An information recommendation method and system based on artificial intelligence

Abstract

The present invention relates to the technical field of data processing, and particularly relates to an information recommendation method and system based on artificial intelligence. It acquires the push information for users within a preset historical time period, and obtains the depth of the user's information cocoon based on the push information for the user; it acquires the satisfaction degree of the user for the push information according to the viewing duration of the user for each push information; it combines the depth of the information cocoon and the satisfaction degree to obtain the information recommendation degree; it acquires the difference in the viewing duration between two adjacent times of the user for the push information of the same attribute, and obtains the information acceptance degree of the user for the push information of each attribute; it recommends information to the user according to the information recommendation degree and the information acceptance degree, which can recommend more comprehensive data information for the user, eliminate the push limitation, realize the diversity of data information push, and enable the user to effectively contact new interests or potential needs.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an information recommendation method and system based on artificial intelligence. Background Art

[0002] The Internet has gradually become the main platform for people to obtain information. Most modern Internet platforms rely on complex algorithms to push personalized content based on users' interests, browsing records, and social behaviors. This recommendation mechanism seemingly improves the user experience and makes information acquisition more accurate and efficient. However, it also makes users more and more easily confined to their known fields during browsing. Users mostly see content they approve or are interested in, while information contrary to this is difficult to come into view, resulting in an increase in the singularity and one-sidedness of information. This information "filter bubble" gradually forms the so-called "information cocoon room", where people's horizons are gradually "circumscribed" by algorithms, ignoring diverse viewpoints and comprehensive information. As a result, people's cognition and horizons become narrow, and the exposure to new and different ideas and knowledge becomes less and less.

[0003] Existing information recommendation algorithms usually perform personalized recommendations by analyzing the similarity of users' interests and behaviors. Specifically, first, it is assumed that users prefer information with certain specific attributes, and then based on the interaction behaviors between users and this information, the understanding of users' true interests is gradually adjusted and optimized. Through data mining and analysis algorithms, the recommendation system can identify information with similar attributes and recommend it to users. However, this method has certain limitations: it usually only recommends information highly similar to users' historical interests, over-relying on personalization, which will lead to the lack of information diversity and limit the opportunities for users to contact new interests or potential needs. Summary of the Invention

[0004] In order to solve the technical problem that the information recommended by existing information recommendation algorithms for users has certain limitations, the purpose of the present invention is to provide an information recommendation method and system based on artificial intelligence, and the specific technical solutions adopted are as follows:

[0005] In the first aspect of the present invention, an information recommendation method based on artificial intelligence is provided, including:

[0006] Obtain the push information for the user within a preset historical time period, and obtain the depth of the user's information cocoon room according to the push information for the user;

[0007] Obtain the satisfaction degree of the user with the push information according to the viewing duration of the user for each push information within the preset historical time period;

[0008] Combine the depth of the information cocoon room and the satisfaction degree to obtain the information recommendation degree of the user for the push information;

[0009] Obtain the difference in the viewing durations of two adjacent views of the push information for the same attribute of the user, and based on the overall situation of the difference, obtain the information acceptance degree of the user for the push information of each attribute;

[0010] Recommend information to the user according to the information recommendation degree and the information acceptance degree.

[0011] In an exemplary embodiment, the information recommendation method based on artificial intelligence further includes:

[0012] Obtain a set of push information attribute vectors corresponding to the push information of the user within a preset historical time period, where the set of push information attribute vectors includes the information attribute vectors of the push information of the user at each sampling moment within the preset historical time period;

[0013] The obtaining of the information cocoon depth of the user according to the push information of the user includes:

[0014] Obtain the similarity of the information attribute vectors at any two adjacent sampling moments, and obtain the similarity less than the preset similarity threshold to obtain the target similarity;

[0015] Take the position between the two sampling moments corresponding to each target similarity as the segmentation position, segment the set of push information attribute vectors, and obtain a plurality of similarity segments;

[0016] Based on each similarity segment, obtain the information cocoon depth of the user.

[0017] In an exemplary embodiment, the obtaining of the information cocoon depth of the user based on each similarity segment includes:

[0018] Obtain the mean value of the similarities included in each similarity segment, and obtain the number of the information attribute vectors in each similarity segment;

[0019] According to the mean value of the similarities, the number of the information attribute vectors, and the number of the similarity segments, obtain the information cocoon depth sub-features of each similarity segment, where the information cocoon depth sub-features are proportional to the mean value of the similarities and the number of the information attribute vectors, and inversely proportional to the number of the similarity segments;

[0020] Obtain the sum value of the information cocoon depth sub-features of each similarity segment and normalize it to obtain the information cocoon depth of the user.

