Internet information intelligent decision-making system based on artificial intelligence

Abstract

The invention discloses an Internet information intelligent decision-making system based on artificial intelligence, and relates to the field of data processing, and the system comprises a decision-making center which is in communication connection with a data collection module, a data preprocessing module, a data processing module and an intelligent decision-making module. Internet information data to be pushed are collected through the data collection module, the collected Internet information data to be pushed are preprocessed through the data preprocessing module, segmented words of the Internet information data are obtained, the obtained segmented words of the Internet information data are processed through the data processing module, and the segmented words of the Internet information data are obtained. According to the method, the active values of the words segmented by the Internet information data are obtained, the intelligent decision-making module carries out intelligent decision-making according to the obtained active values of the words segmented by the Internet information data, pushing is carried out according to interests of a user, and therefore the reliability of Internet information data pushing is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an Internet information intelligent decision-making system based on artificial intelligence. Background Art

[0002] With the rapid development of the Internet, the amount of information has exploded. How to quickly and accurately extract valuable information from massive information to assist decision-making has become an important research topic and practical demand. Traditional information processing methods can no longer meet the current complex and changing needs, so the Internet information intelligent decision-making system based on artificial intelligence came into being;

[0003] How to obtain the active value of words segmented from Internet information data and make intelligent decisions based on the active value of words segmented from Internet information data, so as to improve the reliability of Internet information data push, is a problem we need to solve. To this end, an Internet information intelligent decision-making system based on artificial intelligence is now provided. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an Internet information intelligent decision-making system based on artificial intelligence.

[0005] The object of the present invention can be achieved by the following technical solutions: an Internet information intelligent decision-making system based on artificial intelligence, comprising a decision-making center, wherein the decision-making center is communicatively connected with a data acquisition module, a data preprocessing module, a data processing module and an intelligent decision-making module;

[0006] The data collection module is used to collect the Internet information data to be pushed;

[0007] The data preprocessing module is used to preprocess the collected Internet information data to be pushed, and obtain the words segmented by the Internet information data;

[0008] The data processing module is used to process the words obtained by segmenting the Internet information data to obtain the activity values ​​of the words obtained by segmenting the Internet information data;

[0009] The intelligent decision-making module is used to make intelligent decisions based on the activity values ​​of words segmented from the obtained Internet information data.

[0010] Furthermore, the process of the data collection module collecting the Internet information data to be pushed includes:

[0011] The data collection module is composed of a number of Internet information data collection terminals, and the Internet information data collection terminals are used to collect Internet information data to be pushed to users;

[0012] Each Internet information data collection terminal is configured and a corresponding configuration channel is generated. The corresponding server is linked through the generated configuration channel. The Internet information data collection terminal obtains the Internet information data to be pushed in the corresponding server through the configuration channel.

[0013] Furthermore, the process of preprocessing the collected Internet information data to be pushed by the data preprocessing module includes:

[0014] The preprocessing module is provided with a word database, and the word database stores a plurality of words;

[0015] Obtain the length of the longest word stored in the word database, and record the obtained length of the longest word stored in the word database as L;

[0016] Performing primary word segmentation preprocessing on Internet information data by artificial intelligence technology to obtain a result of the primary word segmentation preprocessing, wherein the result of the primary word segmentation preprocessing includes a number of words;

[0017] Performing secondary word segmentation preprocessing on Internet information data by artificial intelligence technology to obtain secondary word segmentation preprocessing results, wherein the secondary word segmentation preprocessing results include a number of words;

[0018] The number of words obtained by the first-level word segmentation preprocessing is compared with the number of words obtained by the second-level word segmentation preprocessing. If the comparison results are the same, the words obtained by the first-level word segmentation preprocessing are used as the words for segmenting the Internet information data;

[0019] If the comparison results are different, the words obtained by the first-level word segmentation preprocessing and the words obtained by the second-level word segmentation preprocessing are mixed, and the mixed words are used as the words for segmenting the Internet information data.

