Methods, apparatus, electronic devices and storage media for determining similarity between objects

Abstract

This invention relates to a method, apparatus, electronic device, and storage medium for determining the similarity between objects. The method includes: determining a first set of audience users for a first object and a second set of audience users for a second object; determining an overlapping set of audience users between the first and second objects based on the first and second set of audience users; determining a first circle and a second circle with the number of audience users in the first set as the area of ​​a first circle, the number of audience users in the second set as the area of ​​a second circle, and the number of overlapping audience users in the overlapping set as the overlapping area of ​​the first and second circles; determining the distance between the centers of the first and second circles; and determining the similarity between the first and second objects based on the distance between their centers. This avoids the limitations of determining the similarity between objects based on content tags, object file information, etc., and achieves a quantifiable determination of the similarity between objects.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, apparatus, electronic device and storage medium for determining the similarity between objects. Background Technology

[0002] In practical applications, determining the similarity between different objects is a common problem in object content understanding, and it can be valuable in various scenarios such as content operation, planning, and prediction.

[0003] In existing technologies, objects containing similar elements are typically considered to have a high degree of similarity based on information such as content tags and object text. For example, if video clip A and video clip B both have the content tag "dancing scene," then video clip A and video clip B can be considered two highly similar objects.

[0004] However, the above methods for determining the similarity between objects are highly dependent on the richness of the objects' tags or text, which in turn depends on the different levels of understanding of different users. This makes the above methods for determining similarity have certain limitations and are difficult to quantify. Summary of the Invention

[0005] In view of this, in order to solve the technical problems of the limitations and difficulty in quantification of the above-mentioned methods for determining the similarity between objects, embodiments of the present invention provide a method, apparatus, electronic device and storage medium for determining the similarity between objects.

[0006] In a first aspect, embodiments of the present invention provide a method for determining the similarity between objects, the method comprising:

[0007] Determine the first audience set for the first object, and determine the second audience set for the second object;

[0008] Based on the first audience user set and the second audience user set, determine the overlapping audience user set between the first object and the second object;

[0009] The first circle and the second circle are determined by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0010] Determine the center distance between the first circle and the second circle;

[0011] The similarity between the first object and the second object is determined based on the center distance.

[0012] In one possible implementation, determining the overlapping audience set between the first object and the second object based on the first audience set and the second audience set includes:

[0013] Audience users who exist simultaneously in both the first audience user set and the second audience user set are identified as overlapping audience users between the first object and the second object; or, audience users whose feature similarity between the first audience user set and the second audience user set is greater than a preset similarity threshold are identified as overlapping audience users between the first object and the second object.

[0014] The overlapping audience users are grouped into the overlapping audience user set.

[0015] In one possible implementation, determining the center distance between the first circle and the second circle includes:

[0016] The following system of equations is constructed and solved to obtain the distance between the centers of the first circle and the second circle:

[0017]

[0018] Wherein, the UV A The number of users in the first target audience group, the UV B The number of users in the second target audience group, the UV AB The number of overlapping audience users in the overlapping audience user set, r1 is the radius of the first circle, r2 is the radius of the second circle, θ1 is half the angle between the first vector and the second vector, the first vector and the second vector both start from the center of the first circle, and the first vector and the second vector each end at the two intersection points of the first circle and the second circle, respectively, θ2 is half the angle between the third vector and the fourth vector, the third vector and the fourth vector both start from the center of the second circle, and the third vector and the fourth vector each end at the two intersection points of the first circle and the second circle, respectively, and d is the distance between the centers of the first circle and the second circle.

[0019] In one possible implementation, determining the similarity between the first object and the second object based on the center-to-center distance includes:

[0020] The radius of the first circle, the radius of the second circle, and the distance between their centers are input into a preset similarity calculation formula to obtain the similarity between the first object and the second object. The similarity calculation formula is as follows:

[0021]

[0022] Wherein, the S AB The similarity between the first object and the second object is denoted by d; the center distance of the circles is d; r1 is the radius of the first circle and r2 is the radius of the second circle.

[0023] In one possible implementation, before determining the first circle and the second circle by using the number of audience members in the first audience user group as the area of ​​the first circle, the number of audience members in the second audience user group as the area of ​​the second circle, and the number of overlapping audience members in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle, the method further includes:

[0024] For each overlapping audience user in the overlapping audience user set, determine the number of interest points of the overlapping audience user; based on the number of interest points, determine the weight value corresponding to the overlapping audience user, wherein the number of interest points and the weight value are negatively correlated;

[0025] Based on the weight value corresponding to each overlapping audience user, the number of overlapping audience users is adjusted, and based on the adjusted number of overlapping audience users, the steps of determining the first circle and the second circle are performed, with the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0026] In one possible implementation, after determining the overlapping audience user set between the first object and the second object, the method further includes:

[0027] Determine the first publication time of the first object and the second publication time of the second object;

[0028] Based on the first publication time and the second publication time, determine the publication time interval between the first object and the second object;

[0029] The overlapping audience user set is adjusted according to the release time interval, so as to perform the step of determining the first circle and the second circle based on the adjusted overlapping audience user set, with the number of audience users in the first audience user set as the area of ​​the first circle, the number of audience users in the second audience user set as the area of ​​the second circle, and the number of overlapping audience users in the overlapping audience user set as the overlapping area of ​​the first circle and the second circle.

