CN105701680B - Personalized recommendation method and system based on opposite attribute knowledge base - Google Patents

Abstract

The invention discloses a personalized recommendation method and system. The method includes: acquiring a recommendation result sequence recommended by a current recommendation system to a user; acquiring a preset number of recommendation results in a preset direction in the recommendation result sequence as the initial Recommendation result sequence; query whether the opposite attribute of the user is stored in the opposite attribute knowledge base according to the user's identity information; when the query result is yes, respectively match each recommendation result in the initial recommendation result sequence with the opposite attribute of the user; delete In the initial recommendation result sequence, the matching result with the opposite attribute of the user conforms to the recommendation result of the preset condition; the final recommendation result sequence is obtained according to the remaining recommendation results of the initial recommendation result sequence; and the final recommendation result sequence is output. The present invention improves the accuracy of recommending users, thereby improving the user's adoption rate of the recommended results, and enhancing the value of the recommending system to users.

Description

Personalized recommendation method and system based on opposite attribute knowledge base

technical field

The present invention relates to the technical field of recommendation, in particular to a personalized recommendation method and system based on an opposite attribute knowledge base.

Background technique

With the continuous expansion of e-commerce scale and the rapid growth of the number and types of products, users need to spend a lot of time to find the products they want to buy. The process of browsing through a lot of irrelevant information and products will undoubtedly keep consumers away. In order to solve these problems, personalized recommendation technology came into being. Personalized recommendation technology is an advanced business intelligence platform based on massive data mining to help e-commerce sites provide fully personalized decision support and information services for their customers.

However, when the existing personalized recommendation system recommends based on the analysis of the historical data of the user's purchased products, there may be wrong recommendations. For example, the recommendation system finds that user A and user B have similar interest characteristics and purchasing behaviors. Recently, user A purchased a sanitary napkin, and as a result, the recommendation system recommended the sanitary napkin to user B. Is this recommendation accurate? The reason why user A and user B have similar interest characteristics and purchasing behaviors in the past is because user A and user B are siblings, but user A is a woman who recently had menarche, so she started the first time. Buying sanitary napkins, but user B is a male, recommending sanitary napkins to user B is obviously a wrong recommendation. It can be seen that the recommendation results obtained by the existing recommendation technology often do not match the products the user wants to buy, resulting in incorrect recommendations, which in turn reduces the user's adoption rate of the recommendation results and reduces the value of the recommendation system to the user.

SUMMARY OF THE INVENTION

Based on the above situation, the present invention proposes a personalized recommendation method and system, which improves the accuracy of recommending users, thereby increasing the user's adoption rate of the recommendation results, and increasing the value of the recommendation system to users.

In order to achieve the above purpose, the embodiment of the technical solution of the present invention is:

A personalized recommendation method includes the following steps:

Obtain the recommendation result sequence recommended by the current recommendation system to the user;

Acquiring a preset number of recommendation results in a preset direction in the recommendation result sequence as an initial recommendation result sequence, where the preset recommendation number is less than or equal to the total number of recommendation results in the recommendation result sequence;

According to the identity information of the user, query whether to store the opposite attribute of the user in the user opposite attribute table pre-stored in the opposite attribute knowledge base;

When the query result is yes, respectively matching each recommendation result in the initial recommendation result sequence with the opposite attribute of the user;

Delete the recommendation results whose matching results with the opposite attributes of the user meet the preset conditions in the initial recommendation result sequence;

Obtain a final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence;

The final recommendation result sequence is output.

A personalized recommendation system, including:

The recommendation result sequence acquisition module is used to acquire the recommendation result sequence recommended by the current recommendation system to the user;

An initial recommendation result sequence acquisition module, configured to acquire a preset number of recommendation results in a preset direction in the recommendation result sequence as an initial recommendation result sequence, where the preset number of recommendations is less than or equal to the recommendation result sequence The total number of recommended results in;

an attribute query module, configured to query whether the user's opposite attribute is stored in the user's opposite attribute table pre-stored in the opposite attribute knowledge base according to the user's identity information;

a result matching module, configured to respectively match each recommendation result in the initial recommendation result sequence with the opposite attribute of the user when the query result is yes;

a result deletion module, configured to delete a recommendation result whose matching result with the opposite attribute of the user meets a preset condition in the initial recommendation result sequence;

a final recommendation result sequence acquisition module, configured to obtain a final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence;

A sequence output module, used for outputting the final recommendation result sequence.

Compared with the prior art, the beneficial effects of the present invention are as follows: the personalized recommendation method and system of the present invention, based on the opposite attribute knowledge base, through the preset number of recommendation results recommended by the current recommendation system to the user are stored in the opposite direction. The user's opposite attributes in the attribute knowledge base are matched, and the final recommendation result sequence is obtained according to the matching result, which improves the accuracy of the recommendation to the user, meets the user's personalized recommendation needs, improves the user's adoption rate of the recommendation result, and improves the recommendation system. User value, suitable for application.