[0021] In an exemplary embodiment, obtaining the satisfaction degree of the user for the push information according to the viewing duration of the user for each push information within the preset historical time period includes:

[0022] Obtain the viewing duration of each push message by the user, and obtain the average viewing duration of all users for the same push message;

[0023] Based on the difference between the viewing duration of each push message by the user and the average viewing duration of the push message, obtain the anti-fooling parameter of the user for the push message;

[0024] According to the anti-fooling parameters of the user for each push message, the viewing duration of the user for each push message, and the average viewing duration, obtain the satisfaction degree of the user for the push message.

[0025] In an exemplary embodiment, the calculation formula of the anti-fooling parameter is as follows:

[0026] ;

[0027] Wherein, represents the anti-fooling parameter of the th user for the th push message, represents the viewing duration of the th user for the th push message; represents the average viewing duration of all users for the th push message; represents the natural constant; represents the pi;

[0028] The calculation formula of the satisfaction degree is as follows:

[0029] ;

[0030] Wherein, represents the satisfaction degree of the th user, represents the number of push messages, represents the normalization function.

[0031] In an exemplary embodiment, combining the information cocoon depth and the satisfaction degree, obtain the information recommendation degree of the user for the push message, including:

[0032] According to the information cocoon depth and the satisfaction degree, obtain the timely adaptability of the user for the push message, and the timely adaptability is inversely proportional to the information cocoon depth and directly proportional to the satisfaction degree;

[0033] According to the timely adaptability, obtain the information recommendation degree, and the information recommendation degree is inversely proportional to the timely adaptability.

[0034] In an exemplary embodiment, the formula for the timely adaptability is as follows:

[0035] ;

[0036] Wherein, represents the timely adaptability of the th user, represents the satisfaction degree of the th user, represents the information cocoon depth of the th user, represents the natural constant;

[0037] The formula for the information recommendation degree is:

[0038] ;

[0039] Wherein, represents the information recommendation degree of the th user.

[0040] In an exemplary embodiment, obtaining the difference in the viewing durations of two adjacent times of the push information of the same attribute for a user, and obtaining the information acceptance degree of the push information of each attribute for the user according to the overall situation of the difference, includes:

[0041] The formula for the information acceptance degree is as follows:

[0042] ;

[0043] ;

[0044] Wherein, represents the information acceptance degree of the th user for the push information of the th attribute, represents the expected parameter, represents the th viewing of the push information of the th attribute by the th user, represents the total number of viewings of the push information of the th attribute by the th user, represents the viewing duration of the th viewing of the push information of the th attribute by the th user, represents the th viewing of the push information of the th attribute by the Viewing duration of the next viewing.

[0045] In an exemplary embodiment, according to the information recommendation degree and the information acceptance degree, information recommendation for a user is performed, including:

[0046] Obtain the attributes of the push information with an information acceptance degree greater than a preset information acceptance degree threshold to obtain target attributes;

[0047] Multiply the information acceptance degree of each target attribute by the information recommendation degree to obtain the distribution weight of the push information of each target attribute;

[0048] Push the push information of each target attribute to the user according to the distribution weight of the push information of each target attribute.

[0049] In a second aspect of the present invention, there is provided an information recommendation system based on artificial intelligence, including: a memory and a processor; the memory is connected to the processor; the memory is used to store program instructions; the processor is used to implement the above-mentioned information recommendation method based on artificial intelligence when the program instructions are executed.

[0050] The present invention has the following beneficial effects: The information recommendation method based on artificial intelligence provided by the present invention analyzes the push information for the user within a preset historical time period, respectively obtains the information cocoon depth of the user and the satisfaction degree with the push information, then comprehensively obtains the information recommendation degree of the user for the push information based on these two aspects of data information, and obtains the information acceptance degree of the user for the push information of each attribute according to the difference in the viewing duration of the adjacent two viewings of the push information of the same attribute by the user. Finally, according to the information recommendation degree and the information acceptance degree, information recommendation for the user is performed, which can recommend more comprehensive data information for the user, eliminate the push limitation, avoid only recommending information highly similar to the user's historical interests, realize the diversity of push of data information, and enable the user to effectively contact new interests or potential needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flowchart of an information recommendation method based on artificial intelligence provided by an embodiment of the present invention;