[0020] Furthermore, the process of performing first-level word segmentation preprocessing on Internet information data by artificial intelligence technology includes:

[0021] Set the maximum match length of the first level, and set the maximum word length of the first level to L;

[0022] Starting from the first character of the Internet information data, the first L characters are obtained, and the obtained L characters are used as the character fragments to be matched;

[0023] Get the words segmented by the character fragments to be matched consisting of the first L characters;

[0024] Obtain a character segment consisting of the (L+1)th to 2Lth characters, use the obtained character segment consisting of the (L+1)th to 2Lth characters as the character segment to be matched, obtain words segmented from the character segment to be matched consisting of the (L+1)th to 2Lth characters, obtain a character segment consisting of the (2L+1)th to 3Lth characters, use the obtained character segment consisting of the (2L+1)th to 3Lth characters as the character segment to be matched, obtain words segmented from the character segment to be matched consisting of the (2L+1)th to 3Lth characters, and so on, to obtain words segmented from the character segments consisting of the remaining characters of the Internet information data.

[0025] Furthermore, the process of obtaining the words segmented by the to-be-matched character fragments composed of the first L characters includes:

[0026] The character segment to be matched consisting of the first L characters is matched with the words stored in the word database. If the word identical to the character segment to be matched exists in the word database, the character segment to be matched is cut out from the Internet information data as a word. If the word identical to the character segment to be matched does not exist in the word database, the first (L-1) characters of the character segment to be matched are matched with the words stored in the word database.

[0027] If there is a word in the word database that is identical to the first (L-1) characters of the character segment to be matched, the first (L-1) characters of the character segment to be matched are segmented out from the Internet information data as a word, and the remaining character segment to be matched after segmentation is matched with the words stored in the word database. If there is a word in the word database that is identical to the character segment to be matched after segmentation, the remaining character segment to be matched after segmentation is segmented out from the Internet information data as a word. If there is no word in the word database that is identical to the character segment to be matched, the remaining character segment to be matched after segmentation is retained.

[0028] If there is no word in the word database that is identical to the first (L-1) characters of the character segment to be matched, then the remaining unmatched characters in the character segment to be matched are matched with the words stored in the word database;

[0029] If there is a word in the word database that is identical to the remaining unmatched characters in the character segment to be matched, the remaining unmatched characters in the character segment to be matched are segmented out from the Internet information data as a word; if there is no word in the word database that is identical to the remaining unmatched characters in the character segment to be matched, the remaining unmatched characters in the character segment to be matched are retained, and the first (L-2) characters of the character segment to be matched are matched with the words stored in the word database, and so on, ..., until the first character of the character segment to be matched is matched with the words stored in the word database, or there is a word in the word database that is identical to the first L or first (L-1) or first (L-2) or first (L-3) or first (L-4) or ... or first two characters of the character segment to be matched, and the word segmented from the character segment to be matched consisting of the first L characters is obtained.

[0030] Furthermore, the process of performing secondary word segmentation preprocessing on Internet information data by artificial intelligence technology includes:

[0031] Set the secondary maximum matching length, and set the secondary maximum word length to L, that is, the secondary maximum word length is the same as the length of the longest word stored in the word database;

[0032] Starting from the last character of the Internet information data, obtaining the last L characters, using the obtained last L characters as the character segment to be matched, and obtaining the words segmented by the character segment to be matched consisting of the last L characters;

[0033] Obtain a character segment consisting of the last (L+1) to 2L characters, use the obtained character segment consisting of the last (L+1) to 2L characters as the character segment to be matched, obtain words segmented from the character segment to be matched consisting of the last (L+1) to 2L characters, and so on, obtain words segmented from the character segment consisting of the remaining characters of the Internet information data.

[0034] Furthermore, the process of the data processing module processing the words obtained by segmenting the Internet information data includes:

[0035] Obtaining the occurrence frequency of the words segmented from the Internet information data, and obtaining the activity value of the words segmented from the Internet information data according to the obtained occurrence frequency of the words segmented from the Internet information data;

[0036] The activity values ​​of the obtained words of the Internet information data segmentation are sorted from large to small, and the words of the Internet information data segmentation corresponding to the first k activity values ​​are obtained, where k is a positive even number not equal to zero, and the words of the Internet information data segmentation corresponding to the first k activity values ​​obtained are recorded as reference words.