Description of drawings

1 is a schematic flowchart of a personalized recommendation method in an embodiment of the present invention;

FIG. 2 is a flowchart of a personalized recommendation method based on a specific example of the method shown in FIG. 1;

FIG. 3 is a schematic structural diagram of a personalized recommendation system in an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and do not limit the protection scope of the present invention.

In one embodiment, the personalized recommendation method, as shown in Figure 1, includes the following steps:

Step S101: Obtain the recommendation result sequence recommended by the current recommendation system to the user;

Among them, the current recommendation system may be various existing recommendation systems, or may be a newly developed recommendation system; the recommendation results recommended by the recommendation system to users may be various types of recommendation results, such as product recommendation, clothing recommendation , book recommendation, video recommendation, picture recommendation, paper recommendation or friend recommendation, etc.;

Step S102: Acquire a preset number of recommendation results in a preset direction in the recommendation result sequence as an initial recommendation result sequence, where the preset number of recommendations is less than or equal to the total number of recommendation results in the recommendation result sequence;

For example, the number of recommendation results recommended by the recommendation system to a user is denoted as p, and the first n recommendation results in the p recommendation results are used as the n first recommendation results, and the initial recommendation result sequence is obtained. The system will recommend at least one recommendation result to the user, and select all or part of all the recommendation results recommended by the recommendation system to a user as the first recommendation result;

Step S103: query whether to store the opposite attribute of the user in the user opposite attribute table pre-stored in the opposite attribute knowledge base according to the identity information of the user;

For example, the user's opposite attribute is retrieved from the user's opposite attribute table in the opposite attribute knowledge base, and the user's opposite attribute table is retrieved through the user's identity information. When the corresponding user's identity information is retrieved, the user's identity is retrieved. The opposite attribute of the user corresponding to the information; the opposite attribute of the user can be collected in advance and stored in the opposite attribute knowledge base;

Step S104: when the query result is yes, match each recommendation result in the initial recommendation result sequence with the opposite attribute of the user;

The matching degree between a recommendation result and the opposite attribute of the user in the opposite attribute knowledge base is essentially the degree of contradiction between the recommendation result and the user's attribute; from the matching degree between a recommendation result and the user's opposite attribute, It can be seen that the degree of contradiction between the recommendation result and the attribute of the user, the greater the matching degree of a recommendation result and the opposite attribute of the user, the higher the degree of contradiction between the recommendation result and the attribute of the user ;

Step S105: delete a recommendation result whose matching result with the opposite attribute of the user meets a preset condition in the initial recommendation result sequence;

For example, when the matching degree of a recommendation result and the opposite attribute of the user is greater than the preset matching degree value (the minimum matching degree preset value is 0), it means that the recommendation result is inconsistent with the attribute of the user, delete it This recommendation result; the calculation of the matching degree can be converted into the calculation of the matching degree or similarity of the string, and the existing algorithm of the matching degree or similarity of the string can be used, such as the Edit distance method (the edit distance is used to calculate The minimum number of insertions, deletions and replacements required to convert from the original string (s) to the target string (t). Obviously, when one statement is edited into another statement, the minimum number of insertions, deletions and replacements is required. The greater the matching degree), the largest common substring LCS method (obviously, the longer the maximum common substring of the two sentences, the greater the matching degree of the two sentences); the calculation of the matching degree can also use the new matching degree algorithm, such as the number of common characters of two strings as the size of the matching degree;

Step S106: obtaining a final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence;

If the matching degree between a recommendation result and the opposite attribute of the user is greater than the preset matching degree value, it indicates that the recommendation result is contradictory with the attribute of the user. The recommendation results remaining after the recommendation results greater than the matching degree preset value are deleted are used as the final recommendation result sequence;

Step S107: Output the final recommendation result sequence.

The manner of outputting the final recommendation result to the user may be the manner adopted by the existing recommendation system, or may adopt other information output manners, such as the manner of a web page and the manner of a file.

As can be seen from the above description, the personalized recommendation method of the present invention, based on the opposite attribute knowledge base, greatly eliminates the recommendation results that contradict the user attributes, satisfies the needs of the user for personalized recommendation, improves the accuracy of the recommendation, and improves the user experience. The adoption rate of the recommendation results increases the value of the recommendation system to users.

In addition, in a specific example, the user's identity information includes a user ID (identification number), the user opposite attribute table includes a user field and a user opposite attribute field, the user field stores the user ID, the user The opposite attribute of the user is stored in the opposite attribute field, and the opposite attribute of the user is obtained according to the attribute of the user. Any one or any combination.