[0052] Figure 2 is a flowchart for obtaining the information cocoon depth provided by an embodiment of the present invention;

[0053] Figure 3 is a flowchart of steps 1-3 provided by an embodiment of the present invention;

[0054] Figure 4It is a logical relationship diagram between the curve of the depth of the information cocoon provided by an embodiment of the present invention and other related curves;

[0055] Figure 5 It is a flowchart for obtaining the satisfaction degree provided by an embodiment of the present invention;

[0056] Figure 6 It is a logical relationship diagram between the browsing speed of the user for the pushed information and the satisfaction degree provided by an embodiment of the present invention;

[0057] Figure 7 It is a flowchart for obtaining the information recommendation degree provided by an embodiment of the present invention;

[0058] Figure 8 It is a flowchart for recommending information to users provided by an embodiment of the present invention. Detailed implementation manners

[0059] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the accompanying drawings and preferred embodiments to detail the specific implementation manners, structures, features and their effects of the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0061] When users receive information, generally, the information push platform analyzes the browsing behavior of users for the pushed information, uses the similarity of the acceptance behavior of users for the pushed information with different attributes to portrait the users to identify the pushed information that users are interested in, and then uses the information push mechanism to push the information that users are interested in for each user. This kind of push behavior can surely let users continuously receive the information they are interested in, but most of these interested information belongs to information with the same attribute or very high similarity of attributes. When users obtain the pushed information with the same attribute for a long time, they will have "aesthetic fatigue" in information acquisition due to the excessive richness of information with the same attribute, and will also generate an information cocoon due to the inability to have ideological collisions of other attributes. This is an extremely unfavorable phenomenon for the sustainable long-term operation of the platform. Therefore, the present invention proposes an information recommendation method and system based on artificial intelligence, which analyzes the acceptance behavior of users for the pushed information and jointly pushes information of other attributes when the user's impatience degree for the pushed information of the current attribute is relatively high.

[0062] Such asFigure 1 As shown in the figure, an information recommendation method based on artificial intelligence provided by this embodiment includes the following steps:

[0063] Step 1: Obtain the push information for the user within a preset historical time period, and obtain the depth of the user's information cocoon based on the push information for the user.

[0064] The main purpose to be achieved by the present invention is to push information across domains (i.e., attributes) for the user. Its main underlying logic is to analyze the similarity of the push information received by the user and the user's information reception behavior. Therefore, it is necessary to collect the information pushed by the platform to the user and the user's information reception behavior.

[0065] Taking any platform as an example, a user library is constructed. The user library is the scope of the users to be analyzed. The user library includes multiple users, and all of them need to be numbered. And a user behavior database is established. The user behavior database is divided into two parts. The first part is the information log record browsed by the user, and the second part is the log record of the user's browsing information behavior. The two parts in the user behavior database share a timeline.

[0066] Preset a historical time period. The length of the preset historical time period is set according to actual needs. In order to accurately analyze the user, the preset historical time period can be set longer. The preset historical time period includes multiple sampling moments, and the time interval between adjacent sampling moments is set according to actual needs.

[0067] This embodiment analyzes multiple users. Taking any one user as an example below.

[0068] Obtain the push information of the platform to the user within the preset historical time period, specifically: the push information of the platform to the user at each sampling moment within the preset historical time period.

[0069] In an exemplary embodiment, each push message has a corresponding attribute, namely type, such as: push messages with the attribute of sports, push messages with the attribute of automobiles, push messages with the attribute of digital products, and so on. When the platform pushes information to the user at each sampling moment, it also obtains the information attributes of the push messages to the user at each sampling moment in a preset historical time period, and obtains an information attribute vector according to the information attributes of the push message. Vectorizing the information attributes is for facilitating the calculation of the similarity between attributes in the following text. Then, step 1 further includes: obtaining a set of push message attribute vectors corresponding to the push messages to the user within a preset historical time period. The set of push message attribute vectors includes the information attribute vectors of the push messages to the user at each sampling moment in the preset historical time period, and the information attribute vectors in the set of push message attribute vectors are arranged in time sequence. Therefore, each push message to the user at each sampling moment corresponds to an information attribute vector.

[0070] The first part of the user behavior database includes user behavior data in time sequence, that is, within a preset historical time period, the push messages to the user and the information attribute vectors at each sampling moment by the platform.

