Comparison method, device, equipment, storage medium and program product of publisher

Abstract

The present disclosure relates to a publisher comparison method, device, equipment, storage medium and program product. The method includes: obtaining the number of fans of a first publisher at different times and the number of fans of a second publisher at different times; determining a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times; determining a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times; determining the similarity between the first publisher and the second publisher according to a subvector of the first fan growth vector and a subvector of the second fan growth vector.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a publisher's comparison method, apparatus, device, storage medium, and program product. Background Art

[0002] The rise of streaming media social software such as short video APP (Application) has enriched the channels for people to share information. Compared with text and pictures, multimedia objects such as video and audio have stronger expressiveness. For example, video combines auditory information with visual information, has richer content, stronger expressiveness, and better intuitiveness, so it is widely popular on various social media. With the acceleration of the pace of life, short videos, a fragmented way of obtaining information, have gradually been loved by people. More and more people are willing to share their own short videos on short video platforms, and share short videos that they find interesting with others. From watching short videos to actively shooting short videos, users have completed the transformation from consumers to producers. As users shoot more and more high-quality videos and attract more people to watch, the number of their corresponding fans will also show a certain increase. For publishing platforms (such as video platforms or audio platforms), comparing publishers, finding similar publishers, and adopting the same or similar push strategies for similar publishers are of great significance in saving the bandwidth of content distribution networks. Summary of the invention

[0003] The present disclosure provides a comparison technical solution for publishers.

[0004] According to one aspect of the present disclosure, a comparison method of a publisher is provided, comprising:

[0005] Get the number of followers of the first publisher at different times and the number of followers of the second publisher at different times;

[0006] Determining a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times;

[0007] Determining a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times;

[0008] The similarity between the first publisher and the second publisher is determined according to the subvector of the first follower growth vector and the subvector of the second follower growth vector.

[0009] By obtaining the number of fans of the first publisher and the number of fans of the second publisher at different times, determining the first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times, determining the second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times, and determining the similarity between the first publisher and the second publisher according to the subvector of the first fan growth vector and the subvector of the second fan growth vector, similar publishers can be accurately discovered, so that the same or similar push strategies can be adopted for the content published by similar publishers, which in turn helps the publishing platform to distribute the content published by the publishers more effectively, thereby helping to save the bandwidth of the content distribution network.

[0010] In one possible implementation,

[0011] The determining, according to the number of fans of the first publisher at different times, a first fan growth vector corresponding to the first publisher includes: determining, according to the number of fans of the first publisher at different times and a plurality of preset fan number intervals, the first fan growth vector corresponding to the first publisher, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element;

[0012] Determining the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times includes: determining the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times and the preset multiple fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector represents the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element.

[0013] In this implementation, the first fan growth vector corresponding to the first publisher is determined based on the number of fans of the first publisher at different times and multiple preset fan number intervals, and the second fan growth vector corresponding to the second publisher is determined based on the number of fans of the second publisher at different times and multiple preset fan number intervals, wherein any element in the first fan growth vector represents the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element, and any element in the second fan growth vector represents the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element, and the first fan growth vector and the second fan growth vector determined in this way can accurately reflect the characteristics of the fan growth of the first publisher and the second publisher. Based on the first fan growth vector and the second fan growth vector determined in this way, the accuracy of determining the similarity between the first publisher and the second publisher can be improved.

[0014] In a possible implementation, determining the similarity between the first publisher and the second publisher according to the subvector of the first follower growth vector and the subvector of the second follower growth vector includes:

[0015] The similarity between the first publisher and the second publisher is determined according to the continuous subvector of the first follower growth vector and the continuous subvector of the second follower growth vector.

[0016] In this implementation, the similarity between the first publisher and the second publisher is determined based on the continuous subvector of the first follower growth vector and the continuous subvector of the second follower growth vector, thereby improving the accuracy of the determined similarity between the first publisher and the second publisher.

[0017] In a possible implementation, determining the similarity between the first publisher and the second publisher according to the subvector of the first follower growth vector and the subvector of the second follower growth vector includes:

[0018] The similarity between the first publisher and the second publisher is determined according to subvectors of the same length in the first follower growth vector and the second follower growth vector.

[0019] In this implementation, the similarity between the first publisher and the second publisher is determined based on subvectors of the same length in the first and second fan growth vectors, thereby improving the accuracy of the determined similarity between the first publisher and the second publisher.

[0020] In a possible implementation, determining the similarity between the first publisher and the second publisher according to subvectors of the same length in the first follower growth vector and the second follower growth vector includes:

[0021] Determine a plurality of sub-vector pairs in the first powder growth vector and the second powder growth vector according to the sub-vectors of the same length in the first powder growth vector and the second powder growth vector, wherein any sub-vector pair in the plurality of sub-vector pairs includes the sub-vectors of the same length in the first powder growth vector and the second powder growth vector;

[0022] For any sub-vector pair among the plurality of sub-vector pairs, determining the similarity of the sub-vector pair according to a difference vector between two sub-vectors in the sub-vector pair;

[0023] The similarity between the first publisher and the second publisher is determined according to the similarities of the plurality of sub-vector pairs.

[0024] In this implementation, multiple sub-vector pairs in the first fan growth vector and the second fan growth vector are determined based on sub-vectors of the same length in the first fan growth vector and the second fan growth vector, wherein any sub-vector pair in the multiple sub-vector pairs includes sub-vectors of the same length in the first fan growth vector and the second fan growth vector, and for any sub-vector pair in the multiple sub-vector pairs, the similarity of the sub-vector pair is determined based on the difference vector between two sub-vectors in the sub-vector pair, and the similarity between the first publisher and the second publisher is determined based on the similarities of the multiple sub-vector pairs, thereby being able to more accurately determine the similarity between the first publisher and the second publisher based on the difference information between the sub-vectors of the same length in the first fan growth vector and the second fan growth vector.

[0025] In a possible implementation manner, determining the similarity of the subvector pair according to a difference vector between two subvectors in the subvector pair includes:

[0026] Normalizing a difference vector between two sub-vectors in the sub-vector pair to obtain a normalized difference vector corresponding to the sub-vector pair;

[0027] The similarity of the sub-vector pair is determined according to the normalized difference vector corresponding to the sub-vector pair.

[0028] In this implementation, the difference vector between two sub-vectors in the sub-vector pair is normalized to obtain the normalized difference vector corresponding to the sub-vector pair, and the similarity of the sub-vector pair is determined based on the normalized difference vector corresponding to the sub-vector pair. This can help find publishers whose absolute values ​​of elements in the fan growth vector are not similar but whose fan growth trends are similar.

[0029] In a possible implementation manner, normalizing the difference vector between two sub-vectors in the sub-vector pair to obtain a normalized difference vector corresponding to the sub-vector pair includes:

[0030] For a difference vector between two sub-vectors in the sub-vector pair, subtract the minimum element of the difference vector from the elements in the difference vector to obtain a translated difference vector corresponding to the sub-vector pair;

[0031] Based on the target element, the elements in the translated difference vector corresponding to the sub-vector pair are normalized to obtain a normalized difference vector corresponding to the sub-vector pair.

[0032] In this implementation, the difference vector between two sub-vectors in the sub-vector pair is obtained by subtracting the minimum element of the difference vector from the elements in the difference vector to obtain the translated difference vector corresponding to the sub-vector pair, and based on the target element, the elements in the translated difference vector corresponding to the sub-vector pair are normalized to obtain the normalized difference vector corresponding to the sub-vector pair, and based on the normalized difference vector corresponding to the sub-vector pair determined in this way, the similarity between the two sub-vectors in the sub-vector pair can be more accurately determined, thereby more accurately determining the similarity between publishers.

[0033] In a possible implementation manner, the maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element.

[0034] In this implementation, the maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element, thereby normalizing the multiple sub-vector pairs using the same benchmark, and based on the normalized difference vectors corresponding to the sub-vector pairs determined in this way, the similarity between two sub-vectors in the sub-vector pair can be more accurately determined, thereby enabling the similarity between publishers to be more accurately determined.

[0035] In a possible implementation, the similarity of the sub-vector pair is negatively correlated with the sum of elements of the normalized difference vector corresponding to the sub-vector pair.

[0036] According to this implementation, the similarity between two sub-vectors in a sub-vector pair can be determined more accurately.

[0037] In one possible implementation, the similarity of the sub-vector pair is negatively correlated with a first ratio, wherein the first ratio is the ratio between a first sum value and a second sum value, the first sum value is the sum of the elements of the normalized difference vectors corresponding to the sub-vector pair, and the second sum value is the maximum value of the sum of the elements of the normalized difference vectors corresponding to the multiple sub-vector pairs.

[0038] According to this implementation, the accuracy of the similarity of the determined sub-vector pairs can be further improved, that is, the similarity of the sub-vector pairs determined according to this example can more accurately reflect the similarity of the fan growth trends of the first fan growth vector and the second fan growth vector.

[0039] In a possible implementation manner, the similarity of the sub-vector pair is positively correlated with the length of the sub-vector in the sub-vector pair.

[0040] The similarity of the sub-vector pair determined according to this implementation method can more accurately reflect the similarity of the follower growth trends of the first follower growth vector and the second follower growth vector.

[0041] In a possible implementation, the similarity of the sub-vector pair is positively correlated with a second ratio, wherein the second ratio is a ratio between a first length and a second length, the first length is the length of a sub-vector in the sub-vector pair, and the second length is the maximum length of a sub-vector in the multiple sub-vector pairs.

[0042] According to this implementation, the accuracy of the similarity of the determined sub-vector pairs can be further improved, that is, the similarity of the sub-vector pairs determined according to this example can more accurately reflect the similarity of the fan growth trends of the first fan growth vector and the second fan growth vector.

[0043] In a possible implementation, determining the similarity between the first publisher and the second publisher according to the similarities of the plurality of sub-vector pairs includes:

[0044] The maximum similarity among the similarities of the plurality of sub-vector pairs is determined as the similarity between the first publisher and the second publisher.