The user opposite attribute table in the opposite attribute knowledge base includes a user field and a user opposite attribute field, where the user ID is stored in the user field, and the user opposite attribute field is stored in the opposite attribute of the user. Retrieving the opposite attribute of the user from the opposite attribute knowledge base is to retrieve the opposite attribute knowledge base through the user ID. When the corresponding user ID is retrieved, the opposite attribute of the user corresponding to the user ID is retrieved. The opposite attribute of the user is obtained according to the attribute of the user. The attribute of the user may include information related to the user such as the user's age, gender, occupation, education, major, specialty, hobby, and geographic location, etc., to meet the needs of various applications.

The steps of obtaining the opposite attribute of the user: first, query the antonym of the keyword in the user's attribute; when the antonym can be queried, the antonym is used as the opposite attribute of the user; when the antonym cannot be queried, the keyword in the user's attribute is stored in the database The keyword of the same type that is farthest from the keyword in the middle query is taken as the opposite attribute of the user. Among them, various types of keywords and their distances are stored in the database in advance, and the distance here refers to the difference. For example, the keyword with the same academic type is farthest from "primary school" is obviously "postdoctoral".

In addition, in a specific example, when the query result is no, it is determined whether the user is a registered user of the current recommendation system;

When the determination result is yes, obtain the attribute of the user from the registration information of the user in the current recommendation system, obtain the opposite attribute of the user according to the attribute of the user, and store the opposite attribute of the user in the opposite attribute knowledge base;

When the determination result is no, an information collection window is generated, the attributes of the user are collected, the opposite attributes of the user are obtained according to the attributes of the user, and the opposite attributes of the user are stored in the opposite attribute knowledge base .

For example, the opposite attribute of the user is retrieved from the opposite attribute knowledge base. When the user or the opposite attribute of the user cannot be retrieved from the opposite attribute knowledge base, it is determined whether the user is a registered user of the recommendation system. If the user is a registered user, the user attribute in the user's registration information is queried, and the user's opposite attribute is obtained according to the user's attribute and added to the opposite attribute knowledge base. When the user is not a registered user, a dialog box will pop up to ask the user, or it can be obtained by other interactive methods. Or query to obtain the attributes of the user, obtain the opposite attributes of the user according to the attributes of the user and add them to the knowledge base of opposite attributes. Obtain the attribute of the user, obtain the opposite attribute of the user according to the attribute of the user, and add the opposite attribute knowledge base.

In addition, in a specific example, the step of respectively matching each recommendation result in the initial recommendation result sequence with the opposite attribute of the user includes:

respectively converting each recommendation result in the initial recommendation result sequence and the opposite attributes of the user into character strings;

The degree of matching between the character string converted from each recommendation result in the initial recommendation result sequence and the character string converted from the opposite attribute of the user is calculated respectively.

Each recommendation result in the initial recommendation result sequence and the opposite attribute of the user can be converted into strings, and the calculation of the matching degree between the two can be converted into the calculation of the matching degree or similarity of the string. The degree of matching of the opposite attribute can show the degree of contradiction between the recommendation result and the attribute of the user. The higher the degree of inconsistency of attributes.

The calculation of the matching degree can be converted into the calculation of the matching degree or similarity of strings, and the existing algorithm of matching degree or similarity of strings can be used, such as the Edit distance method (the edit distance is used to calculate the distance from the original string (s). ) The minimum number of insertions, deletions and replacements required to convert to the target string (t). Obviously, when a statement is edited into another statement with the minimum number of insertions, deletions and replacements, the smaller the number of insertions, deletions and replacements, the greater the degree of matching ), the maximum common substring LCS method (obviously, the longer the maximum common substring of two sentences, the greater the matching degree of the two sentences); the calculation of the matching degree can also use a new matching degree algorithm, such as the The number of characters in common between the two strings is used as the size of the matching degree.

In addition, in a specific example, the step of deleting a recommendation result whose matching result with the opposite attribute of the user meets a preset condition in the initial recommendation result sequence includes:

Respectively obtain the same number of characters of the character string transformed by each recommendation result in the sequence of initial recommendation results and the character string transformed by the opposite attribute of the user;

Delete the recommendation result whose number of identical characters in the character string converted with the opposite attribute of the user is greater than the preset value in the initial recommendation result sequence.

The character string converted from a recommendation result is the same as the character string converted from the opposite attribute of the user. The number of characters is greater than the preset value (for example, greater than 0), indicating that the recommendation result is inconsistent with the attribute of the user. The recommendation results with conflicting attributes can improve the accuracy of the recommendation.

In order to better understand the above method, an application example of the personalized recommendation method of the present invention is described in detail below.

