized, a policy maker is helped to make a more reasonable policy text, and the blank of relevance analysis between the policy texts is filled.

In some embodiments, determining whether there is a contextual relationship between two policy texts comprises:

and judging whether the two policy texts belong to the same field.

If yes, whether the two policy texts are issued by the same organization or not is judged.

If yes, judging that the two policy texts have a superior-subordinate relation; if not, whether the two policy texts are respectively issued by the center and the local is judged.

If yes, judging that the two policy texts have a superior-subordinate relation; if not, whether the two policy texts are respectively issued by the superior organization and the subordinate organization is judged.

If yes, judging that the two policy texts have a superior-subordinate relation.

Specifically, fig. 2 shows in detail a process of determining whether two policy texts have a hierarchical relationship, which is not described herein again.

In some embodiments, any two sentences with the same attribute in different policy texts are combined into a single sentence pair, and the method further comprises the following steps:

and for each single sentence in the two policy texts, inputting the single sentence into the trained neural network model, and acquiring the policy text category to which the single sentence output by the trained neural network model belongs and the attribute of the single sentence. The trained neural network model is obtained by training based on a training set, and the training set comprises a plurality of sample single sentences, sample policy text categories to which the sample single sentences belong and sample attributes of the sample single sentences.

Specifically, ten policy texts are selected from a policy text database to cover the computer fields of the internet, artificial intelligence, big data and the like, and then each policy text is divided into sentences.

In order to convert the selected policy text into data which can be subjected to supervised training of the neural network model, part of the data is labeled manually. Specifically, the policy text type and the single sentence attribute are labeled on the single sentence of the good sentence. The marked data is used for supervised training in the following tasks such as policy text category classification and single sentence attribute identification of the single sentence.

In order to enable the policy text data to be input into the neural network model for training, based on the Chinese text data, a dictionary is trained Bpe, and instead of the traditional ending segmentation method, the policy text is segmented using Bpe algorithm as input of the neural network model.

It should be noted that, the neural network model is preferably a BERT model, and a good effect can be achieved in multiple natural language processing tasks based on the trained BERT model, and compared with the effects of traditional neural network models such as a TextCnn model and an Lstm model, the BERT model can better extract semantic connotations of texts from deep levels, and has an important role in understanding policy text contents.

And on the basis of the trained BERT model, a fully-connected network and Softmax are built on the upper layer, and the loss of the model is calculated by adopting a cross entropy loss function.

And during training, the policy text and the marked result are simultaneously input into the BERT model for the BERT model to learn and adjust parameters. After training is finished, the BERT model is stored locally, and the results of the training model are evaluated by adopting ten-fold cross validation.

In some embodiments, determining whether two of the pair of single sentences are similar comprises:

and (3) performing syntactic analysis on the two single sentences in the single sentence pair respectively, extracting verbs and corresponding nouns in each single sentence, and judging that the two single sentences are similar if the verbs and the nouns of the two single sentences are matched.

In some embodiments, determining whether two of the pair of single sentences are similar comprises:

and calculating the similarity between the two single sentences by adopting bleu1 or word2vec sentence vectors, and if the similarity is greater than a preset threshold value, judging that the two single sentences are similar. The preset threshold is preferably 0.3.

In some embodiments, determining an association between two policy texts according to a plurality of associations corresponding to a plurality of single sentence pairs includes:

classifying a plurality of single sentences into a plurality of corresponding association relations to obtain a plurality of association relation groups; the incidence relations in the same incidence relation group are the same, and the incidence relations in different incidence relation groups are different.

And counting the number of the association relations in each association relation group, and taking any association relation in the association relation group with the largest number of the association relations as the association relation between the two policy texts.

Specifically, if the association 1 corresponding to the single sentence pair 1 is theoretical guidance, the association 2 corresponding to the single sentence pair 2 is theoretical guidance, and the association 3 corresponding to the single sentence pair 3 is standard management, the three associations are classified into 2 association groups, the association in the 1 st association group is theoretical guidance and theoretical guidance, and the association in the 2 nd association group is standard management. The number of the association relations in the 1 st association relation group is 2, the number of the association relations in the 2 nd association relation group is 1, and 2 is greater than 1, so that the theoretical guidance in the 1 st association relation group is used as the association relation between the policy text 1 and the policy text 2, that is, the policy text 1 as an upper level plays a theoretical guidance role on the policy text 2 as a lower level.

Fig. 3 is a schematic structural diagram of a policy text relevance analysis system according to an embodiment of the present invention, and as shown in fig. 3, the system includes:

a policy text obtaining module 301, configured to obtain two policy texts to be subjected to relevance analysis; a single sentence pair obtaining module 302, configured to determine whether two policy texts have a top-bottom relationship, and if so, form a single sentence pair with any two single sentences with the same attribute in different policy texts, so as to obtain a plurality of single sentence pairs; a single sentence association obtaining module 303, configured to determine, for each single sentence pair, whether two single sentences in the single sentence pair are similar, and if so, determine, according to a policy text category to which the two single sentences belong, an association between the two single sentences and use the association as an association corresponding to the single sentence pair; the policy text association relation obtaining module 304 is configured to determine an association relation between two policy texts according to a plurality of association relations corresponding to the plurality of single sentence pairs.

Specifically, the system provided in the embodiment of the present invention is specifically configured to execute the embodiment of the policy text association analysis method, and details of the embodiment of the present invention are not repeated here. The system provided by the embodiment of the invention realizes the automatic analysis of the relation between the policy texts by modeling the policy texts through the most advanced natural language processing technology, realizes the automatic judgment of the relation between the policy texts, is beneficial to helping a policy maker to make a more reasonable policy text, and fills the blank of the association analysis between the policy texts.

Fig. 4 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor)401, a communication Interface (communication Interface)402, a memory (memory)403 and a communication bus 404, wherein the processor 401, the communication Interface 402 and the memory 403 complete communication with each other through the communication bus 404. The processor 401 may invoke a computer program stored in the memory 403 and executable on the processor 401 to perform the methods provided by the above embodiments, including for example: acquiring two policy texts to be subjected to relevance analysis; judging whether the two policy texts have a top-bottom relation, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs; for each single sentence pair, judging whether two single sentences in the single sentence pair are similar, if so, determining the association relation between the two single sentences according to the policy text types to which the two single sentences belong and taking the association relation as the corresponding association relation of the single sentence pair; and determining the association relationship between the two policy texts according to the association relationships corresponding to the single sentence pairs.

In addition, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method provided in the foregoing embodiments when executed by a processor, and the method includes: acquiring two policy texts to be subjected to relevance analysis; judging whether the two policy texts have a top-bottom relation, if so, combining any two single sentences with the same attribute in the different policy texts into a single sentence pair to obtain a plurality of single sentence pairs; for each single sentence pair, judging whether two single sentences in the single sentence pair are similar, if so, determining the association relation between the two single sentences according to the policy text types to which the two single sentences belong and taking the association relation as the corresponding association relation of the single sentence pair; and determining the association relationship between the two policy texts according to the association relationships corresponding to the single sentence pairs.

The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.