[0045] In this implementation, the maximum similarity among the similarities of the plurality of sub-vector pairs is determined as the similarity between the first publisher and the second publisher, thereby facilitating the discovery of publishers with similar trends in increasing followers.

[0046] According to one aspect of the present disclosure, a comparison device of a publisher is provided, comprising:

[0047] An acquisition module, used to acquire the number of fans of the first publisher at different times and the number of fans of the second publisher at different times;

[0048] A first determination module, configured to determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times;

[0049] A second determination module, configured to determine a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times;

[0050] The third determination module is used to determine the similarity between the first publisher and the second publisher according to the subvector of the first follower growth vector and the subvector of the second follower growth vector.

[0051] In one possible implementation,

[0052] The first determination module is used to determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times and a plurality of preset fan number intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element;

[0053] The second determination module is used to determine the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times and the preset multiple fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector represents the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element.

[0054] In a possible implementation manner, the third determining module is used to:

[0055] The similarity between the first publisher and the second publisher is determined according to the continuous subvector of the first follower growth vector and the continuous subvector of the second follower growth vector.

[0056] In a possible implementation manner, the third determining module is used to:

[0057] The similarity between the first publisher and the second publisher is determined according to subvectors of the same length in the first follower growth vector and the second follower growth vector.

[0058] In a possible implementation manner, the third determining module is used to:

[0059] Determine a plurality of sub-vector pairs in the first powder growth vector and the second powder growth vector according to the sub-vectors of the same length in the first powder growth vector and the second powder growth vector, wherein any sub-vector pair in the plurality of sub-vector pairs includes the sub-vectors of the same length in the first powder growth vector and the second powder growth vector;

[0060] For any sub-vector pair among the plurality of sub-vector pairs, determining the similarity of the sub-vector pair according to a difference vector between two sub-vectors in the sub-vector pair;

[0061] The similarity between the first publisher and the second publisher is determined according to the similarities of the plurality of sub-vector pairs.

[0062] In a possible implementation manner, the third determining module is used to:

[0063] Normalizing a difference vector between two sub-vectors in the sub-vector pair to obtain a normalized difference vector corresponding to the sub-vector pair;

[0064] The similarity of the sub-vector pair is determined according to the normalized difference vector corresponding to the sub-vector pair.

[0065] In a possible implementation manner, the third determining module is used to:

[0066] For a difference vector between two sub-vectors in the sub-vector pair, subtract the minimum element of the difference vector from the elements in the difference vector to obtain a translated difference vector corresponding to the sub-vector pair;

[0067] Based on the target element, the elements in the translated difference vector corresponding to the sub-vector pair are normalized to obtain a normalized difference vector corresponding to the sub-vector pair.

[0068] In a possible implementation manner, the maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element.

[0069] In a possible implementation, the similarity of the sub-vector pair is negatively correlated with the sum of elements of the normalized difference vector corresponding to the sub-vector pair.

[0070] In one possible implementation, the similarity of the sub-vector pair is negatively correlated with a first ratio, wherein the first ratio is the ratio between a first sum value and a second sum value, the first sum value is the sum of the elements of the normalized difference vectors corresponding to the sub-vector pair, and the second sum value is the maximum value of the sum of the elements of the normalized difference vectors corresponding to the multiple sub-vector pairs.

[0071] In a possible implementation manner, the similarity of the sub-vector pair is positively correlated with the length of the sub-vector in the sub-vector pair.

[0072] In a possible implementation, the similarity of the sub-vector pair is positively correlated with a second ratio, wherein the second ratio is a ratio between a first length and a second length, the first length is the length of a sub-vector in the sub-vector pair, and the second length is the maximum length of a sub-vector in the multiple sub-vector pairs.

[0073] In a possible implementation manner, the third determining module is used to:

[0074] The maximum similarity among the similarities of the plurality of sub-vector pairs is determined as the similarity between the first publisher and the second publisher.

[0075] According to one aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; a memory for storing executable instructions; wherein the one or more processors are configured to call the executable instructions stored in the memory to execute the above method.

[0076] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor.

[0077] According to one aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in an electronic device, a processor in the electronic device executes the above method.

[0078] In the embodiments of the present disclosure, by obtaining the number of fans of the first publisher and the number of fans of the second publisher at different times, a first fan growth vector corresponding to the first publisher is determined according to the number of fans of the first publisher at different times, and a second fan growth vector corresponding to the second publisher is determined according to the number of fans of the second publisher at different times, and the similarity between the first publisher and the second publisher is determined according to the sub-vector of the first fan growth vector and the sub-vector of the second fan growth vector, thereby accurately discovering similar publishers, and thus being able to adopt the same or similar push strategies for the content published by similar publishers, which in turn helps the publishing platform to more effectively distribute the content published by the publishers, thereby helping to save the bandwidth of the content distribution network.

[0079] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0080] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0082] Figure 1 A flow chart of a publisher's comparison method provided by an embodiment of the present disclosure is shown.

[0083] Figure 2a A schematic diagram showing a follower growth age curve corresponding to the first publisher in the publisher comparison method provided in an embodiment of the present disclosure.

[0084] Figure 2bA schematic diagram showing a follower growth age curve corresponding to the second publisher in the publisher comparison method provided in an embodiment of the present disclosure.

[0085] Figure 3 A schematic diagram showing a comparison matrix between a first fan growth vector and a second fan growth vector in a comparison method for a publisher provided by an embodiment of the present disclosure.

[0086] Figure 4 A schematic diagram showing a comparison matrix after translation processing in the comparison method of the publisher provided in an embodiment of the present disclosure.

[0087] Figure 5 A schematic diagram showing a normalized comparison matrix in the publisher's comparison method provided by an embodiment of the present disclosure.

[0088] Figure 6a A schematic diagram showing a follower growth age curve corresponding to a target publisher in the publisher comparison method provided in an embodiment of the present disclosure.

[0089] Figure 6b A schematic diagram showing a follower growth day age curve corresponding to the most similar publisher of a target publisher in the publisher comparison method provided by an embodiment of the present disclosure.

[0090] Figure 6c A schematic diagram showing a follower growth day age curve corresponding to similar publishers of a target publisher in the publisher comparison method provided by an embodiment of the present disclosure.

[0091] Figure 6d A schematic diagram showing the follower growth day age curve corresponding to non-similar publishers of the target publisher in the publisher comparison method provided by an embodiment of the present disclosure.

[0092] Figure 7 A schematic diagram showing a fan growth curve corresponding to a publisher in the publisher comparison method provided in an embodiment of the present disclosure.

[0093] Figure 8 A block diagram of a comparison device of a publisher provided by an embodiment of the present disclosure is shown.

[0094] Fig. 9 A block diagram of an electronic device 1900 provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0095] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0096] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0097] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0098] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0099] The embodiments of the present disclosure provide a publisher comparison method, device, electronic device, storage medium and program product, which obtain the number of fans of a first publisher and the number of fans of a second publisher at different times, determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times, determine a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times, and determine the similarity between the first publisher and the second publisher according to a subvector of the first fan growth vector and a subvector of the second fan growth vector, thereby accurately discovering similar publishers, so that the same or similar push strategies can be adopted for the content published by similar publishers, which in turn helps the publishing platform to distribute the content published by the publishers more effectively, thereby helping to save the bandwidth of the content distribution network.

[0100] The publisher comparison method provided by the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0101] Figure 1A flow chart of the comparison method of the publisher provided by the embodiment of the present disclosure is shown. In one possible implementation, the execution subject of the comparison method of the publisher may be the comparison device of the publisher, for example, the comparison method of the publisher may be executed by a terminal device or a server or other electronic device. The terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device or a wearable device, etc. In some possible implementations, the comparison method of the publisher may be implemented by a processor calling computer-readable instructions stored in a memory. For example Figure 1 As shown, the publisher's comparison method includes steps S11 to S14.

[0102] In step S11, the number of fans of the first publisher at different times and the number of fans of the second publisher at different times are obtained.

[0103] In step S12, a first fan growth vector corresponding to the first publisher is determined according to the number of fans of the first publisher at different times.

[0104] In step S13, a second fan growth vector corresponding to the second publisher is determined according to the number of fans of the second publisher at different times.

[0105] In step S14, the similarity between the first publisher and the second publisher is determined based on the subvector of the first follower growth vector and the subvector of the second follower growth vector.

[0106] In the disclosed embodiment, the publisher may represent a person, organization or robot that publishes content. The content published by the publisher may be a short video, video, audio, photo or article, etc., which is not limited here. In some application scenarios, the publisher may also be called an author, creator, blogger, uploader, up master or anchor, etc. In the disclosed embodiment, the first publisher and the second publisher are two different publishers.

[0107] In the disclosed embodiment, fans may represent people who follow or subscribe to a publisher. In some application scenarios, fans may also be referred to as subscribers, followers, followers, or followers, etc.

[0108] In an embodiment of the present disclosure, the number of fans of the first publisher at different times after registering an account can be obtained, and the number of fans of the second publisher at different times after registering an account can be obtained; or, the number of fans of the first publisher at different times after publishing a first item of content can be obtained, and the number of fans of the second publisher at different times after publishing the first item of content can be obtained; and so on.

[0109] For example, you can obtain the number of fans of the first publisher every day after registering an account, and obtain the number of fans of the second publisher every day after registering an account; for another example, you can obtain the number of fans of the first publisher every week after registering an account, and obtain the number of fans of the second publisher every week after registering an account; for another example, you can obtain the number of fans of the first publisher every hour after registering an account, and obtain the number of fans of the second publisher every hour after registering an account; and so on.

[0110] For another example, you can obtain the number of fans of the first publisher every day after the first content is released, and obtain the number of fans of the second publisher every day after the first content is released; for another example, you can obtain the number of fans of the first publisher every week after the first content is released, and obtain the number of fans of the second publisher every week after the first content is released; for another example, you can obtain the number of fans of the first publisher every hour after the first content is released, and obtain the number of fans of the second publisher every hour after the first content is released; and so on.