As shown in Figure 2, the application example may include the following steps:

Step S201: Obtain a recommendation result sequence recommended by a recommendation system of a shopping website to user A;

Step S202: Obtain the first 11 recommended results in the above-mentioned recommendation result sequence as the initial recommendation result sequence, and the total number of recommended results in the above-mentioned recommendation result sequence is greater than or equal to 11; the 11 recommended results are: (1) Marumi Sunscreen Women Waterproof genuine whitening sunscreen essence isolation milk SPF30 UV protection body 45g; (2) free shipping new large mesh shoes men's sandals student casual sports shoes men's summer mesh shoes men's plus size men's shoes; (3) Zhongge Gionee S7 mobile phone case ELIFE7 Shell GN9006 transparent silicone protection soft cover shell accessories back cover tide; (4) iphone4s mobile phone shell apple 5s shell ultra-thin plastic frosted protection hard shell black and white red tide men and women simple; (5) men's bag thickened canvas backpack men's bag casual Travel bag trendy men's bag Korean version men's backpack; (6) Inman 2015 summer new vest women's summer outer wear printed sleeveless shirt summer vest suspender 8520300114; (7) Morigu bird Korean version of the tide 2015 spring and autumn women's canvas shoes platform shoes high-top women's shoes thick bottom Cloth shoes; (8) Big sim Korean custom summer clothes must-have ripped solid color simple round neck loose short-sleeved women's T-shirt; (9) middle-aged and elderly women's summer T-shirt chiffon shirt top large size mother's loose embroidered short-sleeved elderly People clothes; (10) Xiaomi 2s mobile phone protective case two s back cover mobile phone case tide Xiaomi 2 leather case m2 ultra-thin hard flip cover free shipping; (11) South Korea's Dongdaemun 2015 summer new women's fashion floral loose short-sleeved chiffon cake shirt crop top;

Step S203: query whether the opposite attribute of user A is stored in the user opposite attribute table pre-stored in the opposite attribute knowledge base according to the ID of user A; the user opposite attribute table includes a user field and a user opposite attribute field, in which the user field is The user ID is stored, and the opposite attribute of the user is stored in the user's opposite attribute field, and the opposite attribute of the user is obtained according to the attribute of the user, and the attribute of the user includes the age and gender of the user; the opposite attribute knowledge base can store the opposite attribute of the user in advance; a In the embodiment, the user attribute table is shown in Table 1, and the user opposite attribute table is shown in Table 2;

Table 1 User attribute table

User ID User properties 14233 old male 14234 young female 14235 young male 14236 old woman

Table 2 User opposite attribute table

Step S204: when the query result is yes, convert the above 11 recommended results and the opposite attributes of user A into character strings respectively; when the query result is no, determine whether user A is a registered user of the above-mentioned shopping website; If yes, obtain the attribute of user A from the registration information of user A of the above-mentioned shopping website, obtain the opposite attribute of user A according to the attribute of user A, and store the opposite attribute of user A in the opposite attribute knowledge base; If no, generate an information collection window, collect the attributes of user A, obtain the opposite attributes of user A according to the attributes of user A, and store the opposite attributes of user A in the opposite attribute knowledge base;

Knowing that the ID of User A is 14235, it can be queried from the user's opposite attribute table pre-stored in the above-mentioned opposite attribute knowledge base that the opposite attribute of User A is "old woman";

If the opposite attribute of user A cannot be queried in the user opposite attribute table pre-stored in the above-mentioned opposite attribute knowledge base, then determine whether user A is a registered user of the above-mentioned shopping website, and when user A is a registered user, query the user's registration information The attributes of user A in the user A, according to the attributes of user A, the opposite attributes of user A are obtained and added to the knowledge base of opposite attributes. When user A is not a registered user, a dialog box will pop up to ask user A, or it can be obtained by other interactive methods or query methods. Attributes of user A, according to the attributes of user A, the opposite attributes of user A are obtained and added to the opposite attribute knowledge base. If there is no attribute of user A in the user's registration information, you can also ask the user through a pop-up dialog box or obtain the user through other interactive methods. The attribute of user A, according to the attribute of user A, the opposite attribute of user A is obtained and added to the opposite attribute knowledge base;

The attribute of user A is "young male", and the keywords are "young" and "male", the antonyms of the above keywords are obtained by querying "old" and "female", and "old female" is regarded as the opposite attribute of user A;

Step S205: Calculate the matching degree of the character string transformed by the above 11 recommendation results and the character string transformed by the opposite attribute of user A respectively;

The calculation of the matching degree can be converted into the calculation of the matching degree or similarity of strings, and the number of common characters of the two strings can also be used as the size of the matching degree; The size of the degree can show the degree of contradiction between the recommendation result and the attribute of the user; the greater the degree of matching between a recommendation result and the opposite attribute of the user, the degree of contradiction between the recommendation result and the user's attribute. higher;

Step S206: respectively obtaining the same number of characters of the character string converted from the above 11 recommendation results and the character string converted from the opposite attribute of user A;

The calculation method of the matching degree: take the same number of characters of the two strings as the size of the matching degree:

(1) Marumi Sunscreen Female Waterproof Authentic Whitening Sunscreen Essence Isolation Milk SPF30 UV Protection Whole Body 45g The number of identical characters in the string converted by the opposite attributes of the old woman and the user's armor is 1;

(2) Free shipping new large mesh shoes, men's sandals, students' casual sports shoes, men's summer mesh shoes, men's plus size men's shoes, old women's, and user A's opposite attributes are converted to a string with the same number of characters as 0;

(3) Zhongge Gionee S7 mobile phone case ELIFE7 case GN9006 transparent silicone protective soft case case accessories back cover trendy old women and user A The number of identical characters in the string converted by the opposite attributes is 0;

(4) iphone4s mobile phone shell apple 5s shell ultra-thin plastic frosted protection hard shell black and white red tide men and women simple old women and user A with the opposite attributes of the string converted to the same character number is 1;

(5) Free shipping men's bags, thickened canvas backpacks, men's bags, leisure travel bags, trendy men's bags, Korean version of men's backpacks, old women's, and user A's opposite attributes of the character string converted to the same number of characters are 0;

(6) Inman 2015 summer clothes new vest women's summer outer wear printed sleeveless shirt summer vest suspenders 8520300114 old women and user A's opposite attributes of the string converted to the same character number is 1;

(7) Morigu Bird Korean version of the tide 2015 spring and autumn women's canvas shoes, platform shoes, high-top, height-enhancing women's shoes, thick-soled cloth shoes, the number of identical characters in the strings converted by the opposite attributes of the elderly women and user A is 2;

(8) The number of identical characters in the string converted by the opposite attributes of the old woman and the user's armor is 1;

(9) Middle-aged and elderly women's summer clothes T-shirts, chiffon shirts, tops, large-size mother's clothes, loose embroidery, short-sleeved clothes for the elderly

(10) Mi 2s mobile phone protective case 2 s back cover mobile phone case trendy Mi 2 leather case shell m2 ultra-thin hard flip cover free shipping The number of the same characters in the string converted by the opposite attributes of the elderly women and user A is 0;

(11) South Korea's Dongdaemun 2015 summer new women's fashion Floral Loose Short Sleeve Chiffon Cake Shirt Short Top Shirt The number of identical characters in the string converted by the opposite attributes of the old women and user A is 1;

Step S207: delete the recommendation results whose number of identical characters is not zero in the character string converted with the opposite attribute of user A from the above 11 recommendation results;

i.e. remove:

Marumi sunscreen female waterproof authentic whitening sunscreen essence isolation milk SPF30 UV protection body 45g;

iphone4s mobile phone shell apple 5s shell ultra-thin plastic frosted protection hard shell black and white red tide men and women simple;

Inman 2015 summer new vest women's summer outer wear printed sleeveless shirt summer vest suspenders 8520300114;

Morigu bird Korean version of the tide 2015 spring and autumn women's canvas shoes platform shoes high-top women's shoes thick-soled cloth shoes;

Big sim Korean custom summer clothes must-have hole solid color simple round neck loose short-sleeved women's T-shirt;

Middle-aged and elderly women's summer clothes T-shirts, chiffon shirts, tops, large size mother's clothes, loose embroidered short-sleeved clothes for the elderly;

South Korea's Dongdaemun 2015 summer new women's fashion floral loose short-sleeved chiffon cake shirt short top;

Step S208: Obtain the final recommendation result sequence according to the remaining recommendation results of the above 11 recommendation result sequences:

(1) Free shipping new large mesh shoes men's sandals student casual sports shoes men's summer mesh shoes men's plus size men's shoes;

(2) Zhongge Gionee S7 mobile phone case ELIFE7 shell GN9006 transparent silicone protective soft cover shell accessories back cover damp;

(3) Free shipping men's bag thickened canvas backpack men's bag leisure travel bag trendy men's bag Korean version of the men's backpack;

(4) Mi 2s mobile phone protective case 2s back cover mobile phone case tide Mi 2 leather case shell m2 ultra-thin hard flip cover free shipping;

Step S209: Output the above-mentioned final recommendation result sequence.

The manner of outputting the final recommendation result to the user may be the manner adopted by the existing recommendation system, or may adopt other information output manners, such as the manner of a web page and the manner of a file.

In this application example, the remaining recommendation results after deleting the recommendation results whose matching degree with the opposite attribute of user A is not 0 in the 11 recommendation results is taken as the final recommendation result, which greatly eliminates the recommendation results that contradict the user's attributes, and satisfies the The user's personalized recommendation needs, improve the accuracy of the recommendation, improve the user's adoption rate of the recommendation results, and enhance the value of the recommendation system to the user.

