A system and method for intelligently setting monitoring words

Abstract

The present invention discloses a system and method for intelligently setting monitoring words, including an article collection module, an article processing module, an intelligent matching module, and a monitoring word generation module. The article collection module is used to collect news, forums, microblogs, and electronic newspaper article publishing sites, and send the articles to a database. The article processing module is used to analyze the topic of the article, extract the words therein as a matching content set, and randomly take 300 of them to provide a filterable operation for the user. The articles directly matched by the user are judged and marked as unreasonable and do not meet the business content, and negative cases are generated and sent to the intelligent matching module. The present invention no longer requires the user to provide an explicit and accurate logical combination solution, but only needs to provide intuitive feedback on whether the specific content matches the result of the intelligent matching, so that the algorithm can obtain feedback to intelligently optimize an implicit and accurate monitoring phrase, and can continue to optimize afterwards.

Description

Technical Field

[0001] The invention belongs to the field of data collection and analysis, and in particular relates to an intelligent monitoring word setting system. Background Art

[0002] The professional threshold for setting up solutions in public opinion applications is high, the logic is complex, and the skills and experience of personnel are high. This patent is based on the content analysis business itself, and users do not need to understand the complex logic and can use it easily. Therefore, we have made improvements to this and proposed an intelligent setting monitoring word system. Summary of the invention

[0003] The purpose of the present invention is to overcome the above problems existing in the prior art and to provide an intelligent monitoring word setting system, which no longer requires users to provide explicit and precise logical combination solutions, but only requires intuitive feedback on the results of intelligent matching as to whether the specific content matches, so that the algorithm can obtain feedback to intelligently optimize an implicit and precise monitoring phrase, and can continue to optimize afterwards.

[0004] In order to achieve the above technical objectives and the above technical effects, the present invention is implemented through the following technical solutions:

[0005] An intelligent monitoring word setting system, comprising an article collection module, an article processing module, an intelligent matching module, and a monitoring word generation module;

[0006] The article collection module is used to collect news, forums, microblogs, and electronic newspaper article publishing sites, and send the articles to the database;

[0007] The article processing module is used to analyze the topic of the article, extract the words therein as a matching content set, and randomly select 300 articles from them to provide users with a screening operation. The articles directly matched by the user are judged and marked as unreasonable and unsatisfactory content, and negative cases are generated and sent to the intelligent matching module;

[0008] The smart matching module includes a positive content submodule and a negative content submodule. The positive content submodule is used to optimize and calculate the initialization detection group according to the negative case mark to form an iterative business monitoring phrase, and then go through an algorithm loop until the proportion of positive example content is greater than a preset value. The negative content submodule is used to optimize and calculate the initialization detection group according to the negative case mark to form an iterative business monitoring phrase, and then go through an algorithm loop until the proportion of negative example content is less than a preset value, and send the phrase that meets the condition to the monitoring word generation module;

[0009] The monitoring word generation module sorts the monitoring word groups and displays the characteristic words according to the user-set levels.

[0010] Furthermore, the database contains at least a preset number of positive cases and negative cases, and the user's monitoring words are compared with the positive cases and negative cases to obtain the screenable monitoring words.

[0011] A method for intelligently setting monitoring words comprises the following steps:

[0012] A. Analyze the data in the database and generate positive cases and negative cases based on the user monitoring words; the module generates a positive annotation set for positive cases and a negative annotation set for negative cases;

[0013] B. Establish a common word set of the positive annotation set and the negative annotation set, select a word from them, delete the common word set from the positive annotation set, and obtain data under the same conditions;

[0014] C. Calculate from the data acquisition, if it is greater than the preset value, delete the common word set from the positive annotation set, obtain the data under the same conditions, and judge whether it is the preset data; if it is less than the preset value, delete the common word set from the common set, and judge whether it is the preset data;

[0015] D. If the preset data does not match, repeat step C until the preset value is met;

[0016] F. Delete a class of words in the positively marked word set, calculate the negatively marked value, and if it is greater than a predetermined value, obtain a detection phrase set and send it to the monitoring word generation module;

[0017] G. The monitoring word generation module sorts the monitoring phrases and displays the characteristic words according to the user-set level.