[0111] In the embodiment of the present disclosure, the first fan growth vector corresponding to the first publisher can be determined according to the number of fans of the first publisher at different times. For example, the first fan growth vector corresponding to the first publisher can be determined according to the number of fans of the first publisher every day after registering the account. The first fan growth vector can represent the fan growth vector corresponding to the first publisher. The first fan growth vector can reflect the change information of the number of fans of the first publisher.

[0112] According to the number of fans of the second publisher at different times, the second fan growth vector corresponding to the second publisher can be determined. For example, the second fan growth vector corresponding to the second publisher can be determined according to the number of fans of the second publisher every day after registering the account. The second fan growth vector can represent the fan growth vector corresponding to the second publisher. The second fan growth vector can reflect the change information of the number of fans of the second publisher.

[0113] The first fan growth vector includes at least one element, and the second fan growth vector includes at least one element. The lengths of the first fan growth vector and the second fan growth vector may be the same or different.

[0114] The embodiment of the present disclosure does not limit the execution order of step S12 and step S13, as long as step S12 and step S13 are executed after step S11 and before step S14 respectively. For example, the comparison method of the publisher provided by the embodiment of the present disclosure can be executed in the order of step S11-step S12-step S13-step S14. For another example, the comparison method of the publisher provided by the embodiment of the present disclosure can be executed in the order of step S11-step S13-step S12-step S14. For another example, step S12 and step S13 can be executed simultaneously.

[0115] In a possible implementation, determining the first fan growth vector corresponding to the first publisher based on the number of fans of the first publisher at different times includes: determining the first fan growth vector corresponding to the first publisher based on the number of fans of the first publisher at different times and a plurality of preset fan number intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element; determining the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times includes: determining the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times and the plurality of preset fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector indicates the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element.

[0116] In this implementation, the lengths of each fan number interval in the preset multiple fan number intervals can be the same or different. For example, the number of preset fan number intervals is 101, and these 101 fan number intervals are [0,1w), [1w,2w),…, [99w,100w), [100w,+∞). For another example, the number of preset fan number intervals is 4, and these 4 fan number intervals are [0,1w), [1w,10w), [10w,100w), [100w,+∞). Wherein, w represents ten thousand. For example, 1w represents 10000, and 100w represents 1000000. In this implementation, the first fan increase vector and the second fan increase vector can be one-dimensional vectors respectively. In this implementation, the first fan increase vector and the second fan increase vector can also be called fan number transition vectors.

[0117] In one example, the preset multiple intervals of the number of fans include [0, 1w), [1w, 2w), ..., [99w, 100w), [100w, +∞). According to the preset multiple intervals of the number of fans and the number of fans of the first publisher every day after registering the account, the first fan growth vector corresponding to the first publisher can be determined. For example, the length of time that the number of fans of the first publisher stays in the fan number interval [0,1w) is 5 days (that is, the length of time it takes for the number of fans of the first publisher to increase from 0 to 9999 is 5 days), the length of time that the number of fans of the first publisher stays in the fan number interval [1w,2w) is 0 day, the length of time that the number of fans of the first publisher stays in the fan number interval [2w,3w) is 2 days, the length of time that the number of fans of the first publisher stays in the fan number interval [3w,4w) is 1 day, the length of time that the number of fans of the first publisher stays in the fan number interval [4w,5w) is 1 day, the length of time that the number of fans of the first publisher stays in the fan number interval [5w,6w) is 0 day, the length of time that the number of fans of the first publisher stays in the fan number interval [6w,7w) is 2 days, and the current number of fans of the first publisher has not yet reached 7w, then it can be determined that the first fan increase vector corresponding to the first publisher is [5,0,2,1,1,0,2]. According to the preset multiple fan number intervals and the number of fans of the second publisher every day after registering the account, the second fan growth vector corresponding to the second publisher can be determined. For example, the number of fans of the second publisher stays in the fan number interval [0,1w) for 7 days (that is, the time it takes for the number of fans of the second publisher to increase from 0 to 9999 is 7 days), the number of fans of the second publisher stays in the fan number interval [1w,2w) for 0 days, the number of fans of the second publisher stays in the fan number interval [2w,3w) for 6 days, the number of fans of the second publisher stays in the fan number interval [3w,4w) for 3 days, the number of fans of the second publisher stays in the fan number interval [4w,5w) for 3 days, and the number of fans of the second publisher has not yet reached 5w, then the second fan growth vector corresponding to the second publisher can be determined to be [7,0,6,3,3].

[0118] In another example, the preset multiple fan number intervals include [0, 1w), [1w, 10w), [10w, 100w),

[0119] [100w,+∞). According to the preset multiple fan number intervals and the number of fans of the first publisher every day after registering the account, the first fan growth vector corresponding to the first publisher can be determined. For example, the length of time that the number of fans of the first publisher stays in the fan number interval [0,1w) is 1000 days, the length of time that the number of fans of the first publisher stays in the fan number interval [1w,10w) is 10 days, and the length of time that the number of fans of the first publisher stays in the fan number interval [10w,100w) is 20 days, then the first fan growth vector corresponding to the first publisher can be determined to be [1000,10,20]. According to the preset multiple fan number intervals and the number of fans of the second publisher every day after registering the account, the second fan growth vector corresponding to the second publisher can be determined. For example, the number of fans of the second publisher stays in the fan number range [0, 1w) for 2000 days, the number of fans of the second publisher stays in the fan number range [1w, 10w) for 20 days, and the number of fans of the second publisher stays in the fan number range [10w, 100w) for 40 days. It can be determined that the second fan growth vector corresponding to the second publisher is [2000, 20, 40].

[0120] In this implementation, the first fan growth vector corresponding to the first publisher is determined based on the number of fans of the first publisher at different times and multiple preset fan number intervals, and the second fan growth vector corresponding to the second publisher is determined based on the number of fans of the second publisher at different times and multiple preset fan number intervals, wherein any element in the first fan growth vector represents the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element, and any element in the second fan growth vector represents the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element, and the first fan growth vector and the second fan growth vector determined in this way can accurately reflect the characteristics of the fan growth of the first publisher and the second publisher. Based on the first fan growth vector and the second fan growth vector determined in this way, the accuracy of determining the similarity between the first publisher and the second publisher can be improved.

[0121] In another possible implementation, determining the first fan growth vector corresponding to the first publisher based on the number of fans of the first publisher at different times includes: determining the first fan growth vector corresponding to the first publisher based on the number of fans of the first publisher at different times and a plurality of preset time intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector represents an increase in the number of fans of the first publisher in the time interval corresponding to the element; determining the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times includes: determining the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times and the plurality of preset time intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector represents an increase in the number of fans of the second publisher in the time interval corresponding to the element.

[0122] In the embodiment of the present disclosure, after determining the first follower growth vector corresponding to the first publisher and the second follower growth vector corresponding to the second publisher, the similarity between the first publisher and the second publisher can be determined based on the similarity between the subvector of the first follower growth vector and the subvector of the second follower growth vector. The length of the subvector of the first follower growth vector is less than or equal to the length of the first follower growth vector, and the length of the subvector of the first follower growth vector is greater than or equal to 1; the length of the subvector of the second follower growth vector is less than or equal to the length of the second follower growth vector, and the length of the subvector of the second follower growth vector is greater than or equal to 1. In a possible implementation, the similarity between the first publisher and the second publisher can be determined based on the subvector of the first follower growth vector whose length is greater than or equal to 2, and the subvector of the second follower growth vector whose length is greater than or equal to 2.

[0123] In the embodiments of the present disclosure, for any vector, if all elements in the vector are elements in the first fan-increasing vector, and when the number of elements in the vector is greater than or equal to 2, the order of the elements in the vector is the same as that of the first fan-increasing vector, then the vector is a sub-vector of the first fan-increasing vector. For example, if the first fan-increasing vector is [5,0,2,1,1,0,2], then the sub-vectors of the first fan-increasing vector include [5,0,2], [2,1,1,0], [0,1,0], [5,0,2,1,1,0,2], and so on. Suppose a vector is [2,0,5]. Although the elements in [2,0,5] are all elements in the first fan-increasing vector, the order of the elements in [2,0,5] is different from that of the first fan-increasing vector. Therefore, [2,0,5] is not a sub-vector of the first fan-increasing vector.

[0124] For any vector, if all elements in the vector are elements in the second fan growth vector, and the number of elements in the vector is greater than or equal to 2, and the order of elements in the vector is the same as that of the second fan growth vector, then the vector is a subvector of the second fan growth vector.

[0125] In a possible implementation, determining the similarity between the first publisher and the second publisher based on a sub-vector of the first follower growth vector and a sub-vector of the second follower growth vector includes: determining the similarity between the first publisher and the second publisher based on a continuous sub-vector of the first follower growth vector and a continuous sub-vector of the second follower growth vector.

[0126] In this implementation, for any subvector of the first fan growth vector, if the adjacent elements in the subvector are also adjacent in the first fan growth vector, then the subvector is a continuous subvector of the first fan growth vector; if any two adjacent elements in the subvector are not adjacent in the first fan growth vector, then the subvector is a non-continuous subvector of the first fan growth vector. For example, if the first fan growth vector is [5,0,2,1,1,0,2], then the continuous subvectors of the first fan growth vector include [5,0,2], [2,1,1,0], [5,0,2,1,1,0,2], etc., and the non-continuous subvectors of the first fan growth vector include [0,1,0], [5,2,1,1,0,2], etc.

[0127] For any subvector of the second powder growth vector, if the adjacent elements in the subvector are also adjacent in the second powder growth vector, then the subvector is a continuous subvector of the second powder growth vector; if any two adjacent elements in the subvector are not adjacent in the second powder growth vector, then the subvector is a non-continuous subvector of the second powder growth vector.