In one embodiment, the personalized recommendation system, as shown in Figure 3, includes:

The recommendation result sequence obtaining module 301 is used to obtain the recommendation result sequence recommended by the current recommendation system to the user;

The initial recommendation result sequence acquisition module 302 is configured to acquire a preset recommended number of recommendation results in a preset direction in the recommendation result sequence as an initial recommendation result sequence, and the preset recommendation number is less than or equal to the recommendation result The total number of recommended results in the sequence;

The attribute query module 303 is configured to query whether the opposite attribute of the user is stored in the user opposite attribute table pre-stored in the opposite attribute knowledge base according to the identity information of the user;

A result matching module 304, configured to respectively match each recommendation result in the initial recommendation result sequence with the opposite attribute of the user when the query result is yes;

A result deletion module 305, configured to delete a recommendation result whose matching result with the opposite attribute of the user meets a preset condition in the initial recommendation result sequence;

A final recommendation result sequence obtaining module 306, configured to obtain a final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence;

The sequence output module 307 is configured to output the final recommendation result sequence.

In addition, in a specific example, the user's identity information includes a user ID, the user opposite attribute table includes a user field and a user opposite attribute field, the user field stores the user ID, and the user opposite attribute field stores The opposite attribute of the user, the opposite attribute of the user is obtained according to the attribute of the user, and the attribute of the user includes any one or any one of the user's age, gender, occupation, education, major, specialty, hobby, and geographic location. combination.

The user opposite attribute table in the opposite attribute knowledge base includes a user field and a user opposite attribute field, where the user ID is stored in the user field, and the user opposite attribute field is stored in the opposite attribute of the user. Retrieving the opposite attribute of the user from the opposite attribute knowledge base is to retrieve the opposite attribute knowledge base through the user ID. When the corresponding user ID is retrieved, the opposite attribute of the user corresponding to the user ID is retrieved. The opposite attribute of the user is obtained according to the attribute of the user. The attribute of the user may include information related to the user such as the user's age, gender, occupation, education, major, specialty, hobby, and geographic location, etc., to meet the needs of various applications.

The steps of obtaining the opposite attribute of the user: first, query the antonym of the keyword in the user's attribute; when the antonym can be queried, the antonym is used as the opposite attribute of the user; when the antonym cannot be queried, the keyword in the user's attribute is stored in the database The keyword of the same type that is farthest from the keyword in the middle query is taken as the opposite attribute of the user. Among them, various types of keywords and their distances are stored in the database in advance, and the distance here refers to the difference. For example, the keyword with the same academic type is farthest from "primary school" is obviously "postdoctoral".

As shown in FIG. 3, in a specific example, the system further includes an attribute acquisition module 308, configured to determine whether the user is a registered user of the current recommendation system when the query result is no;

When the determination result is yes, obtain the attribute of the user from the registration information of the user in the current recommendation system, obtain the opposite attribute of the user according to the attribute of the user, and store the opposite attribute of the user in the opposite attribute knowledge base;

When the determination result is no, an information collection window is generated, the attributes of the user are collected, the opposite attributes of the user are obtained according to the attributes of the user, and the opposite attributes of the user are stored in the opposite attribute knowledge base .

For example, the opposite attribute of the user is retrieved from the opposite attribute knowledge base. When the user or the opposite attribute of the user cannot be retrieved from the opposite attribute knowledge base, it is determined whether the user is a registered user of the recommendation system. If the user is a registered user, the user attribute in the user's registration information is queried, and the user's opposite attribute is obtained according to the user's attribute and added to the opposite attribute knowledge base. When the user is not a registered user, a dialog box will pop up to ask the user, or it can be obtained by other interactive methods. Or query to obtain the attributes of the user, obtain the opposite attributes of the user according to the attributes of the user and add them to the knowledge base of opposite attributes. Obtain the attribute of the user, obtain the opposite attribute of the user according to the attribute of the user, and add the opposite attribute knowledge base.

As shown in FIG. 3, in a specific example, the result matching module 304 includes:

A conversion unit 3041, configured to convert each recommendation result in the initial recommendation result sequence and the opposite attribute of the user into character strings;

The matching unit 3042 is configured to calculate the matching degree of the character string transformed by each recommendation result in the initial recommendation result sequence and the character string transformed by the opposite attribute of the user, respectively.

Each recommendation result in the initial recommendation result sequence and the opposite attribute of the user can be converted into strings, and the calculation of the matching degree between the two can be converted into the calculation of the matching degree or similarity of the string. The degree of matching of the opposite attribute can show the degree of contradiction between the recommendation result and the attribute of the user. The higher the degree of inconsistency of attributes.