[0037] Furthermore, the process of the intelligent decision module making intelligent decisions according to the activity values ​​of the words obtained by segmenting the Internet information data includes:

[0038] Obtaining Internet information data being browsed by a user, and obtaining activity values ​​of words segmented from the Internet information data being browsed by the user, sorting the obtained activity values ​​of the words segmented from the Internet information data being browsed by the user from large to small, obtaining the words segmented from the Internet information data being browsed by the user corresponding to the first k activity values, and recording the words segmented from the Internet information data being browsed by the user corresponding to the obtained first k activity values ​​as standard words;

[0039] The obtained standard words are compared with the reference words. If there are k / 2 or more reference words that are the same as the standard words, the Internet information data to be pushed will be pushed to the user. If there are not k / 2 or more reference words that are the same as the standard words, the Internet information data to be pushed will be prohibited from being pushed to the user.

[0040] Compared with the prior art, the beneficial effects of the present invention are: collecting Internet information data to be pushed, pre-processing the collected Internet information data to be pushed, obtaining words segmented from the Internet information data, processing the obtained words segmented from the Internet information data, obtaining activity values ​​of the words segmented from the Internet information data, making intelligent decisions based on the obtained activity values ​​of the words segmented from the Internet information data, and pushing based on user interests, thereby improving the reliability of pushing Internet information data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0042] like Figure 1 As shown, an Internet information intelligent decision-making system based on artificial intelligence includes a decision center, and the decision center is communicatively connected with a data acquisition module, a data preprocessing module, a data processing module and an intelligent decision-making module;

[0043] The data collection module is used to collect the Internet information data to be pushed;

[0044] It should be further explained that, in the specific implementation process, the process of the data collection module collecting the Internet information data to be pushed includes:

[0045] The data collection module is composed of a number of Internet information data collection terminals, and the Internet information data collection terminals are used to collect Internet information data to be pushed to users;

[0046] Each Internet information data collection terminal is configured and a corresponding configuration channel is generated. The corresponding server is linked through the generated configuration channel. The Internet information data collection terminal obtains the Internet information data to be pushed in the corresponding server through the configuration channel.

[0047] The data preprocessing module is used to preprocess the collected Internet information data to be pushed, and obtain the words segmented by the Internet information data;

[0048] It should be further explained that, in the specific implementation process, the process of preprocessing the collected Internet information data to be pushed by the data preprocessing module includes:

[0049] The preprocessing module is provided with a word database, and the word database stores a plurality of words;

[0050] Obtain the length of the longest word stored in the word database, and record the obtained length of the longest word stored in the word database as L;

[0051] Perform primary word segmentation preprocessing on Internet information data through artificial intelligence technology;

[0052] It should be further explained that, in the specific implementation process, the process of performing primary word segmentation preprocessing on Internet information data through artificial intelligence technology includes:

[0053] Set the maximum matching length of the first level, and set the maximum word length of the first level to L, that is, the maximum word length of the first level is the same as the length of the longest word stored in the word database;

[0054] Starting from the first character of the Internet information data, the first L characters are obtained, and the obtained L characters are used as the character fragment to be matched. If the character length of the Internet information data is less than L, all characters of the Internet information data are obtained, and all characters of the obtained Internet information data are used as the character fragment to be matched;

[0055] Obtain words segmented from the character segment to be matched, match the character segment to be matched with words stored in a word database, if the word database contains the same word as the character segment to be matched, segment the character segment to be matched from the Internet information data as a word, if the word database does not contain the same word as the character segment to be matched, match the first (L-1) characters of the character segment to be matched with words stored in the word database, if the word database contains the same word as the first (L-1) characters of the character segment to be matched, segment the first (L-1) characters of the character segment to be matched from the Internet information data as a word, and match the character segment to be matched remaining after segmentation with words stored in the word database, if the word database contains the same word as the character segment to be matched remaining after segmentation, segment the character segment to be matched remaining after segmentation from the Internet information data as a word, if the word database does not contain the same word as the character segment to be matched, retain the character segment to be matched remaining after segmentation;

[0056] If there is no word in the word database that is identical to the first (L-1) characters of the character segment to be matched, the remaining unmatched characters in the character segment to be matched are matched with the words stored in the word database; if there is a word in the word database that is identical to the remaining unmatched characters in the character segment to be matched, the remaining unmatched characters in the character segment to be matched are segmented from the Internet information data as a word; if there is no word in the word database that is identical to the remaining unmatched characters in the character segment to be matched, the remaining unmatched characters in the character segment to be matched are retained, and the first (L-2) characters of the character segment to be matched are matched with the words stored in the word database;

[0057] If there is a word in the word database that is identical to the first (L-2) characters of the character segment to be matched, the first (L-2) characters of the character segment to be matched are segmented out from the Internet information data as a word, and the remaining character segment to be matched after segmentation is matched with the words stored in the word database. If there is a word in the word database that is identical to the character segment to be matched after segmentation, the remaining character segment to be matched after segmentation is segmented out from the Internet information data as a word. If there is no word in the word database that is identical to the character segment to be matched, the remaining character segment to be matched after segmentation is retained.