[0128] In this implementation, the similarity between the first publisher and the second publisher is determined based on the continuous subvector of the first follower growth vector and the continuous subvector of the second follower growth vector, thereby improving the accuracy of the determined similarity between the first publisher and the second publisher.

[0129] In another possible implementation manner, the similarity between the first publisher and the second publisher may be determined according to a non-continuous sub-vector of the first follower growth vector and a non-continuous sub-vector of the second follower growth vector.

[0130] In a possible implementation, the determining the similarity between the first publisher and the second publisher based on a subvector of the first follower growth vector and a subvector of the second follower growth vector includes: determining the similarity between the first publisher and the second publisher based on subvectors of the same length in the first follower growth vector and the second follower growth vector. In this implementation, by determining the similarity between the first publisher and the second publisher based on subvectors of the same length in the first follower growth vector and the second follower growth vector, the accuracy of the determined similarity between the first publisher and the second publisher can be improved.

[0131] As an example of this implementation method, determining the similarity between the first publisher and the second publisher based on sub-vectors of the same length in the first follower growth vector and the second follower growth vector includes: determining the similarity between the first publisher and the second publisher based on continuous sub-vectors of the same length in the first follower growth vector and the second follower growth vector.

[0132] In another possible implementation manner, the similarity between the first publisher and the second publisher may be determined based on sub-vectors of different lengths in the first follower growth vector and the second follower growth vector.

[0133] In a possible implementation, the determining the similarity between the first publisher and the second publisher based on the subvectors of the same length in the first and second fan-increasing vectors includes: determining a plurality of subvector pairs in the first and second fan-increasing vectors based on the subvectors of the same length in the first and second fan-increasing vectors, wherein any subvector pair in the plurality of subvector pairs includes subvectors of the same length in the first and second fan-increasing vectors; for any subvector pair in the plurality of subvector pairs, determining the similarity of the subvector pair based on the difference vector between two subvectors in the subvector pair; and determining the similarity between the first publisher and the second publisher based on the similarity of the plurality of subvector pairs. In this implementation, any subvector pair in the plurality of subvector pairs includes two subvectors, the two subvectors include a subvector of the first and second fan-increasing vectors and a subvector of the second fan-increasing vector, and the two subvectors have the same length. For any subvector pair in the plurality of subvector pairs, the similarity of the subvector pair can be determined based on the difference vector between two subvectors in the subvector pair. The similarity of any sub-vector pair may represent the similarity between the two sub-vectors in the sub-vector pair.

[0134] In this implementation, multiple sub-vector pairs in the first fan growth vector and the second fan growth vector are determined based on sub-vectors of the same length in the first fan growth vector and the second fan growth vector, wherein any sub-vector pair in the multiple sub-vector pairs includes sub-vectors of the same length in the first fan growth vector and the second fan growth vector, and for any sub-vector pair in the multiple sub-vector pairs, the similarity of the sub-vector pair is determined based on the difference vector between two sub-vectors in the sub-vector pair, and the similarity between the first publisher and the second publisher is determined based on the similarities of the multiple sub-vector pairs, thereby being able to more accurately determine the similarity between the first publisher and the second publisher based on the difference information between the sub-vectors of the same length in the first fan growth vector and the second fan growth vector.

[0135] As an example of this implementation, for any sub-vector pair among the multiple sub-vector pairs, when the length of the sub-vector in the sub-vector pair is less than the maximum sub-vector length, the two sub-vectors in the sub-vector pair respectively contain edge elements of the corresponding fan growth vector. The maximum sub-vector length is the smaller value of the length of the first fan growth vector and the length of the second fan growth vector. For example, the length of the first fan growth vector is 7, and the length of the second fan growth vector is 5, then the maximum sub-vector length is 5. The edge elements of any fan growth vector include the first element and the last element of the fan growth vector. For example, the first fan growth vector is [5,0,2,1,1,0,2], then the edge elements of the first fan growth vector include 5 and 2. For another example, the second fan growth vector is [7,0,6,3,3], then the edge elements of the second fan growth vector include 7 and 3.

[0136] For example, the first fan growth vector is [5,0,2,1,1,0,2], and the second fan growth vector is [7,0,6,3,3], then the following 9 sub-vector pairs can be determined: {[5,0],[3,3]}, {[5,0,2],[6,3,3]}, {[5,0,2,1],[0,6,3,3]}, {[5,0,2,1,1],[7,0,6,3,3]}, {[0,2,1,1,0],[7,0,6,3,3]}, {[2,1,1,0,2],[7,0,6,3,3]}, {[1,1,0,2],[7,0,6,3]}, {[1,0,2],[7,0,6]}, {[0,2],[7,0]}.

[0137] In this example, the length of the first fan growth vector is 7, and the length of the second fan growth vector is 5. Therefore, the maximum sub-vector length in the sub-vector pair of the first fan growth vector and the second fan growth vector is 5. Among them, the length of the subvectors in the pairs {[5,0,2,1,1],[7,0,6,3,3]}, {[0,2,1,1,0],[7,0,6,3,3]}, and {[2,1,1,0,2],[7,0,6,3,3]} is equal to 5; the length of the subvectors in the pairs {[5,0],[3,3]}, {[5,0,2],[6,3,3]}, {[5,0,2,1],[0,6,3,3]}, {[1,1,0,2],[7,0,6,3]}, {[1,0,2],[7,0,6]}, and {[0,2],[7,0]} is less than 5. In the sub-vector pairs {[5,0],[3,3]}, {[5,0,2],[6,3,3]}, {[5,0,2,1],[0,6,3,3]}, {[1,1,0,2],[7,0,6,3]}, {[1,0,2],[7,0,6]}, and {[0,2],[7,0]}, the two sub-vectors in each sub-vector pair contain the edge elements of the corresponding powder growth vector. For example, in the sub-vector pair {[5,0],[3,3]}, [5,0] contains the edge element 5 of the first fan growth vector, and [3,3] contains the edge element 3 of the second fan growth vector; in the sub-vector pair {[5,0,2],[6,3,3]}, [5,0,2] contains the edge element 5 of the first fan growth vector, and [6,3,3] contains the edge element 3 of the second fan growth vector; in the sub-vector pair {[5,0,2,1],[0,6,3,3]}, [5,0,2,1] contains the edge element 5 of the first fan growth vector, and [0,6,3,3] contains the edge element 3 of the second fan growth vector The edge element 3 of the quantity; [1,1,0,2] in {[1,1,0,2],[7,0,6,3]} contains the edge element 2 of the first fan growth vector, and [7,0,6,3] contains the edge element 7 of the second fan growth vector; [1,0,2] in {[1,0,2],[7,0,6]} contains the edge element 2 of the first fan growth vector, and [7,0,6] contains the edge element 7 of the second fan growth vector; [0,2] in {[0,2],[7,0]} contains the edge element 2 of the first fan growth vector, and [7,0] contains the edge element 7 of the second fan growth vector.

[0138] Among them, the difference vector between the two subvectors in the subvector pair {[5,0],[3,3]} is [-2,3], the difference vector between the two subvectors in the subvector pair {[5,0,2],[6,3,3]} is [1,3,1], the difference vector between the two subvectors in the subvector pair {[5,0,2,1],[0,6,3,3]} is [-5,6,1,2], the difference vector between the two subvectors in the subvector pair {[5,0,2,1,1],[7,0,6,3,3]} is [2,0,4,2,2], the difference vector between the two subvectors in the subvector pair {[0,2,1,1,0],[7,0,6,3,3 ]} is [7,-2,5,2,3], the difference vector between the two subvectors in the subvector pair {[2,1,1,0,2],[7,0,6,3,3]} is [5,-1,5,3,1], the difference vector between the two subvectors in the subvector pair {[1,1,0,2],[7,0,6,3]} is [6,-1,6,1], the difference vector between the two subvectors in the subvector pair {[1,0,2],[7,0,6]} is [6,0,4], and the difference vector between the two subvectors in the subvector pair {[0,2],[7,0]} is [7,-2].

[0139] As an example of this implementation method, a comparison matrix between the first fan growth vector and the second fan growth vector can be constructed based on the first fan growth vector and the second fan growth vector, wherein the comparison matrix can be an m×n matrix, m can be the number of elements in the second fan growth vector, n can be the number of elements in the first fan growth vector, and the element in the i-th row and j-th column in the comparison matrix can be the difference between the i-th element of the second fan growth vector and the j-th element of the first fan growth vector, 1≤i≤m, 1≤j≤n.

[0140] Figure 2a A schematic diagram showing the age curve of the number of followers of the first publisher in the publisher comparison method provided by the embodiment of the present disclosure. Figure 2a In the figure, the horizontal axis is the number of fans, in units of 10,000 people, and the vertical axis is the time axis, in units of days. The first fan increase vector corresponding to the first publisher is [5, 0, 2, 1, 1, 0, 2]. The first fan increase vector consists of 7 elements.

[0141] Figure 2b A schematic diagram showing the age curve of the second publisher's corresponding fan growth in the publisher comparison method provided by the embodiment of the present disclosure. Figure 2b In the figure, the horizontal axis is the number of fans, in units of 10,000, and the vertical axis is the time axis, in units of days. The second fan increase vector corresponding to the second publisher is [7, 0, 6, 3, 3]. The second fan increase vector includes 5 elements.

[0142] Figure 3A schematic diagram showing a comparison matrix between a first fan growth vector and a second fan growth vector in a comparison method provided by a publisher in an embodiment of the present disclosure. Figure 3 In the example shown, the first fan growth vector is [5, 0, 2, 1, 1, 0, 2], the second fan growth vector is [7, 0, 6, 3, 3], and the comparison matrix between the first and second fan growth vectors is a 5×7 matrix. The element in the i-th row and j-th column of the comparison matrix is ​​the difference between the i-th element of the second fan growth vector and the j-th element of the first fan growth vector, where 1≤i≤5, 1≤j≤7. Figure 3 In , the arrows correspond one-to-one to the difference vectors corresponding to the sub-vector pair. The difference vector corresponding to the sub-vector pair represents the difference vector between the two sub-vectors in the sub-vector pair.