[0071] Then, according to the push messages to the user, the information cocoon depth of the user is obtained. In an exemplary embodiment, as Figure 2 shown, the process of obtaining the information cocoon depth includes:

[0072] Step 1-1: Obtain the similarity between the information attribute vectors at any two adjacent sampling moments, and obtain the similarities less than a preset similarity threshold to obtain the target similarity.

[0073] Since the information attribute vectors in the set of push message attribute vectors are arranged in time sequence, therefore, obtain the similarity between the information attribute vectors at any two adjacent sampling moments in the set of push message attribute vectors. Among them, the similarity between two vectors can be obtained by using existing similarity calculation methods, such as: cosine similarity, Pearson correlation coefficient, and so on. It should be noted that after calculating the similarity, it needs to be normalized and incorporated into the numerical range of 0-1 for subsequent processing. In other exemplary embodiments, the DTW distance between two vectors can also be calculated, and then negative correlation normalization is performed to obtain the similarity.

[0074] It should be understood that the normalization and negative correlation normalization methods in this embodiment can be specifically set according to the actual situation. For example, normalization can adopt the maximum-minimum normalization method, or the following common method: , represents the processing object, represents the exponential function with the natural constant as the base. Negative correlation normalization can adopt the following common method: .

[0075] Taking the th user as an example, assume that the preset historical time period includes sampling moments. Then, there will be information attribute vectors, and the similarity of the information attribute vectors will be obtained.

[0076] Preset a similarity threshold. The numerical range of the preset similarity threshold is 0 - 1, and the specific value is set according to actual judgment needs, such as 0.8.

[0077] Compare the size of each similarity with the preset similarity threshold, and obtain the similarities that are less than the preset similarity threshold. Define the similarities that are less than the preset similarity threshold as the target similarities.

[0078] Step 1 - 2: Take the position between the two sampling moments corresponding to each target similarity as the segmentation position, and segment the set of push information attribute vectors to obtain multiple similar segments.

[0079] Since each target similarity corresponds to two adjacent sampling moments, then take the position between the two sampling moments corresponding to each target similarity as the segmentation position, and segment the set of push information attribute vectors according to each segmentation position to obtain multiple similar segments. Specifically: the first similar segment is the interval between the first sampling moment of the preset historical time period and the previous sampling moment of the two adjacent sampling moments corresponding to the first target similarity; the second similar segment is the interval between the latter sampling moment of the two adjacent sampling moments corresponding to the first target similarity and the previous sampling moment of the two adjacent sampling moments corresponding to the second target similarity; the third similar segment is the interval between the latter sampling moment of the two adjacent sampling moments corresponding to the second target similarity and the previous sampling moment of the two adjacent sampling moments corresponding to the third target similarity, and so on. The last similar segment is the interval between the latter sampling moment of the two adjacent sampling moments corresponding to the last target similarity and the last sampling moment of the preset historical time period.

[0080] Through the above segmentation method, the differences between the push information of different similar segments are relatively large, while the differences between the push information within the same similar segment are relatively small, and the push information is relatively similar.

[0081] Step 1 - 3: Based on each similar segment, obtain the information cocoon depth of the user.

[0082] In an exemplary embodiment, as Figure 3 shown, the process of obtaining the information cocoon depth of the user includes:

[0083] Step 1-3-1: Obtain the mean of the similarities included in each similar segment, and obtain the number of information attribute vectors in each similar segment.

[0084] It should be understood that each similar segment includes multiple sampling moments, and thus includes multiple similarities. Then, for any similar segment, obtain the mean of the similarities included in that similar segment. At the same time, obtain the number of information attribute vectors in that similar segment, that is, the number of sampling moments included.

[0085] Step 1-3-2: According to the mean of the similarities, the number of information attribute vectors, and the number of similar segments, obtain the sub-feature of the information cocoon depth for each similar segment.

[0086] For any similar segment, according to the mean of the similarities of that similar segment, the number of information attribute vectors of that similar segment, and the number of similar segments, obtain the sub-feature of the information cocoon depth of that similar segment. The sub-feature of the information cocoon depth is proportional to the mean of the similarities and the number of information attribute vectors, and inversely proportional to the number of similar segments.

[0087] Step 1-3-3: Obtain the sum value of the sub-features of the information cocoon depth for each similar segment and normalize it to obtain the information cocoon depth of the user.