[0058] If there is no word identical to the first (L-2) characters of the character segment to be matched in the word database, the remaining unmatched characters in the character segment to be matched are matched with the words stored in the word database; if there is a word identical to the remaining unmatched characters in the character segment to be matched in the word database, the remaining unmatched characters in the character segment to be matched are segmented from the Internet information data as a word; if there is no word identical to the remaining unmatched characters in the character segment to be matched in the word database, the remaining unmatched characters in the character segment to be matched are retained, and the first (L-3) characters of the character segment to be matched are matched with the words stored in the word database, and so on, ..., until the first character of the character segment to be matched is matched with the words stored in the word database, or there is a word identical to the first L or first (L-1) or first (L-2) or first (L-3) or first (L-4) or ... or first two characters of the character segment to be matched in the word database, and the word segmented from the character segment to be matched is obtained;

[0059] Obtain a character segment consisting of the (L+1)th to 2Lth characters, use the obtained character segment consisting of the (L+1)th to 2Lth characters as the character segment to be matched, obtain words segmented from the character segment to be matched, obtain a character segment consisting of the (2L+1)th to 3Lth characters, use the obtained character segment consisting of the (2L+1)th to 3Lth characters as the character segment to be matched, obtain words segmented from the character segment to be matched, and so on, to obtain words segmented from the character segments consisting of the remaining characters of the Internet information data;

[0060] Perform secondary word segmentation preprocessing on Internet information data through artificial intelligence technology;

[0061] It should be further explained that, in the specific implementation process, the process of performing secondary word segmentation preprocessing on Internet information data through artificial intelligence technology includes:

[0062] Set the secondary maximum matching length, and set the secondary maximum word length to L, that is, the secondary maximum word length is the same as the length of the longest word stored in the word database;

[0063] Starting from the last character of the Internet information data, the last L characters are obtained, and the obtained last L characters are used as the character segment to be matched. If the character length of the Internet information data is less than L, all characters of the Internet information data are obtained, and all characters of the obtained Internet information data are used as the character segment to be matched, and words are obtained by segmenting the character segment to be matched;

[0064] Obtain a character segment consisting of the last (L+1) to 2L characters, use the obtained character segment consisting of the last (L+1) to 2L characters as the character segment to be matched, obtain words segmented from the character segment to be matched, and so on, obtain words segmented from the character segment consisting of the remaining characters of the Internet information data;

[0065] The number of words obtained by the first-level word segmentation preprocessing is compared with the number of words obtained by the second-level word segmentation preprocessing. If the comparison results are the same, the words obtained by the first-level word segmentation preprocessing are used as the words for segmenting the Internet information data;

[0066] If the comparison results are different, the words obtained by the first-level word segmentation preprocessing and the words obtained by the second-level word segmentation preprocessing are mixed, and the mixed words are used as the words for segmenting the Internet information data.

[0067] The data processing module is used to process the words obtained by segmenting the Internet information data to obtain the activity values ​​of the words obtained by segmenting the Internet information data;

[0068] It should be further explained that, in the specific implementation process, the process of the data processing module processing the words obtained by segmenting the Internet information data includes:

[0069] The words segmented from the Internet information data are labeled as i, i=1, 2, 3, ..., n, where n is a positive integer, and the occurrence frequency of the words segmented from the Internet information data is obtained, and the occurrence frequency of the words segmented from the Internet information data obtained is recorded as S i ;

[0070] The activity value of the words segmented from the Internet information data is obtained according to the occurrence frequency of the words segmented from the Internet information data, and the activity value of the words segmented from the Internet information data is recorded as P i ;

[0071] in,

[0072] The activity values ​​of the obtained words of the Internet information data segmentation are sorted from large to small, and the words of the Internet information data segmentation corresponding to the first k activity values ​​are obtained, where k is a positive even number not equal to zero, and the words of the Internet information data segmentation corresponding to the first k activity values ​​obtained are recorded as reference words.