[0143] As an example of this implementation, the similarity of the subvector pair is determined based on the difference vector between the two subvectors in the subvector pair, including: normalizing the difference vector between the two subvectors in the subvector pair to obtain the normalized difference vector corresponding to the subvector pair; and determining the similarity of the subvector pair based on the normalized difference vector corresponding to the subvector pair. In this example, the normalized difference vector corresponding to the subvector pair is obtained by normalizing the difference vector between the two subvectors in the subvector pair, and the similarity of the subvector pair is determined based on the normalized difference vector corresponding to the subvector pair, thereby finding publishers whose absolute values ​​of elements in the fan growth vector are not similar but whose fan growth trends are similar. For example, the first fan growth vector corresponding to the first publisher is [1000, 10, 20], and the second fan growth vector corresponding to the second publisher is [2000, 20, 40]. Although the absolute values ​​of the first and second fan growth vectors are quite different, the fan growth trends of the first and second publishers are similar.

[0144] In one example, the normalizing the difference vector between two sub-vectors in the sub-vector pair to obtain the normalized difference vector corresponding to the sub-vector pair includes: for the difference vector between two sub-vectors in the sub-vector pair, respectively subtracting the minimum element of the difference vector from the elements in the difference vector to obtain the translated difference vector corresponding to the sub-vector pair; and normalizing the elements in the translated difference vector corresponding to the sub-vector pair based on the target element to obtain the normalized difference vector corresponding to the sub-vector pair.

[0145] For example, for the difference vector [-2,3] between two sub-vectors in the sub-vector pair {[5,0],[3,3]}, the minimum element of the difference vector is -2. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively can obtain the translated difference vector [0,5] corresponding to the sub-vector pair {[5,0],[3,3]}.

[0146] For the difference vector [1,3,1] between two subvectors in the subvector pair {[5,0,2],[6,3,3]}, the minimum element of the difference vector is 1. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively can obtain the translated difference vector [0,2,0] corresponding to the subvector pair {[5,0,2],[6,3,3]};

[0147] For the difference vector [-5,6,1,2] between two subvectors in the subvector pair {[5,0,2,1],[0,6,3,3]}, the minimum element of the difference vector is -5. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively, the translated difference vector [0,11,6,7] corresponding to the subvector pair {[5,0,2,1],[0,6,3,3]} can be obtained;

[0148] For the difference vector [2,0,4,2,2] between two subvectors in the subvector pair {[5,0,2,1,1],[7,0,6,3,3]}, the minimum element of the difference vector is 0. Subtract the minimum element of the difference vector from the elements in the difference vector to obtain the translated difference vector [2,0,4,2,2] corresponding to the subvector pair {[5,0,2,1,1],[7,0,6,3,3]};

[0149] For the difference vector [7,-2,5,2,3] between two subvectors in the subvector pair {[0,2,1,1,0],[7,0,6,3,3]}, the minimum element of the difference vector is -2. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively can obtain the translated difference vector [9,0,7,4,5] corresponding to the subvector pair {[0,2,1,1,0],[7,0,6,3,3]};

[0150] For the difference vector [5,-1,5,3,1] between two subvectors in the subvector pair {[2,1,1,0,2],[7,0,6,3,3]}, the minimum element of the difference vector is -1. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively can obtain the translated difference vector [6,0,6,4,2] corresponding to the subvector pair {[2,1,1,0,2],[7,0,6,3,3]};

[0151] For the difference vector [6,-1,6,1] between two subvectors in the subvector pair {[1,1,0,2],[7,0,6,3]}, the minimum element of the difference vector is -1. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively can obtain the translated difference vector [7,0,7,2] corresponding to the subvector pair {[1,1,0,2],[7,0,6,3]};

[0152] For the difference vector [6,0,4] between two sub-vectors in the sub-vector pair {[1,0,2],[7,0,6]}, the minimum element of the difference vector is 0. Subtracting the minimum element of the difference vector from the elements in the difference vector respectively can obtain the translated difference vector [6,0,4] corresponding to the sub-vector pair {[1,0,2],[7,0,6]};

[0153] For the difference vector [7,-2] between two sub-vectors in the sub-vector pair {[0,2],[7,0]}, the minimum element of the difference vector is -2, and the elements in the difference vector are subtracted from the minimum element of the difference vector to obtain the translated difference vector [9,0] corresponding to the sub-vector pair {[0,2],[7,0]}.

[0154] Figure 4 A schematic diagram showing a comparison matrix after translation processing in the comparison method of the publisher provided in an embodiment of the present disclosure. Figure 4 In , the arrows correspond to the difference vectors after translation of the corresponding sub-vector pairs. Figure 4 As shown, for the element in the upper left corner of the comparison matrix, the absolute value of the element in the upper left corner can be taken; and / or, for the element in the lower right corner of the comparison matrix, the absolute value of the element in the lower right corner can be taken.

[0155] In this example, the multiple sub-vector pairs may correspond to the same target element or to different target elements, which is not limited here. The target element corresponding to any sub-vector pair among the multiple sub-vector pairs is greater than or equal to the maximum element in the translated difference vector corresponding to the sub-vector pair.

[0156] In this example, for the difference vector between two sub-vectors in the sub-vector pair, the smallest element of the difference vector is subtracted from the elements in the difference vector to obtain the translated difference vector corresponding to the sub-vector pair, and based on the target element, the elements in the translated difference vector corresponding to the sub-vector pair are normalized to obtain the normalized difference vector corresponding to the sub-vector pair, and based on the normalized difference vector corresponding to the sub-vector pair determined in this way, the similarity between the two sub-vectors in the sub-vector pair can be more accurately determined, thereby more accurately determining the similarity between publishers.

[0157] In one example, the maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element. In this example, the target elements corresponding to the multiple sub-vector pairs are the same. For example, the translated difference vectors corresponding to the multiple sub-vector pairs are [0,5], [0,2,0], [0,11,6,7], [2,0,4,2,2], [9,0,7,4,5], [6,0,6,4,2], [7,0,7,2], [6,0,4] and [9,0], respectively, among which the maximum element is 11, so 11 can be determined as the target element. By dividing each element in [0,5], [0,2,0], [0,11,6,7], [2,0,4,2,2], [9,0,7,4,5], [6,0,6,4,2], [7,0,7,2], [6,0,4] and [9,0] by 11, the normalized difference vectors corresponding to the multiple sub-vector pairs can be obtained.

[0158] In this example, the maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element, and the multiple sub-vector pairs are normalized using the same benchmark. Based on the normalized difference vectors corresponding to the sub-vector pairs determined in this way, the similarity between two sub-vectors in the sub-vector pair can be more accurately determined, thereby enabling the similarity between publishers to be more accurately determined.

[0159] In one example, for any sub-vector pair among the multiple sub-vector pairs, the elements in the translated difference vector corresponding to the sub-vector pair can be added with 1 respectively, and then divided by the third sum value to obtain the normalized difference vector corresponding to the sub-vector pair, where the third sum value is the sum of the target element and 1.

[0160] For example, if the target element is 11, the third sum is 12;

[0161] For the translated difference vector [0,5] corresponding to the sub-vector pair {[5,0],[3,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.083,0.5] corresponding to the sub-vector pair {[5,0],[3,3]};

[0162] For the translated difference vector [0,2,0] corresponding to the sub-vector pair {[5,0,2],[6,3,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.083,0.25,0.083] corresponding to the sub-vector pair {[5,0,2],[6,3,3]};

[0163] For the translated difference vector [0,11,6,7] corresponding to the sub-vector pair {[5,0,2,1],[0,6,3,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.083,1.0,0.583,0.667] corresponding to the sub-vector pair {[5,0,2,1],[0,6,3,3]};

[0164] For the translated difference vector [2,0,4,2,2] corresponding to the sub-vector pair {[5,0,2,1,1],[7,0,6,3,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.25,0.083,0.417,0.25,0.25] corresponding to the sub-vector pair {[5,0,2,1,1],[7,0,6,3,3]};

[0165] For the translated difference vector [9,0,7,4,5] corresponding to the sub-vector pair {[0,2,1,1,0],[7,0,6,3,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.833,0.083,0.667,0.417,0.5] corresponding to the sub-vector pair {[0,2,1,1,0],[7,0,6,3,3]};

[0166] For the translated difference vector [6,0,6,4,2] corresponding to the sub-vector pair {[2,1,1,0,2],[7,0,6,3,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.583,0.083,0.583,0.417,0.25] corresponding to the sub-vector pair {[2,1,1,0,2],[7,0,6,3,3]};

[0167] For the translated difference vector [7,0,7,2] corresponding to the sub-vector pair {[1,1,0,2],[7,0,6,3]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.667,0.083,0.667,0.25] corresponding to the sub-vector pair {[1,1,0,2],[7,0,6,3]};

[0168] For the translated difference vector [6,0,4] corresponding to the sub-vector pair {[1,0,2],[7,0,6]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.583,0.083,0.417] corresponding to the sub-vector pair {[1,0,2],[7,0,6]};

[0169] For the translated difference vector [9,0] corresponding to the sub-vector pair {[0,2],[7,0]}, add 1 to each element in the translated difference vector and divide by 12 to obtain the normalized difference vector [0.833,0.083] corresponding to the sub-vector pair {[0,2],[7,0]}.

[0170] Figure 5 A schematic diagram showing a normalized comparison matrix in the comparison method of the publisher provided by the embodiment of the present disclosure. Figure 5 In , the arrows correspond one-to-one to the normalized difference vectors corresponding to the sub-vector pairs.

[0171] In another example, the target elements corresponding to the plurality of sub-vector pairs may be different. For example, for any sub-vector pair among the plurality of sub-vector pairs, the maximum element in the translated difference vector corresponding to the sub-vector pair may be determined as the target element corresponding to the sub-vector pair.