[0088] In an exemplary embodiment, the following gives the calculation formula for the information cocoon depth:

[0089] ;

[0090] Among them, represents the th user, represents the information cocoon depth of the th user, represents the th similar segment of the th user, represents the number of similar segments of the th user, represents the th user's th similar segment's mean of similarities, represents the th user's th similar segment's number of information attribute vectors, represents the normalization function.

[0091] represents the th user's sub-feature of the information cocoon depth.

[0092] For the th user, for the platform for the When pushing information to a user, the platform analyzes the similarity of the information pushed to the user and the duration of similar information (i.e., the number of information attribute vectors in the similar segment). The more similar the information pushed by the platform to the user, the longer the duration of the similar information, and the fewer the total number of similar segments, it indicates that the attributes (i.e., types) of the pushed information obtained by the user are more unique. Then, the higher the depth of the information cocoon. Therefore, using the product of the mean similarity in the similar segments with relatively high similarity of the user divided by the length of the similar segment, and then dividing by the total number of similar segments as the information cocoon depth sub-feature of each similar segment, and fusing the information cocoon depth sub-features of all similar segments, the information cocoon depth of the user is obtained.

[0093] As Figure 4 shown, it is a logical relationship diagram between the curve of the information cocoon depth and other related curves. The abscissa is time, and the ordinate is amplitude. Among them, curve B1 represents the curve of the change in the possibility of the user obtaining pushed information of other attributes, curve B2 is the similarity change curve, and curve B3 is the change curve of the user's information cocoon depth. Figure 4 In it, as the similarity of the content pushed by the platform to the user is getting higher and higher, and the pushing time of similar attributes is getting longer and longer, the greater the depth of the information cocoon when the user obtains information on this platform, and the lower the possibility of the user receiving pushed information of other attributes.

[0094] By using the above method, the information cocoon depth of each user is obtained.

[0095] Step 2: Obtain the satisfaction degree of the user with the pushed information according to the viewing duration of each pushed information of the user in the preset historical time period.

[0096] When the platform pushes information to the user, it will use the user's historical behavior habits to conduct user behavior analysis, and then push more interesting information to the user. However, the user's acceptance threshold for pushed information of the same attribute will become higher and higher, resulting in too low accuracy of information pushing. Therefore, in this embodiment, by performing similarity analysis on the user's historical pushed information, it is judged whether the pushed information to the user is too similar and lasts for a long time, and combined with the user's historical viewing behavior of information to obtain whether each user is satisfied with the information pushed by the platform, which is used to describe the user's satisfaction degree with the current pushed information of the platform.

[0097] In an exemplary embodiment, as Figure 5 shown, the process of obtaining the satisfaction degree includes:

[0098] Step 2-1: Obtain the viewing duration of each push message by the user, and obtain the average viewing duration of all users for the same push message.

[0099] After the user obtains each push message from the system, the user will view each push message. Then, obtain the viewing duration of each push message by the user. The viewing duration is specifically the time length obtained by starting to time from when the user opens a certain push message until the user closes the push message. For example: If the push message is a link to a sports news, then start timing from when the user opens the link until the user closes the link, and the time length obtained is the viewing duration of the link. Thus, the viewing durations of the user for each push message within a preset historical time period are obtained.

[0100] The second part in the user behavior database includes the viewing durations of the user for each push message within a preset historical time period.

[0101] Since the system pushes messages to each user in the user library, there will be a situation where the same push message is pushed to multiple users at the same time, and multiple users will view the same push message. Then, obtain the viewing durations of multiple users for the same push message, and then calculate the average value to obtain the average viewing duration of all users for the same push message.

[0102] Step 2-2: Based on the difference between the viewing duration of the user for each push message and the average viewing duration of the push message, obtain the anti-fooling parameter of the user for the push message.

[0103] For any push message, according to the difference between the viewing duration of the user for the push message and the average viewing duration of the push message, obtain the anti-fooling parameter of the user for the push message. The purpose of setting the anti-fooling parameter is to prevent the user from performing non-human mechanical viewing of the push message. The specific behavior can be manifested as the user opening the push message and staying on the page of the push message for a long time, but not actually receiving the information.