The calculation of the matching degree can be converted into the calculation of the matching degree or similarity of strings, and the existing algorithm of matching degree or similarity of strings can be used, such as the Edit distance method (the edit distance is used to calculate the distance from the original string (s). ) The minimum number of insertions, deletions and replacements required to convert to the target string (t). Obviously, when a statement is edited into another statement with the minimum number of insertions, deletions and replacements, the smaller the number of insertions, deletions and replacements, the greater the degree of matching ), the maximum common substring LCS method (obviously, the longer the maximum common substring of two sentences, the greater the matching degree of the two sentences); the calculation of the matching degree can also use a new matching degree algorithm, such as the The number of common characters of the two strings is used as the size of the matching degree.

As shown in FIG. 3, in a specific example, the result deletion module 305 includes:

The obtaining unit 3051 is used to obtain the same number of characters of the character string transformed by each recommendation result in the initial recommendation result sequence and the character string transformed by the opposite attribute of the user;

A deletion unit 3052, configured to delete a recommendation result in which the number of identical characters of the character string converted with the opposite attribute of the user in the initial recommendation result sequence is greater than a preset value.

The character string converted from a recommendation result is the same as the character string converted from the opposite attribute of the user. The number of characters is greater than the preset value (for example, greater than 0), indicating that the recommendation result is inconsistent with the attribute of the user. The recommendation results with conflicting attributes can improve the accuracy of the recommendation.

Based on the system of this embodiment shown in FIG. 3 , a specific working process may be as follows:

First, the recommendation result sequence acquisition module 301 acquires the recommendation result sequence recommended by the current recommendation system to the user; the initial recommendation result sequence acquisition module 302 acquires a preset number of recommendation results in a preset direction in the recommendation result sequence as the initial recommendation result sequence, the preset first recommendation number is less than or equal to the total number of recommendation results in the recommendation result sequence; the attribute query module 303 searches the user's opposite attribute table pre-stored in the opposite attribute knowledge base according to the user's identity information Whether to store the opposite attribute of the user; when the query result is yes, the conversion unit 3041 in the result matching module 304 converts each recommendation result in the initial recommendation result sequence and the opposite attribute of the user into character strings; The matching unit 3042 respectively calculates the matching degree between the character string converted from each recommendation result in the initial recommendation result sequence and the character string converted from the opposite attribute of the user; when the query result is no, the attribute acquisition module 308 judges the user Whether it is a registered user of the current recommendation system; when the determination result is yes, obtain the user's attribute from the registration information of the user in the current recommendation system, and obtain the user's attribute according to the user's attribute. Opposite attribute, store the opposite attribute of the user in the opposite attribute knowledge base; when the judgment result is no, generate an information collection window, collect the attribute of the user, and obtain the user according to the attribute of the user The opposite attribute of the user is stored in the opposite attribute knowledge base; the obtaining unit 3051 in the result deletion module 305 obtains the character strings transformed by each recommendation result in the initial recommendation result sequence and the The same number of characters in the character string converted by the opposite attribute of the user; the deletion unit 3052 deletes the recommendation result whose number of identical characters in the character string converted with the opposite attribute of the user is greater than the preset value in the initial recommendation result sequence; finally The recommendation result sequence acquisition module 306 obtains the final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence; the sequence output module 307 outputs the final recommendation result sequence.

It can be seen from the above description that the personalized recommendation system of the present invention, based on the opposite attribute knowledge base, greatly eliminates the recommendation results that contradict the user attributes, satisfies the user's needs for personalized recommendation, improves the accuracy of the recommendation, and improves the user experience. The adoption rate of the recommendation results increases the value of the recommendation system to users.

The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above-described embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be regarded as the scope described in this specification.

The above-mentioned embodiments only represent several embodiments of the present invention, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can also be made, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims (8)