[0172] In another example, the normalizing the difference vector between two sub-vectors in the sub-vector pair to obtain the normalized difference vector corresponding to the sub-vector pair includes: for the difference vector between two sub-vectors in the sub-vector pair, subtracting the minimum element of the difference vector from the elements in the difference vector, and adding 1 to obtain the translated difference vector corresponding to the sub-vector pair; and normalizing the elements in the translated difference vector corresponding to the sub-vector pair based on the target element to obtain the normalized difference vector corresponding to the sub-vector pair.

[0173] In one example, the similarity of the subvector pair is negatively correlated with the sum of the elements of the normalized difference vectors corresponding to the subvector pair. In this example, for any subvector pair among the multiple subvector pairs, the larger the sum of the elements of the normalized difference vectors corresponding to the subvector pair, the smaller the similarity between the two subvectors in the subvector pair, and the smaller the sum of the elements of the normalized difference vectors corresponding to the subvector pair, the greater the similarity between the two subvectors in the subvector pair. According to this example, the similarity between the two subvectors in the subvector pair can be determined more accurately.

[0174] In one example, the similarity of the sub-vector pair is negatively correlated with a first ratio, wherein the first ratio is the ratio between a first sum value and a second sum value, the first sum value is the sum of the elements of the normalized difference vectors corresponding to the sub-vector pair, and the second sum value is the maximum value of the sum of the elements of the normalized difference vectors corresponding to the multiple sub-vector pairs.

[0175] Among them, the first ratio corresponding to the kth sub-vector pair in the plurality of sub-vector pairs can be recorded as Among them, d krepresents the first sum value corresponding to the kth sub-vector pair, that is, d k represents the sum of the elements of the normalized difference vector corresponding to the kth sub-vector pair, d kmax represents the second sum, that is, d kmax represents the maximum value of the sum of the elements of the normalized difference vectors corresponding to the plurality of sub-vector pairs. For example, if there are 9 sub-vector pairs in total, then 1≤k≤9.

[0176] For example, the normalized difference vector corresponding to the subvector pair {[5,0],[3,3]} is [0.083,0.5]. Then, the d corresponding to the subvector pair {[5,0],[3,3]} is k =0.083+0.5=0.583;

[0177] The normalized difference vector corresponding to the subvector pair {[5,0,2],[6,3,3]} is [0.083,0.25,0.083]. Then, the d corresponding to the subvector pair {[5,0,2],[6,3,3]} is k =0.083+0.25+0.083=0.416;

[0178] The normalized difference vector corresponding to the subvector pair {[5,0,2,1],[0,6,3,3]} is [0.083,1.0,0.583,0.667]. Then, the d corresponding to the subvector pair {[5,0,2,1],[0,6,3,3]} is k =0.083+1.0+0.583+0.667=2.333;

[0179] The normalized difference vector corresponding to the subvector pair {[5,0,2,1,1],[7,0,6,3,3]} is [0.25,0.083,0.417,0.25,0.25]. Then, the d corresponding to the subvector pair {[5,0,2,1,1],[7,0,6,3,3]} is k =0.25+0.083+0.417+0.25+0.25=1.25;

[0180] The normalized difference vector corresponding to the subvector pair {[0,2,1,1,0],[7,0,6,3,3]} is [0.833,0.083,0.667,0.417,0.5]. Then, the d corresponding to the subvector pair {[0,2,1,1,0],[7,0,6,3,3]} is k =0.833+0.083+0.667+0.417+0.5=2.5;

[0181] The normalized difference vector corresponding to the subvector pair {[2,1,1,0,2],[7,0,6,3,3]} is [0.583,0.083,0.583,0.417,0.25]. Then, the d corresponding to the subvector pair {[2,1,1,0,2],[7,0,6,3,3]} is k =0.583+0.083+0.583+0.417+0.25=1.916;

[0182] The normalized difference vector corresponding to the subvector pair {[1,1,0,2],[7,0,6,3]} is [0.667,0.083,0.667,0.25]. Then, the d corresponding to the subvector pair {[1,1,0,2],[7,0,6,3]} is k =0.667+0.083+0.667+0.25=1.667;

[0183] The normalized difference vector corresponding to the subvector pair {[1,0,2],[7,0,6]} is [0.583,0.083,0.417]. Then, the d corresponding to the subvector pair {[1,0,2],[7,0,6]} is k =0.583+0.083+0.417=1.083;

[0184] The normalized difference vector corresponding to the subvector pair {[0,2],[7,0]} is [0.833,0.083]. Then, the d corresponding to the subvector pair {[0,2],[7,0]} is k =0.833+0.083=0.916.

[0185] Among them, d kmax =2.5.

[0186] According to this example, the accuracy of the similarity of the determined sub-vector pairs can be further improved, that is, the similarity of the sub-vector pairs determined according to this example can more accurately reflect the similarity of the fan growth trends of the first fan growth vector and the second fan growth vector.

[0187] In one example, the similarity of the sub-vector pair is positively correlated with the length of the sub-vector in the sub-vector pair. In this example, for any sub-vector pair in the multiple sub-vector pairs, the larger the length of the sub-vector in the sub-vector pair, the greater the similarity between the two sub-vectors in the sub-vector pair, and the smaller the length of the sub-vector in the sub-vector pair, the smaller the similarity between the two sub-vectors in the sub-vector pair. The similarity of the sub-vector pair determined according to this example can more accurately reflect the similarity of the fan growth trends of the first fan growth vector and the second fan growth vector.

[0188] In one example, the similarity of the sub-vector pair is positively correlated with a second ratio, wherein the second ratio is a ratio between a first length and a second length, the first length being the length of a sub-vector in the sub-vector pair, and the second length being the maximum length of a sub-vector in the multiple sub-vector pairs.

[0189] The second ratio corresponding to the kth sub-vector pair among the plurality of sub-vector pairs can be expressed as Among them, l k represents the first length corresponding to the kth sub-vector pair, that is, l k represents the length of the subvector in the kth subvector pair, l max Represents the second length, i.e., l max represents the maximum length of a sub-vector in the plurality of sub-vector pairs. For example, if there are 9 sub-vector pairs in total, then 1≤k≤9.

[0190] For example, the subvector pair {[5,0],[3,3]} corresponds to l k = 2, the corresponding l of the subvector pair {[5,0,2],[6,3,3]} k =3, the corresponding l of the subvector pair {[5,0,2,1],[0,6,3,3]} k =4, the corresponding l of the subvector pair {[5,0,2,1,1],[7,0,6,3,3]} k =5, the corresponding l of the subvector pair {[0,2,1,1,0],[7,0,6,3,3]} k =5, the corresponding l of the subvector pair {[2,1,1,0,2],[7,0,6,3,3]} k =5, the corresponding l of the subvector pair {[1,1,0,2],[7,0,6,3]} k =4, the corresponding l of the subvector pair {[1,0,2],[7,0,6]} k =3, the corresponding l of the subvector pair {[0,2],[7,0]} k =2. Among them, l max =5.

[0191] According to this example, the accuracy of the similarity of the determined sub-vector pairs can be further improved, that is, the similarity of the sub-vector pairs determined according to this example can more accurately reflect the similarity of the fan growth trends of the first fan growth vector and the second fan growth vector.

[0192] In one example, Formula 1 can be used to determine the similarity s between the two sub-vectors in the k-th sub-vector pair: k :

[0193]

[0194] Among them, d k represents the sum of the elements of the normalized difference vector corresponding to the kth sub-vector pair, d kmax represents the maximum value of the sum of the elements of the normalized difference vectors corresponding to the plurality of sub-vector pairs, l k represents the length of the subvector in the kth subvector pair, l max represents the maximum length of a sub-vector in the plurality of sub-vector pairs.

[0195] For example, for the subvector pair {[5,0],[3,3]},

[0196] For the pair of subvectors {[5,0,2,1],[0,6,3,3]},

[0197] For the subvector pair {[0,2,1,1,0],[7,0,6,3,3]},

[0198] In this example, by adopting the distance penalty and length penalty Determine the similarity s between the two sub-vectors in the k-th sub-vector pair k , the determined similarity s k It can more accurately reflect the similarity of the follower growth trends of the first follower growth vector and the second follower growth vector.

[0199] As another example of this implementation, the difference vector between the two sub-vectors in the sub-vector pair may not be normalized, and the similarity of the sub-vector pair may be determined directly based on the two sub-vectors in the sub-vector pair.

[0200] As an example of this implementation, determining the similarity between the first publisher and the second publisher based on the similarities of the multiple sub-vector pairs includes: determining the maximum similarity among the similarities of the multiple sub-vector pairs as the similarity between the first publisher and the second publisher. In this example, by determining the maximum similarity among the similarities of the multiple sub-vector pairs as the similarity between the first publisher and the second publisher, it is helpful to discover publishers with similar fan growth trends.

[0201] In other examples, the similarity between the first publisher and the second publisher may also be determined according to an average value or a median of the similarities of the plurality of sub-vector pairs.

[0202] In one possible implementation, after determining the similarity between the first publisher and the second publisher, the method further includes: in response to the similarity between the first publisher and the second publisher being greater than or equal to a preset similarity, determining that the first publisher and the second publisher are similar publishers to each other; or, in response to the similarity between the first publisher and the second publisher being less than a preset similarity, determining that the first publisher and the second publisher are non-similar publishers to each other.

[0203] The publisher comparison method provided by the embodiment of the present disclosure is described below through a specific application scenario.

[0204] In this application scenario, 101 intervals of the number of fans can be preset, namely [0, 1w), [1w, 2w), …, [99w, 100w), [100w, +∞). The number of fans of the first publisher every day after registering the account can be obtained, and the first fan growth vector corresponding to the first publisher can be determined based on the number of fans of the first publisher every day after registering the account and the preset 101 fan number intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates the number of days that the number of fans of the first publisher stays in the fan number interval corresponding to the element. For example, the first fan growth vector is [5, 0, 2, 1, 1, 0, 2]. The number of fans of the second publisher every day after registering the account can be obtained, and the second fan growth vector corresponding to the second publisher can be determined based on the number of fans of the second publisher every day after registering the account and the preset 101 fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector indicates the number of days that the number of fans of the second publisher stays in the fan number interval corresponding to the element. For example, the second fan growth vector is [7,0,6,3,3].