[0030] Secondly, embodiments of the present invention provide an apparatus for determining the similarity between objects, the apparatus comprising:

[0031] The first determining module is used to determine the first audience user set of the first object and the second audience user set of the second object;

[0032] The second determining module is used to determine the overlapping audience set between the first object and the second object based on the first audience set and the second audience set;

[0033] The third determining module is used to determine the first circle and the second circle by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0034] The fourth determining module is used to determine the center distance between the first circle and the second circle;

[0035] The fifth determining module is used to determine the similarity between the first object and the second object based on the center distance.

[0036] In one possible implementation, the second determining module is specifically used for:

[0037] Audience users who exist simultaneously in both the first audience user set and the second audience user set are identified as overlapping audience users between the first object and the second object; or, audience users whose feature similarity between the first audience user set and the second audience user set is greater than a preset similarity threshold are identified as overlapping audience users between the first object and the second object.

[0038] The overlapping audience users are grouped into the overlapping audience user set.

[0039] In one possible implementation, the fourth determining module is specifically used for:

[0040] The following system of equations is constructed and solved to obtain the distance between the centers of the first circle and the second circle:

[0041]

[0042] Wherein, the UV A The number of users in the first target audience group, the UV B The number of users in the second target audience group, the UV ABThe number of overlapping audience users in the overlapping audience user set, r1 is the radius of the first circle, r2 is the radius of the second circle, θ1 is half the angle between the first vector and the second vector, the first vector and the second vector both start from the center of the first circle, and the first vector and the second vector each end at the two intersection points of the first circle and the second circle, respectively, θ2 is half the angle between the third vector and the fourth vector, the third vector and the fourth vector both start from the center of the second circle, and the third vector and the fourth vector each end at the two intersection points of the first circle and the second circle, respectively, and d is the distance between the centers of the first circle and the second circle.

[0043] In one possible implementation, the fifth determining module is specifically used for:

[0044] The radius of the first circle, the radius of the second circle, and the distance between their centers are input into a preset similarity calculation formula to obtain the similarity between the first object and the second object. The similarity calculation formula is as follows:

[0045]

[0046] Wherein, the S AB The similarity between the first object and the second object is denoted by d; the center distance of the circles is d; r1 is the radius of the first circle and r2 is the radius of the second circle.

[0047] In one possible implementation, the device further includes:

[0048] The sixth determining module is used to determine the area of ​​a first circle (based on the number of users in the first audience user set), the area of ​​a second circle (based on the number of users in the second audience user set), and the overlapping area of ​​the first and second circles (based on the number of overlapping users in the overlapping audience user set) before determining the first and second circles. Specifically, for each overlapping audience user in the overlapping audience user set, the module determines the number of interest points for that overlapping audience user. Based on the number of interest points, the module determines the weight value corresponding to the overlapping audience user, wherein the number of interest points and the weight value are negatively correlated.

[0049] The first adjustment module is used to adjust the number of overlapping audience users according to the weight value corresponding to each overlapping audience user, so as to perform the step of determining the first circle and the second circle based on the adjusted number of overlapping audience users, with the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0050] In one possible implementation, the device further includes:

[0051] The seventh determining module is used to determine the first publication time of the first object and the second publication time of the second object after determining the overlapping audience user set between the first object and the second object;

[0052] The eighth determining module is used to determine the publication time interval between the first object and the second object based on the first publication time and the second publication time;

[0053] The second adjustment module is used to adjust the overlapping audience user set according to the release time interval, so as to perform the steps of determining the first circle and the second circle based on the number of audience users in the first audience user set as the area of ​​the first circle, the number of audience users in the second audience user set as the area of ​​the second circle, and the number of overlapping audience users in the overlapping audience user set as the overlapping area of ​​the first circle and the second circle.

[0054] Thirdly, embodiments of the present invention provide an electronic device, including: a processor and a memory, wherein the processor is configured to execute a program stored in the memory for determining the similarity between objects, to implement the method for determining the similarity between objects as described in the first aspect.

[0055] Fourthly, embodiments of the present invention provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the method for determining the similarity between objects as described in the first aspect.