[0104] In an exemplary embodiment, the calculation formula of the anti-fooling parameter is as follows:

[0105] ;

[0106] Wherein, represents the anti-fooling parameter of the th user for the th push message, represents the viewing duration of the th user for the th push message; Indicates the average viewing duration of all users for the th push message; Indicates the natural constant; Indicates the pi. The calculation formula of is essentially a variant of the Gaussian function, and the parameter is only

[0107] Step 2-3: According to the anti-fooling parameters of each push message for the user, the viewing duration of the user for each push message, and the average viewing duration, obtain the satisfaction degree of the user for the push message.

[0108] In an exemplary embodiment, the calculation formula of the satisfaction degree is as follows:

[0109] ;

[0110] where, Indicates the satisfaction degree of the th user, Indicates the number of push messages.

[0111] The normalization method for here can be: Obtain the of the th user for all push messages, find the maximum value and the minimum value from them, and then use the maximum-minimum normalization method to normalize the th user's for each push message.

[0112] When the user views the push messages on the platform, the user usually pays more attention to the push messages that are interested, while the user usually pays less attention to the push messages that are not interested. Intuitively, more viewing time is invested in the content that is interested, while there is generally no long viewing time for the content that is not interested. Therefore, this embodiment uses this logic to calculate the satisfaction degree of the user for the push message. The specific calculation logic is: The anti-fooling parameter is used as the weight value of the difference between the viewing duration of the push message and its average viewing duration. The design logic of the anti-fooling parameter is: When the viewing duration of the th push message viewed by the user is less than its average viewing duration by a larger margin, the anti-fooling parameter is larger, that is, the weight value is larger. When the viewing duration of the th push message exceeds the average viewing duration by a larger margin, the anti-fooling parameter is smaller. And, the smaller the average viewing duration, the faster the growth or decrease speed of the anti-fooling parameter, and vice versa.

[0113] Such as Figure 6As shown in the figure, it is a logical relationship diagram between the viewing speed of push information by users and their satisfaction level. The abscissa represents time, and the ordinate represents amplitude. Among them, curve C1 is the viewing speed curve of push information by users, and curve C2 is the satisfaction level curve of push information by users. The faster the viewing speed, the shorter the viewing duration and the lower the satisfaction level.

[0114] By adopting the above process, the satisfaction level of each user is obtained.

[0115] Step 3: Combine the depth of the information cocoon and the satisfaction level to obtain the information recommendation degree of the push information for the user.

[0116] Based on the obtained depth of the information cocoon and satisfaction level of the push information for the user, the information recommendation degree of the push information for the user is obtained, which is used to describe whether the push information from the platform meets the user's needs.

[0117] In an exemplary embodiment, the process of obtaining the information recommendation degree is as Figure 7 shown, including:

[0118] Step 3-1: According to the depth of the information cocoon and the satisfaction level, obtain the timely adaptability of the push information for the user.

[0119] The higher the depth of the information cocoon when the platform pushes information to the user and the lower the satisfaction level of the user with the push information, the worse the adaptability between the user's viewing expectation of the push information and the timely push information from the platform. According to the depth of the information cocoon and the satisfaction level, the timely adaptability of the push information for the user is obtained. The timely adaptability is inversely proportional to the depth of the information cocoon and directly proportional to the satisfaction level.

[0120] In an exemplary embodiment, the calculation formula for the timely adaptability is as follows:

[0121] ;

[0122] Wherein, represents the timely adaptability of the th user, represents the satisfaction level of the th user, represents the depth of the information cocoon of the th user, represents the natural constant.

[0123] Step 3-2: According to the timely adaptability, obtain the information recommendation degree.

[0124] The lower the timeliness adaptability, the more necessary it is to recommend push information of new attributes to users. Conversely, the higher the timeliness adaptability, the less necessary it is to recommend information. Therefore, according to the timeliness adaptability, the information recommendation degree is obtained, and the information recommendation degree is inversely proportional to the timeliness adaptability.

[0125] In an exemplary embodiment, the calculation formula for the information recommendation degree is:

[0126] ;

[0127] where represents the information recommendation degree of the th user.

[0128] Step 4: Obtain the difference in the viewing durations of two adjacent push messages of the same attribute for the user, and based on the overall situation of the difference, obtain the information acceptance degree of the user for the push messages of each attribute.

[0129] For the th user, among the push messages pushed by the system to the th user, some push messages belong to the same attribute. For example, there are multiple push messages that are all sports-related. Then, obtain the viewing durations of each push message of the same attribute for the th user within a preset historical time period, and then calculate the difference in the viewing durations of two adjacent viewings of the push messages of the same attribute for the th user. Then, obtain the overall situation of the viewing duration differences of the push messages of the same attribute for the th user within the preset historical time period, and finally obtain the information acceptance degree of the user for the push messages of each attribute.