[0205] According to the first and second fan growth vectors, the following nine sub-vector pairs can be determined: {[5,0],[3,3]}, {[5,0,2],[6,3,3]}, {[5,0,2,1],[0,6,3,3]}, {[5,0,2,1,1],[7,0,6,3,3]}, {[0,2,1,1,0],[7,0,6,3,3]}, {[2,1,1,0,2],[7,0,6,3,3]}, {[1,1,0,2],[7,0,6,3]}, {[1,0,2],[7,0,6]}, {[0,2],[7,0]}.

[0206] Among them, the difference vector between the two subvectors in the subvector pair {[5,0],[3,3]} is [-2,3], the difference vector between the two subvectors in the subvector pair {[5,0,2],[6,3,3]} is [1,3,1], the difference vector between the two subvectors in the subvector pair {[5,0,2,1],[0,6,3,3]} is [-5,6,1,2], the difference vector between the two subvectors in the subvector pair {[5,0,2,1,1],[7,0,6,3,3]} is [2,0,4,2,2], the difference vector between the two subvectors in the subvector pair {[0,2,1,1,0],[7,0,6,3,3 ]} is [7,-2,5,2,3], the difference vector between the two subvectors in the subvector pair {[2,1,1,0,2],[7,0,6,3,3]} is [5,-1,5,3,1], the difference vector between the two subvectors in the subvector pair {[1,1,0,2],[7,0,6,3]} is [6,-1,6,1], the difference vector between the two subvectors in the subvector pair {[1,0,2],[7,0,6]} is [6,0,4], and the difference vector between the two subvectors in the subvector pair {[0,2],[7,0]} is [7,-2].

[0207] like Figure 3 As shown, a comparison matrix between the first fan growth vector and the second fan growth vector can be constructed. The comparison matrix is ​​a 5×7 matrix. The element in the i-th row and j-th column of the comparison matrix is ​​the difference between the i-th element of the second fan growth vector and the j-th element of the first fan growth vector, where 1≤i≤5, 1≤j≤7. Figure 3 In , the arrows correspond one-to-one to the difference vectors corresponding to the sub-vector pairs.

[0208] For the difference vector between two sub-vectors in any of the 9 sub-vector pairs, the elements in the difference vector are subtracted from the minimum element of the difference vector to obtain the translated difference vector corresponding to the sub-vector pair. Among them, the translated difference vector corresponding to the sub-vector pair {[5,0],[3,3]} is [0,5], the translated difference vector corresponding to the sub-vector pair {[5,0,2],[6,3,3]} is [0,2,0], the translated difference vector corresponding to the sub-vector pair {[5,0,2,1],[0,6,3,3]} is [0,11,6,7], the translated difference vector corresponding to the sub-vector pair {[5,0,2,1,1],[7,0,6,3,3]} is [2,0,4,2,2], and the translated difference vector corresponding to the sub-vector pair {[0,2,1,1,0],[7,0,6, The translated difference vector corresponding to the subvector pair {[2,1,1,0,2],[7,0,6,3,3]} is [6,0,6,4,2], the translated difference vector corresponding to the subvector pair {[1,1,0,2],[7,0,6,3]} is [7,0,7,2], the translated difference vector corresponding to the subvector pair {[1,0,2],[7,0,6]} is [6,0,4], and the translated difference vector corresponding to the subvector pair {[0,2],[7,0]} is [9,0].

[0209] The maximum element 11 in the translated difference vector corresponding to the 9 sub-vector pairs can be determined as the target element. The target element is added by 1 to obtain the third sum 12. For any of the 9 sub-vector pairs, the elements in the translated difference vector corresponding to the sub-vector pair can be added by 1 respectively, and then divided by the third sum to obtain the normalized difference vector corresponding to the sub-vector pair. Among them, the normalized difference vector corresponding to the subvector pair {[5,0],[3,3]} is [0.083,0.5], the normalized difference vector corresponding to the subvector pair {[5,0,2],[6,3,3]} is [0.083,0.25,0.083], the normalized difference vector corresponding to the subvector pair {[5,0,2,1],[0,6,3,3]} is [0.083,1.0,0.583,0.667], the normalized difference vector corresponding to the subvector pair {[5,0,2,1,1],[7,0,6,3,3]} is [0.25,0.083,0.417,0.25,0.25], and the normalized difference vector corresponding to the subvector pair {[0,2,1,1,0],[7,0,6,3,3]} is [0.083,0.25,0.083] The difference vector is [0.833, 0.083, 0.667, 0.417, 0.5], the normalized difference vector corresponding to the sub-vector pair {[2, 1, 1, 0, 2], [7, 0, 6, 3, 3]} is [0.583, 0.083, 0.583, 0.417, 0.25], the normalized difference vector corresponding to the sub-vector pair {[1, 1, 0, 2], [7, 0, 6, 3]} is [0.667, 0.083, 0.667, 0.25], the normalized difference vector corresponding to the sub-vector pair {[1, 0, 2], [7, 0, 6]} is [0.583, 0.083, 0.417], and the normalized difference vector corresponding to the sub-vector pair {[0, 2], [7, 0]} is [0.833, 0.083].

[0210] The similarity of each of the 9 sub-vector pairs may be determined using Formula 1. The maximum similarity among the similarities of the 9 sub-vector pairs may be determined as the similarity between the first publisher and the second publisher.

[0211] Figure 6a A schematic diagram showing the age curve of the number of followers of a target publisher in the publisher comparison method provided by the embodiment of the present disclosure. Figure 6a In the figure, the horizontal axis is the number of fans, in units of 10,000 people, and the vertical axis is the time axis, in units of days. Using the publisher comparison method provided by the embodiment of the present disclosure, for any target publisher, similar publishers, most similar publishers, and non-similar publishers corresponding to the target publisher can be determined. Figure 6b A schematic diagram showing the age curve of the number of followers of the most similar publishers of the target publisher in the publisher comparison method provided by the embodiment of the present disclosure. Figure 6bIn the figure, the horizontal axis is the number of fans, in units of ten thousand people, and the vertical axis is the time axis, in units of days. Figure 6c A schematic diagram showing the age curve of the number of followers of similar publishers of a target publisher in the publisher comparison method provided by an embodiment of the present disclosure. Figure 6c In the figure, the horizontal axis is the number of fans, in units of ten thousand people, and the vertical axis is the time axis, in units of days. Figure 6d A schematic diagram showing the fan growth day age curve corresponding to the non-similar publishers of the target publisher in the publisher comparison method provided by the embodiment of the present disclosure. Figure 6d In the figure, the horizontal axis is the number of fans, in units of ten thousand people, and the vertical axis is the time axis, in units of days.

[0212] Figure 7 A schematic diagram showing a fan growth curve corresponding to a publisher in the publisher comparison method provided by an embodiment of the present disclosure. Figure 7 In the chart, the horizontal axis is the time axis, with the unit being days, and the vertical axis represents the number of fans, with the unit being 10,000 people. Figure 7 As shown, according to the number of fans of publisher 1 every day after registering an account, a fan growth curve 31 corresponding to publisher 1 can be obtained; according to the number of fans of publisher 2 every day after registering an account, a fan growth curve 32 corresponding to publisher 2 can be obtained; according to the number of fans of publisher 3 every day after registering an account, a fan growth curve 33 corresponding to publisher 3 can be obtained; according to the number of fans of publisher 4 every day after registering an account, a fan growth curve 34 corresponding to publisher 4 can be obtained; according to the number of fans of publisher 5 every day after registering an account, a fan growth curve 35 corresponding to publisher 5 can be obtained. Using the comparison method of publishers provided by the embodiment of the present disclosure, it can be determined that publisher 1, publisher 2, publisher 3 and publisher 5 are similar publishers, and publisher 4 and publisher 5 are non-similar publishers.

[0213] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, the present disclosure will not repeat them. It can be understood by those skilled in the art that in the above-mentioned method of the specific implementation method, the specific execution order of each step should be determined according to its function and possible internal logic.

[0214] In addition, the present disclosure also provides a publisher's comparison device, electronic device, computer-readable storage medium, and computer program product, all of which can be used to implement any publisher's comparison method provided by the present disclosure. The corresponding technical solutions and technical effects can be found in the corresponding records in the method part and will not be repeated here.

[0215] Figure 8 FIG. 2 is a block diagram of a comparison device provided by a publisher according to an embodiment of the present disclosure. Figure 8 As shown, the publisher's comparison device includes:

[0216] An acquisition module 41 is used to acquire the number of fans of the first publisher at different times and the number of fans of the second publisher at different times;

[0217] A first determination module 42, configured to determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times;

[0218] A second determination module 43, configured to determine a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times;

[0219] The third determining module 44 is used to determine the similarity between the first publisher and the second publisher according to the sub-vector of the first follower growth vector and the sub-vector of the second follower growth vector.

[0220] In one possible implementation,

[0221] The first determination module 42 is used to determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times and a plurality of preset fan number intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element;

[0222] The second determination module 43 is used to determine the second fan growth vector corresponding to the second publisher based on the number of fans of the second publisher at different times and the preset multiple fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector represents the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element.

[0223] In a possible implementation, the third determining module 44 is used to:

[0224] The similarity between the first publisher and the second publisher is determined according to the continuous subvector of the first follower growth vector and the continuous subvector of the second follower growth vector.

[0225] In a possible implementation, the third determining module 44 is used to:

[0226] The similarity between the first publisher and the second publisher is determined according to subvectors of the same length in the first follower growth vector and the second follower growth vector.