[0073] The intelligent decision-making module is used to make intelligent decisions based on the activity values ​​of the words segmented from the obtained Internet information data;

[0074] It should be further explained that, in the specific implementation process, the process of the intelligent decision module making intelligent decisions according to the activity values ​​of the words obtained by segmenting the Internet information data includes:

[0075] Obtaining Internet information data being browsed by a user, and obtaining activity values ​​of words segmented from the Internet information data being browsed by the user, sorting the obtained activity values ​​of the words segmented from the Internet information data being browsed by the user from large to small, obtaining the words segmented from the Internet information data being browsed by the user corresponding to the first k activity values, and recording the words segmented from the Internet information data being browsed by the user corresponding to the obtained first k activity values ​​as standard words;

[0076] The obtained standard words are compared with the reference words. If there are k / 2 or more reference words that are the same as the standard words, the Internet information data to be pushed will be pushed to the user. If there are not k / 2 or more reference words that are the same as the standard words, the Internet information data to be pushed will be prohibited from being pushed to the user.

[0077] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An Internet information intelligent decision-making system based on artificial intelligence, including a decision-making center, characterized in that: The decision center is communicatively connected to a data acquisition module, a data preprocessing module, a data processing module and an intelligent decision module; The data collection module is used to collect the Internet information data to be pushed; The data preprocessing module is used to preprocess the collected Internet information data to be pushed, and obtain the words segmented by the Internet information data; The data processing module is used to process the words obtained by segmenting the Internet information data to obtain the activity values ​​of the words obtained by segmenting the Internet information data; The intelligent decision-making module is used to make intelligent decisions based on the activity values ​​of words segmented from the obtained Internet information data.

2. According to claim 1, an Internet information intelligent decision-making system based on artificial intelligence is characterized in that: The process of the data collection module collecting the Internet information data to be pushed includes: The data collection module is composed of a number of Internet information data collection terminals, and the Internet information data collection terminals are used to collect Internet information data to be pushed to users; Each Internet information data collection terminal is configured and a corresponding configuration channel is generated. The corresponding server is linked through the generated configuration channel. The Internet information data collection terminal obtains the Internet information data to be pushed in the corresponding server through the configuration channel.

3. The Internet information intelligent decision-making system based on artificial intelligence according to claim 2 is characterized in that: The process of preprocessing the collected Internet information data to be pushed by the data preprocessing module includes: The preprocessing module is provided with a word database, and the word database stores a plurality of words; Obtain the length of the longest word stored in the word database, and record the obtained length of the longest word stored in the word database as L; Performing primary word segmentation preprocessing on Internet information data by artificial intelligence technology to obtain a result of the primary word segmentation preprocessing, wherein the result of the primary word segmentation preprocessing includes a number of words; Performing secondary word segmentation preprocessing on Internet information data by artificial intelligence technology to obtain secondary word segmentation preprocessing results, wherein the secondary word segmentation preprocessing results include a number of words; The number of words obtained by the first-level word segmentation preprocessing is compared with the number of words obtained by the second-level word segmentation preprocessing. If the comparison results are the same, the words obtained by the first-level word segmentation preprocessing are used as the words for segmenting the Internet information data; If the comparison results are different, the words obtained by the first-level word segmentation preprocessing and the words obtained by the second-level word segmentation preprocessing are mixed, and the mixed words are used as the words for segmenting the Internet information data.

4. The Internet information intelligent decision-making system based on artificial intelligence according to claim 3 is characterized in that: The process of preprocessing Internet information data using artificial intelligence technology for first-level word segmentation includes: Set the maximum match length of the first level, and set the maximum word length of the first level to L; Starting from the first character of the Internet information data, the first L characters are obtained, and the obtained L characters are used as the character fragments to be matched; Get the words segmented by the character fragments to be matched consisting of the first L characters; Obtain a character segment consisting of the (L+1)th to 2Lth characters, use the obtained character segment consisting of the (L+1)th to 2Lth characters as the character segment to be matched, obtain words segmented from the character segment to be matched consisting of the (L+1)th to 2Lth characters, obtain a character segment consisting of the (2L+1)th to 3Lth characters, use the obtained character segment consisting of the (2L+1)th to 3Lth characters as the character segment to be matched, obtain words segmented from the character segment to be matched consisting of the (2L+1)th to 3Lth characters, and so on, to obtain words segmented from the character segments consisting of the remaining characters of the Internet information data.