[0018] The intelligent matching module calculation method includes the following steps:

[0019] S1. Analyze the data in the database and generate positive cases and negative cases based on user monitoring words;

[0020] S2, the module performs positive annotation set P for positive cases and negative annotation set N for negative cases;

[0021] S3, segment the positive annotation set P to establish a truncated segmentation set and merge it with the original business feature word set to establish a set A;

[0022] S4, segment the set N to establish a negative word set B;

[0023] S5, establish a common word set C of A and B;

[0024] S6, select a word W in C, delete W from the set A and obtain the set T with the same condition data;

[0025] S7, calculate the content of N in T, if it is greater than a preset value, delete W from the A set, set it as a new A set, delete W from the C set, set it as a new C set, and determine whether the C set is an empty set; if it is less than a preset value, delete W from the C set, set it as a new C set, and determine whether the C set is an empty set;

[0026] S8. If C is not an empty set, repeat steps S6 and S7 until the preset value is met;

[0027] S9. Delete any unlabeled element a in the set A, record it as the set A2, use A2 as the collection word and the same conditions to obtain data T, calculate the content of the original P element in T, and determine whether it is greater than the preset value. If the preset value is met, continue to determine whether there are unlabeled elements in the set A. If n is greater than 0, the judgment ends. If n is less than 0, return to S9.

[0028] The beneficial effect of the present invention is that this intelligent monitoring word setting system and method no longer requires users to provide explicit and precise logical combination solutions, but only requires intuitive feedback on whether the specific content matches the results of intelligent matching, so that the algorithm can obtain feedback to intelligently optimize an implicit and precise monitoring phrase, and can continue to optimize afterwards. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0030] Figure 1 It is a schematic diagram of the process of the present invention;

[0031] Figure 2 It is a schematic diagram of the algorithm structure of the intelligent matching module of the present invention;

[0032] Figure 3 It is a schematic diagram of the algorithm structure of the intelligent matching module of the present invention;

[0033] Figure 4 It is a schematic diagram of the algorithm structure of the intelligent matching module of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0036] like Figure 1 The intelligent setting monitoring word system shown in the figure includes an article collection module, an article processing module, an intelligent matching module, and a monitoring word generation module. The article collection module is used to collect news, forums, microblogs, and electronic newspaper article publishing sites, and send the articles to the database. The article processing module is used to analyze the topics of the articles, extract the words therein as matching content sets, and randomly select 300 of them to provide users with filterable operations. The articles directly matched by the users are judged and marked as unreasonable and unsatisfactory content, and negative cases are generated and sent to the intelligent matching module. The intelligent matching module includes a positive content submodule and a negative content submodule. The positive content submodule is used to select the content according to the negative content. The face case marking optimizes the calculation of the initialization detection group to form the iterative business monitoring phrase, which goes through the algorithm loop until the proportion of positive example content is greater than the preset value. The negative content sub-module is used to optimize the calculation of the initialization detection group according to the negative case marking to form the iterative business monitoring phrase, which goes through the algorithm loop until the proportion of negative example content is less than the preset value. The phrase that meets the conditions is sent to the monitoring phrase generation module. The monitoring phrase generation module sorts the monitoring phrase and displays the feature words according to the user-set level. The database contains at least a preset number of positive cases and negative cases. The user's monitoring words are compared with the positive cases and negative cases to obtain the screenable monitoring words.

[0037] A method for intelligently setting monitoring words comprises the following steps:

[0038] A. Analyze the data in the database and generate positive cases and negative cases based on the user monitoring words; the module generates a positive annotation set for positive cases and a negative annotation set for negative cases;

[0039] B. Establish a common word set of the positive annotation set and the negative annotation set, select a word from them, delete the common word set from the positive annotation set, and obtain data under the same conditions;

[0040] C. Calculate from the data acquisition, if it is greater than the preset value, delete the common word set from the positive annotation set, obtain the data under the same conditions, and judge whether it is the preset data; if it is less than the preset value, delete the common word set from the common set, and judge whether it is the preset data;

[0041] D. If the preset data does not match, repeat step C until the preset value is met;

[0042] F. Delete a class of words in the positively marked word set, calculate the negatively marked value, and if it is greater than a predetermined value, obtain a detection phrase set and send it to the monitoring word generation module;

[0043] G. The monitoring word generation module sorts the monitoring phrases and displays the characteristic words according to the user-set level.