[0227] In a possible implementation, the third determining module 44 is used to:

[0228] Determine a plurality of sub-vector pairs in the first powder growth vector and the second powder growth vector according to the sub-vectors of the same length in the first powder growth vector and the second powder growth vector, wherein any sub-vector pair in the plurality of sub-vector pairs includes the sub-vectors of the same length in the first powder growth vector and the second powder growth vector;

[0229] For any sub-vector pair among the plurality of sub-vector pairs, determining the similarity of the sub-vector pair according to a difference vector between two sub-vectors in the sub-vector pair;

[0230] The similarity between the first publisher and the second publisher is determined according to the similarities of the plurality of sub-vector pairs.

[0231] In a possible implementation, the third determining module 44 is used to:

[0232] Normalizing a difference vector between two sub-vectors in the sub-vector pair to obtain a normalized difference vector corresponding to the sub-vector pair;

[0233] The similarity of the sub-vector pair is determined according to the normalized difference vector corresponding to the sub-vector pair.

[0234] In a possible implementation, the third determining module 44 is used to:

[0235] For a difference vector between two sub-vectors in the sub-vector pair, subtract the minimum element of the difference vector from the elements in the difference vector to obtain a translated difference vector corresponding to the sub-vector pair;

[0236] Based on the target element, the elements in the translated difference vector corresponding to the sub-vector pair are normalized to obtain a normalized difference vector corresponding to the sub-vector pair.

[0237] In a possible implementation manner, the maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element.

[0238] In a possible implementation, the similarity of the sub-vector pair is negatively correlated with the sum of elements of the normalized difference vector corresponding to the sub-vector pair.

[0239] In one possible implementation, the similarity of the sub-vector pair is negatively correlated with a first ratio, wherein the first ratio is the ratio between a first sum value and a second sum value, the first sum value is the sum of the elements of the normalized difference vectors corresponding to the sub-vector pair, and the second sum value is the maximum value of the sum of the elements of the normalized difference vectors corresponding to the multiple sub-vector pairs.

[0240] In a possible implementation manner, the similarity of the sub-vector pair is positively correlated with the length of the sub-vector in the sub-vector pair.

[0241] In a possible implementation, the similarity of the sub-vector pair is positively correlated with a second ratio, wherein the second ratio is a ratio between a first length and a second length, the first length is the length of a sub-vector in the sub-vector pair, and the second length is the maximum length of a sub-vector in the multiple sub-vector pairs.

[0242] In a possible implementation, the third determining module 44 is used to:

[0243] The maximum similarity among the similarities of the plurality of sub-vector pairs is determined as the similarity between the first publisher and the second publisher.

[0244] In the embodiments of the present disclosure, by obtaining the number of fans of the first publisher and the number of fans of the second publisher at different times, a first fan growth vector corresponding to the first publisher is determined according to the number of fans of the first publisher at different times, and a second fan growth vector corresponding to the second publisher is determined according to the number of fans of the second publisher at different times, and the similarity between the first publisher and the second publisher is determined according to the sub-vector of the first fan growth vector and the sub-vector of the second fan growth vector, thereby accurately discovering similar publishers, and thus being able to adopt the same or similar push strategies for the content published by similar publishers, which in turn helps the publishing platform to more effectively distribute the content published by the publishers, thereby helping to save the bandwidth of the content distribution network.

[0245] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. Its specific implementation and technical effects can refer to the description of the above method embodiments. For the sake of brevity, they will not be repeated here.

[0246] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium, or may be a volatile computer-readable storage medium.

[0247] The embodiment of the present disclosure further provides a computer program, including a computer-readable code. When the computer-readable code is executed in an electronic device, a processor in the electronic device executes the above method.

[0248] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in an electronic device, a processor in the electronic device executes the above method.

[0249] An embodiment of the present disclosure also provides an electronic device, comprising: one or more processors; and a memory for storing executable instructions; wherein the one or more processors are configured to call the executable instructions stored in the memory to execute the above method.

[0250] The electronic device may be provided as a terminal, a server, or a device in other forms.

[0251] Fig. 9 1 is a block diagram of an electronic device 1900 provided by an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server. Fig. 9 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0252] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as a Microsoft Server operating system (Windows Server 2003). TM ), a graphical user interface operating system launched by Apple (Mac OSX TM ), a multi-user, multi-process computer operating system (Unix TM ), a free and open source Unix-like operating system (Linux TM ), an open source Unix-like operating system (FreeBSD TM ) or similar.

[0253] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0254] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0255] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0256] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0257] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0258] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0259] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0260] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0261] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0262] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.

[0263] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0264] If the technical solution of the embodiments of the present disclosure involves personal information, the product using the technical solution of the embodiments of the present disclosure has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of the embodiments of the present disclosure involves sensitive personal information, the product using the technical solution of the embodiments of the present disclosure has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the requirement of "explicit consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to collect his or her personal information; or on the device for processing personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0265] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A comparison method for publishers, characterized in that: include: Get the number of followers of the first publisher at different times and the number of followers of the second publisher at different times; Determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times and a plurality of preset fan number intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates the length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element; Determine a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times and the preset multiple fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector represents the length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element; The similarity between the first publisher and the second publisher is determined according to the subvector of the first follower growth vector and the subvector of the second follower growth vector.

2. The method according to claim 1, characterized in that The determining the similarity between the first publisher and the second publisher according to the subvector of the first follower growth vector and the subvector of the second follower growth vector includes: The similarity between the first publisher and the second publisher is determined according to the continuous subvector of the first follower growth vector and the continuous subvector of the second follower growth vector.

3. The method according to claim 1, characterized in that The determining the similarity between the first publisher and the second publisher according to the subvector of the first follower growth vector and the subvector of the second follower growth vector includes: The similarity between the first publisher and the second publisher is determined according to subvectors of the same length in the first follower growth vector and the second follower growth vector.

4. The method according to claim 3, characterized in that: The determining the similarity between the first publisher and the second publisher according to the subvectors of the same length in the first follower growth vector and the second follower growth vector includes: Determine a plurality of sub-vector pairs in the first powder growth vector and the second powder growth vector according to the sub-vectors of the same length in the first powder growth vector and the second powder growth vector, wherein any sub-vector pair in the plurality of sub-vector pairs includes the sub-vectors of the same length in the first powder growth vector and the second powder growth vector; For any sub-vector pair among the plurality of sub-vector pairs, determining the similarity of the sub-vector pair according to a difference vector between two sub-vectors in the sub-vector pair; The similarity between the first publisher and the second publisher is determined according to the similarities of the plurality of sub-vector pairs.

5. The method according to claim 4, characterized in that The determining the similarity of the subvector pair according to the difference vector between two subvectors in the subvector pair comprises: Normalizing a difference vector between two sub-vectors in the sub-vector pair to obtain a normalized difference vector corresponding to the sub-vector pair; The similarity of the sub-vector pair is determined according to the normalized difference vector corresponding to the sub-vector pair.

6. The method according to claim 5, characterized in that The normalizing the difference vector between two sub-vectors in the sub-vector pair to obtain a normalized difference vector corresponding to the sub-vector pair includes: For a difference vector between two sub-vectors in the sub-vector pair, subtract the minimum element of the difference vector from the elements in the difference vector to obtain a translated difference vector corresponding to the sub-vector pair; Based on the target element, the elements in the translated difference vector corresponding to the sub-vector pair are normalized to obtain a normalized difference vector corresponding to the sub-vector pair.

7. The method according to claim 6, characterized in that The maximum element in the translated difference vectors corresponding to the multiple sub-vector pairs is determined as the target element.

8. The method according to any one of claims 5 to 7, characterized in that The similarity of the sub-vector pair is negatively correlated with the sum of the elements of the normalized difference vector corresponding to the sub-vector pair.

9. The method according to claim 8, characterized in that The similarity of the sub-vector pair is negatively correlated with a first ratio, wherein the first ratio is the ratio between a first sum value and a second sum value, the first sum value is the sum of the elements of the normalized difference vectors corresponding to the sub-vector pair, and the second sum value is the maximum value of the sum of the elements of the normalized difference vectors corresponding to the multiple sub-vector pairs.

10. The method according to claim 8, characterized in that The similarity of the sub-vector pair is positively correlated with the length of the sub-vector in the sub-vector pair.

11. The method according to claim 10, characterized in that The similarity of the sub-vector pair is positively correlated with a second ratio, wherein the second ratio is a ratio between a first length and a second length, the first length is a length of a sub-vector in the sub-vector pair, and the second length is a maximum length of a sub-vector in the multiple sub-vector pairs.

12. The method according to any one of claims 4 to 7, characterized in that: The determining, according to the similarities of the plurality of sub-vector pairs, the similarity between the first publisher and the second publisher comprises: The maximum similarity among the similarities of the plurality of sub-vector pairs is determined as the similarity between the first publisher and the second publisher.

13. A publisher's comparison device, characterized in that: include: An acquisition module, used to acquire the number of fans of the first publisher at different times and the number of fans of the second publisher at different times; a first determination module, configured to determine a first fan growth vector corresponding to the first publisher according to the number of fans of the first publisher at different times and a plurality of preset fan number intervals, wherein the first fan growth vector includes at least one element, and any element in the first fan growth vector indicates a length of time that the number of fans of the first publisher stays in the fan number interval corresponding to the element; a second determination module, configured to determine a second fan growth vector corresponding to the second publisher according to the number of fans of the second publisher at different times and the plurality of preset fan number intervals, wherein the second fan growth vector includes at least one element, and any element in the second fan growth vector indicates a length of time that the number of fans of the second publisher stays in the fan number interval corresponding to the element; The third determination module is used to determine the similarity between the first publisher and the second publisher according to the subvector of the first follower growth vector and the subvector of the second follower growth vector.

14. An electronic device, characterized in that: include: one or more processors; a memory for storing executable instructions; The one or more processors are configured to call the executable instructions stored in the memory to execute the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product, characterized in that The invention comprises a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code, wherein when the computer-readable code is executed in an electronic device, a processor in the electronic device executes the method according to any one of claims 1 to 12.

Images