[0130] In an exemplary embodiment, the calculation formula for the information acceptance degree is as follows:

[0131] ;

[0132] ;

[0133] where represents the information acceptance degree of the th user for the push messages of the th attribute, represents the expected parameter, represents the th viewing of the push messages of the th attribute by the th user, represents the th viewing of the push messages of the The total number of views of the push information of an attribute, Indicates the th user's th attribute's th view duration of the push information, Indicates the th user's th attribute's th view duration of the push information.

[0134] The difference between the view duration of the last view of the push information of a certain attribute by the user and the view duration of the adjacent previous view represents the expected growth of the user's view expectation for the push information of this attribute compared to the previous view expectation of the user for the push information of this attribute. Then, add up all the expected growths. The greater the total expected growth, the higher the acceptance degree of the user for the push information of this attribute as the time sequence increases, and vice versa. Among them, the purpose of the expected parameter is that when the view expectation of the user for the push information of a certain attribute shows negative growth, the acceptance degree of the user for the push information of this attribute is forced to be 0.

[0135] Using the above method, the information acceptance degree of the user for the push information of each attribute can be obtained.

[0136] Step 5: Recommend information to the user according to the information recommendation degree and the information acceptance degree.

[0137] In an exemplary embodiment, as Figure 8 shown, the specific process of recommending information to the user includes:

[0138] Step 5-1: Obtain the attributes of the push information with an information acceptance degree greater than the preset information acceptance degree threshold to obtain the target attributes.

[0139] Preset an information acceptance degree threshold, which is within the range of 0-1, and the specific value is set according to actual judgment needs.

[0140] Compare the information acceptance degree of the th user for the push information of each attribute with the preset information acceptance degree threshold, obtain the push information with an information acceptance degree greater than the preset information acceptance degree threshold, and define the attributes of the obtained push information with an information acceptance degree greater than the preset information acceptance degree threshold as the target attributes.

[0141] Step 5-2: Multiply the information acceptance degree of each target attribute by the information recommendation degree to obtain the distribution weight of the push information of each target attribute.

[0142] For any target attribute corresponding to the nth user, calculate the product of the information acceptance degree of the target attribute and the information recommendation degree of the mth user. The product corresponding to the target attribute is used as the allocation weight of the push information of the target attribute for the nth user.

[0143] Step 5-3: Push the push information of each target attribute to the user according to the allocation weight of the push information of each target attribute.

[0144] The system pushes the push information of each target attribute to the nth user according to the allocation weight of the push information of each target attribute of the nth user. Specifically: The system uses the allocation weight as the push ratio, and uses the push ratio of the allocation weight of the push information of each target attribute of the nth user to push the push information of each target attribute to the nth user.

[0145] In an exemplary embodiment, the push information of the original attribute can also be continuously pushed to the nth user at the ratio of the timely adaptability of the nth user. It should be understood that this part does not belong to a part of the information recommendation method based on artificial intelligence provided in this embodiment, and is not limited here. nth user.

[0146] Using the above process, information is pushed to each user.

[0147] This embodiment also provides an information recommendation system based on artificial intelligence, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-mentioned information recommendation method embodiment based on artificial intelligence when the program instructions are executed.

[0148] In an exemplary embodiment, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned information recommendation method embodiment based on artificial intelligence are implemented.