[0044] like Figure 2 , Figure 3 and Figure 4 As shown, the intelligent matching module calculation method includes the following steps:

[0045] S1. Analyze the data in the database and generate positive cases and negative cases based on user monitoring words;

[0046] S2, the module performs positive annotation set P for positive cases and negative annotation set N for negative cases;

[0047] S3. Segment the positive annotation set P to establish a truncated segmentation set and merge it with the original business feature word set to establish a set A.

[0048] S4. Segment the set N to create a negative word set B

[0049] S5. Create a common word set C between A and B

[0050] S6, select a word W in C, delete W from the set A and obtain the set T with the same condition data,

[0051] S7, calculate the content of N in T, if it is greater than a preset value, delete W from the A set, set it as a new A set, delete W from the C set, set it as a new C set, and determine whether the C set is an empty set; if it is less than a preset value, delete W from the C set, set it as a new C set, and determine whether the C set is an empty set;

[0052] S8. If C is not an empty set, repeat steps S6 and S7 until the preset value is met.

[0053] S9. Delete any unlabeled element a in the set A, record it as the set A2, use A2 as the collection word and the same conditions to obtain data T, calculate the content of the original P element in T, and determine whether it is greater than the preset value. If the preset value is met, continue to determine whether there are unlabeled elements in the set A. If n is greater than 0, the judgment ends. If n is less than 0, return to S9.

[0054] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0055] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. An intelligent monitoring word setting system, characterized in that: It includes article collection module, article processing module, intelligent matching module and monitoring word generation module; The article collection module is used to collect news, forums, microblogs, and electronic newspaper article publishing sites, and send the articles to the database; The article processing module is used to analyze the topic of the article, extract the words therein as a matching content set, and randomly select 300 articles from them to provide users with a screening operation. The articles directly matched by the user are judged and marked as unreasonable and unsatisfactory content, and negative cases are generated and sent to the intelligent matching module; The smart matching module includes a positive content submodule and a negative content submodule. The positive content submodule is used to optimize and calculate the initialization detection group according to the negative case mark to form an iterative business monitoring phrase, and then go through an algorithm loop until the proportion of positive example content is greater than a preset value. The negative content submodule is used to optimize and calculate the initialization detection group according to the negative case mark to form an iterative business monitoring phrase, and then go through an algorithm loop until the proportion of negative example content is less than a preset value, and send the phrase that meets the condition to the monitoring word generation module; The monitoring word generation module sorts the monitoring words and displays the characteristic words according to the user-set level; The intelligent matching module calculation method includes the following steps: S1. Analyze the data in the database and generate positive cases and negative cases based on user monitoring words; S2, the module performs positive annotation set P for positive cases and negative annotation set N for negative cases; S3, segment the positive annotation set P to establish a truncated segmentation set and combine it with the original business feature word set to establish a set A; S4, segment the set N to establish a negative word set B; S5, establish a common word set C of A and B; S6, select a word W in C, delete W from the set A and obtain the set T with the same condition data; S7, calculate the content of N in T, if it is greater than a preset value, delete W from the A set, set it as a new A set, delete W from the C set, set it as a new C set, and determine whether the C set is an empty set; if it is less than a preset value, delete W from the C set, set it as a new C set, and determine whether the C set is an empty set; S8. If C is not an empty set, repeat steps S6 and S7 until the preset value is met; S9. Delete any unlabeled element a in the set A, record it as the set A2, use A2 as the collection word and the same conditions to obtain data T, calculate the content of the original P element in T, and determine whether it is greater than the preset value. If the preset value is met, continue to determine whether there are unlabeled elements in the set A. If n is greater than 0, the judgment ends. If n is less than 0, return to S9.

2. The intelligent monitoring word setting system according to claim 1, characterized in that: The database contains at least a preset number of positive cases and negative cases, and the user's monitoring words are compared with the positive cases and the negative cases to obtain the screenable monitoring words.

Images