5. The Internet information intelligent decision-making system based on artificial intelligence according to claim 4 is characterized in that: The process of obtaining the words segmented by the character fragment to be matched composed of the first L characters includes: The character segment to be matched consisting of the first L characters is matched with the words stored in the word database. If the word identical to the character segment to be matched exists in the word database, the character segment to be matched is cut out from the Internet information data as a word. If the word identical to the character segment to be matched does not exist in the word database, the first (L-1) characters of the character segment to be matched are matched with the words stored in the word database. If there is a word in the word database that is identical to the first (L-1) characters of the character segment to be matched, the first (L-1) characters of the character segment to be matched are segmented out from the Internet information data as a word, and the remaining character segment to be matched after segmentation is matched with the words stored in the word database. If there is a word in the word database that is identical to the character segment to be matched after segmentation, the remaining character segment to be matched after segmentation is segmented out from the Internet information data as a word. If there is no word in the word database that is identical to the character segment to be matched, the remaining character segment to be matched after segmentation is retained. If there is no word in the word database that is identical to the first (L-1) characters of the character segment to be matched, then the remaining unmatched characters in the character segment to be matched are matched with the words stored in the word database; If there is a word in the word database that is identical to the remaining unmatched characters in the character segment to be matched, the remaining unmatched characters in the character segment to be matched are segmented out from the Internet information data as a word; if there is no word in the word database that is identical to the remaining unmatched characters in the character segment to be matched, the remaining unmatched characters in the character segment to be matched are retained, and the first (L-2) characters of the character segment to be matched are matched with the words stored in the word database, and so on, ..., until the first character of the character segment to be matched is matched with the words stored in the word database, or there is a word in the word database that is identical to the first L or first (L-1) or first (L-2) or first (L-3) or first (L-4) or ... or first two characters of the character segment to be matched, and the word segmented from the character segment to be matched consisting of the first L characters is obtained.

6. The Internet information intelligent decision-making system based on artificial intelligence according to claim 5 is characterized in that: The process of performing secondary word segmentation preprocessing on Internet information data through artificial intelligence technology includes: Set the secondary maximum matching length, and set the secondary maximum word length to L, that is, the secondary maximum word length is the same as the length of the longest word stored in the word database; Starting from the last character of the Internet information data, obtaining the last L characters, using the obtained last L characters as the character segment to be matched, and obtaining the words segmented by the character segment to be matched consisting of the last L characters; Obtain a character segment consisting of the last (L+1) to 2L characters, use the obtained character segment consisting of the last (L+1) to 2L characters as the character segment to be matched, obtain words segmented from the character segment to be matched consisting of the last (L+1) to 2L characters, and so on, obtain words segmented from the character segment consisting of the remaining characters of the Internet information data.

7. The Internet information intelligent decision-making system based on artificial intelligence according to claim 6 is characterized in that: The process of the data processing module processing the words obtained by segmenting the Internet information data includes: Obtaining the occurrence frequency of the words segmented from the Internet information data, and obtaining the activity value of the words segmented from the Internet information data according to the obtained occurrence frequency of the words segmented from the Internet information data; The activity values ​​of the obtained words of the Internet information data segmentation are sorted from large to small, and the words of the Internet information data segmentation corresponding to the first k activity values ​​are obtained, where k is a positive even number not equal to zero, and the words of the Internet information data segmentation corresponding to the first k activity values ​​obtained are recorded as reference words.

8. The Internet information intelligent decision-making system based on artificial intelligence according to claim 7 is characterized in that: The process of the intelligent decision module making intelligent decisions according to the activity values ​​of the words obtained by segmenting the Internet information data includes: Obtaining Internet information data being browsed by a user, and obtaining activity values ​​of words segmented from the Internet information data being browsed by the user, sorting the obtained activity values ​​of the words segmented from the Internet information data being browsed by the user from large to small, obtaining the words segmented from the Internet information data being browsed by the user corresponding to the first k activity values, and recording the words segmented from the Internet information data being browsed by the user corresponding to the obtained first k activity values ​​as standard words; The obtained standard words are compared with the reference words. If there are k / 2 or more reference words that are the same as the standard words, the Internet information data to be pushed will be pushed to the user. If there are not k / 2 or more reference words that are the same as the standard words, the Internet information data to be pushed will be prohibited from being pushed to the user.

Images