1. a personalized recommendation method, is characterized in that, comprises the following steps: Obtain the recommendation result sequence recommended by the current recommendation system to the user; Acquiring a preset number of recommendation results in a preset direction in the recommendation result sequence as an initial recommendation result sequence, where the preset recommendation number is less than or equal to the total number of recommendation results in the recommendation result sequence; According to the user's identity information, query whether the user's opposite attribute is stored in the user's opposite attribute table pre-stored in the opposite attribute knowledge base; the step of obtaining the user's opposite attribute includes: when the user's opposite attribute can be queried in the database. When the antonym of the keyword in the attribute of the user is the antonym of the keyword, the antonym of the keyword is used as the opposite attribute of the user; when the antonym of the keyword in the attribute of the user is not queried in the database, the distance from the The keyword of the same type with the farthest keyword is used as the opposite attribute of the user; the distance refers to the difference; When the query result is yes, respectively matching each recommendation result in the initial recommendation result sequence with the opposite attribute of the user; When the query result is no, it is judged whether the user is a registered user of the current recommendation system; when the judgment result is yes, the attribute of the user is obtained from the registration information of the user of the current recommendation system, The opposite attribute of the user is obtained according to the attribute of the user, and the opposite attribute of the user is stored in the opposite attribute knowledge base; when the judgment result is no, an information collection window is generated to collect the attribute of the user , obtain the opposite attribute of the user according to the attribute of the user, and store the opposite attribute of the user in the opposite attribute knowledge base; Delete the recommendation result whose matching result with the opposite attribute of the user meets the preset condition in the initial recommendation result sequence; the preset condition is that the matching degree of the recommendation result and the opposite attribute of the user is greater than the matching degree prediction. set value; Obtain a final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence; The final recommendation result sequence is output. 2. The personalized recommendation method according to claim 1, wherein the user's identity information includes a user ID, the user opposite attribute table includes a user field and a user opposite attribute field, and the user field stores the user ID, the user's opposite attribute field stores the user's opposite attribute, the user's opposite attribute is obtained according to the user's attribute, and the user's attribute includes the user's age, gender, occupation, education, major, specialty, hobby and any one or any combination of geographic locations. 3. The personalized recommendation method according to claim 1, wherein the step of respectively matching each recommendation result in the initial recommendation result sequence with the opposite attribute of the user comprises: respectively converting each recommendation result in the initial recommendation result sequence and the opposite attributes of the user into character strings; The degree of matching between the character string converted from each recommendation result in the initial recommendation result sequence and the character string converted from the opposite attribute of the user is calculated respectively. 4. The personalized recommendation method according to claim 3, wherein the step of deleting a recommendation result whose matching result with the opposite attribute of the user in the initial recommendation result sequence meets a preset condition comprises: Respectively obtain the same number of characters of the character string transformed by each recommendation result in the sequence of initial recommendation results and the character string transformed by the opposite attribute of the user; Delete the recommendation result whose number of identical characters in the character string converted with the opposite attribute of the user is greater than the preset value in the initial recommendation result sequence. 5. A personalized recommendation system, comprising: The recommendation result sequence acquisition module is used to acquire the recommendation result sequence recommended by the current recommendation system to the user; An initial recommendation result sequence acquisition module, configured to acquire a preset number of recommendation results in a preset direction in the recommendation result sequence as an initial recommendation result sequence, where the preset number of recommendations is less than or equal to the recommendation result sequence The total number of recommended results in; The attribute query module is used for querying whether the opposite attribute of the user is stored in the user opposite attribute table pre-stored in the opposite attribute knowledge base according to the identity information of the user; the step of obtaining the opposite attribute of the user includes: When the antonym of the keyword in the attribute of the user is queried in the database, the antonym of the keyword is used as the opposite attribute of the user; when the antonym of the keyword in the attribute of the user is not queried in the database, Take the keyword of the same type that is farthest from the keyword in the database as the opposite attribute of the user; a result matching module, configured to respectively match each recommendation result in the initial recommendation result sequence with the opposite attribute of the user when the query result is yes; an attribute acquisition module, configured to determine whether the user is a registered user of the current recommendation system when the query result is no; acquire from the registration information of the user of the current recommendation system when the determination result is yes For the attribute of the user, obtain the opposite attribute of the user according to the attribute of the user, and store the opposite attribute of the user in the opposite attribute knowledge base; when the judgment result is no, an information collection window is generated, collecting the attributes of the user, obtaining the opposite attribute of the user according to the attribute of the user, and storing the opposite attribute of the user in the opposite attribute knowledge base; A result deletion module, configured to delete a recommendation result whose matching result with the opposite attribute of the user meets a preset condition in the initial recommendation result sequence; The matching degree is greater than the matching degree preset value; a final recommendation result sequence acquisition module, configured to obtain a final recommendation result sequence according to the remaining recommendation results of the initial recommendation result sequence; A sequence output module, used for outputting the final recommendation result sequence. 6 . The personalized recommendation system according to claim 5 , wherein the user's identity information includes a user ID, the user opposite attribute table includes a user field and a user opposite attribute field, and the user field stores the user ID, the user's opposite attribute field stores the user's opposite attribute, the user's opposite attribute is obtained according to the user's attribute, and the user's attribute includes the user's age, gender, occupation, education, major, specialty, hobby and any one or any combination of geographic locations. 7. The personalized recommendation system according to claim 5, wherein the result matching module comprises: a conversion unit, configured to convert each recommendation result in the initial recommendation result sequence and the opposite attribute of the user into character strings; A matching unit, configured to respectively calculate the matching degree of the character string transformed from each recommendation result in the initial recommendation result sequence and the character string transformed from the opposite attribute of the user. 8. The personalized recommendation system according to claim 7, wherein the result deletion module comprises: an obtaining unit, configured to obtain the same number of characters of the character string transformed by each recommendation result in the initial recommendation result sequence and the character string transformed by the opposite attribute of the user; A deletion unit, configured to delete a recommendation result whose number of identical characters in the character string converted with the opposite attribute of the user is greater than a preset value in the initial recommendation result sequence.

Images