[0149] It should be noted that: The above sequence of embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0150] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. An information recommendation method based on artificial intelligence, characterized in that, Including: Obtain the push information to the user within a preset historical time period, and obtain the depth of the user's information cocoon based on the push information to the user; Obtain the satisfaction degree of the user with the push information according to the viewing duration of the user for each push information in the preset historical time period; Combine the depth of the information cocoon and the satisfaction degree to obtain the information recommendation degree of the user for the push information; Obtain the difference in the viewing duration between two adjacent viewings of the push information of the same attribute by the user, and obtain the information acceptance degree of the user for the push information of each attribute according to the overall situation of the difference; Perform information recommendation for the user according to the information recommendation degree and the information acceptance degree; The information recommendation method based on artificial intelligence further includes: Obtain a set of push information attribute vectors corresponding to the push information to the user within a preset historical time period, and the set of push information attribute vectors includes the information attribute vectors of the push information to the user at each sampling moment in the preset historical time period; The obtaining the depth of the user's information cocoon according to the push information to the user includes: Obtain the similarity of the information attribute vectors at any two adjacent sampling moments, and obtain the similarity less than the preset similarity threshold to obtain the target similarity; Take the position between the two sampling moments corresponding to each target similarity as the segmentation position, segment the set of push information attribute vectors, and obtain a plurality of similar segments; Based on each similar segment, obtain the depth of the user's information cocoon; The obtaining the depth of the user's information cocoon based on each similar segment includes: Obtain the mean value of the similarities included in each similar segment, and obtain the number of the information attribute vectors in each similar segment; According to the mean value of the similarities, the number of the information attribute vectors, and the number of the similar segments, obtain the information cocoon depth sub-feature of each similar segment, and the information cocoon depth sub-feature is proportional to the mean value of the similarities and the number of the information attribute vectors, and inversely proportional to the number of the similar segments; Obtain the sum value of the information cocoon depth sub-features of each similar segment and normalize it to obtain the depth of the user's information cocoon.

2. The information recommendation method based on artificial intelligence according to claim 1, characterized in that Obtain the satisfaction degree of the user with the push information according to the viewing duration of the user for each push information in the preset historical time period, including: Obtain the viewing duration of the user for each push information, and obtain the average viewing duration of all users for the same push information; Based on the difference between the viewing duration of the user for each push information and the average viewing duration of the push information, obtain the anti-fooling parameter of the user for the push information; According to the anti-fooling parameters of the user for each push information, the viewing duration of the user for each push information, and the average viewing duration, obtain the satisfaction degree of the user with the push information.

3. The information recommendation method based on artificial intelligence according to claim 2, characterized in that, The calculation formula of the anti-fooling parameter is as follows: ； Among them, represents the anti-fooling parameter of the th user for the th push message; represents the viewing duration of the th user for the th push message; represents the average viewing duration of all users for the th push message; represents the natural constant; represents the pi. The calculation formula of the satisfaction degree is as follows: ； in, Indicates The satisfaction level of each user, Indicates the number of pushed messages. Represents the normalization function.

4. The information recommendation method based on artificial intelligence according to claim 1, characterized in that, Combining the depth of the information cocoon and the satisfaction degree to obtain the information recommendation degree of the user for the push information includes: According to the depth of the information cocoon and the satisfaction degree, obtain the timely adaptability of the user for the push information, and the timely adaptability is inversely proportional to the depth of the information cocoon and directly proportional to the satisfaction degree; According to the timeliness adaptability, the information recommendation degree is obtained, and the information recommendation degree is inversely proportional to the timeliness adaptability.

5. The information recommendation method based on artificial intelligence according to claim 4, characterized in that, The calculation formula of the timeliness adaptability is as follows: ； Among them, represents the timely adaptability of the th user, represents the satisfaction degree of the th user, represents the information cocoon depth of the th user, represents the natural constant; The calculation formula of the information recommendation degree is: ； Among them, represents the degree of information recommendation for the 6. The information recommendation method based on artificial intelligence according to claim 1, characterized in that Obtaining the difference in the viewing durations of the user for the push information of the same attribute in two adjacent times, and obtaining the information acceptance degree of the user for the push information of each attribute according to the overall situation of the difference, including: The calculation formula of the information acceptance degree is as follows: ； ； Among them, represents the information acceptance degree of the th user for the push information of the th attribute, represents the expected parameter, represents the th view of the push information of the th attribute by the th user, represents the total number of views of the push information of the th user for the th attribute, represents the viewing duration of the th view of the push information of the th attribute by the th user, represents the viewing duration of the th view of the push information of the th attribute by the th user.

7. The information recommendation method based on artificial intelligence according to claim 1, characterized in that According to the information recommendation degree and the information acceptance degree, information recommendation is performed on the user, including: Obtaining the attributes of the push information with an information acceptance degree greater than the preset information acceptance degree threshold to obtain target attributes; Multiplying the information acceptance degree of each target attribute by the information recommendation degree to obtain the distribution weight of the push information of each target attribute; Pushing the push information of each target attribute to the user according to the distribution weight of the push information of each target attribute.

8. An information recommendation system based on artificial intelligence, characterized in that, Including: A memory and a processor; The memory is connected to the processor; The memory is used for storing program instructions; The processor is used for implementing the information recommendation method based on artificial intelligence according to any one of claims 1-7 when the program instructions are executed.

Images