[0056] The technical solution provided by this invention determines a first set of audience users for a first object and a second set of audience users for a second object. Based on the first and second set of audience users, an overlapping set of audience users between the first and second objects is determined. A first circle and a second circle are defined by the number of audience users in the first set, the number of audience users in the second set, and the number of overlapping audience users in the overlapping set. The center-to-center distance between the first and second circles is then determined, and the similarity between the first and second objects is determined based on this center-to-center distance. This technical solution establishes a first circle with the number of audience users of the first object as its area and a second circle with the number of audience users of the second object as its area. The relative positions of the first and second circles are determined based on the number of overlapping audience users. The similarity between the first and second objects is then determined based on the center-to-center distance. This method measures the similarity between the first and second objects based on their overlapping audience users, without requiring an understanding of the content itself, and can directly output a quantified content similarity based on the overlapping audience users. It avoids the limitations of determining the similarity between objects based on content tags, object file information, etc., and realizes a quantifiable determination of the similarity between objects. Attached Figure Description

[0057] Figure 1 A flowchart illustrating an embodiment of a method for determining similarity between objects provided by an embodiment of the present invention;

[0058] Figure 2 This is an example of the first and second circles;

[0059] Figure 3A This is another example of the first and second circles;

[0060] Figure 3B This is yet another example of the first and second circles;

[0061] Figure 3C This is yet another example of the first and second circles;

[0062] Figure 4 A flowchart illustrating an embodiment of another method for determining similarity between objects provided by an embodiment of the present invention;

[0063] Figure 5 A flowchart illustrating an embodiment of another method for determining the similarity between objects provided by an embodiment of the present invention;

[0064] Figure 6 A block diagram illustrating an embodiment of a device for determining the similarity between objects, provided in this invention.

[0065] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] The method for determining the similarity between objects provided by the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0068] See Figure 1 This is a flowchart illustrating an embodiment of a method for determining the similarity between objects provided by an embodiment of the present invention. Figure 1 As shown, the process may include the following steps:

[0069] Step 101: Determine the first audience user set of the first object, and determine the second audience user set of the second object.

[0070] The first object and the second object mentioned above can be two objects whose similarity is to be determined. The first object and the second object can be videos, text, or images, etc., and this embodiment of the invention does not impose any limitations on this.

[0071] The aforementioned first audience user set is the set of users who browse the aforementioned first object (hereinafter referred to as the audience users of the first object). For example, when the aforementioned first object is a video, the audience users of the first object may be logged-in users of the video playback software. Similarly, the aforementioned second audience user set is the set of users who browse the aforementioned second object (hereinafter referred to as the audience users of the second object).

[0072] In one embodiment, the executing entity of this invention can obtain the audience users of a first object from stored object browsing data and classify the audience users of the first object into a first audience user set of the first object. It can also obtain the audience users of a second object from stored object browsing data and classify the audience users of the second object into a second audience user set of the second object.

[0073] Step 102: Determine the overlapping audience set between the first object and the second object based on the first audience user set and the second audience user set.

[0074] In one embodiment, the same user may browse both the first object and the second object. That is, the user is both the audience user of the first object and the audience user of the second object. Therefore, the user mentioned above can be referred to as the overlapping audience user of the first object and the second object.

[0075] In other words, audience users who exist simultaneously in both the first and second audience user sets can be identified as overlapping audience users between the first and second objects. These overlapping audience users are then grouped into the overlapping audience user set.

[0076] As an optional implementation, it can be determined whether a user exists in both the first and second audience user sets based on the user ID (Identity document) of each audience user in the first and second audience user sets.

[0077] In another embodiment, audience users whose feature similarity between the first audience user set and the second audience user set is greater than a preset similarity threshold can be identified as overlapping audience users between the first object and the second object. Then, these overlapping audience users are grouped into an overlapping audience user set.

[0078] The feature similarity between the audience users in the first audience user set and the audience users in the second audience user set can be calculated based on the user features of the two audience users, including but not limited to: the age group of the audience users, the time when they browsed the object, and their points of interest.

[0079] As an optional implementation, for each user in the first audience user set, this audience user can be combined with each audience user in the second audience user set to obtain multiple audience user combinations. Then, for each audience user combination, the similarity between two audience users in the combination can be determined based on the user characteristics of each audience user. The two audience users in the combination whose similarity is greater than a preset similarity threshold are identified as overlapping audience users and included in the overlapping audience user set.

[0080] Step 103: Determine the first circle and the second circle by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience user groups as the overlapping area of ​​the first circle and the second circle.

[0081] Step 104: Determine the distance between the centers of the first circle and the second circle.

[0082] The following provides a unified explanation of steps 103 and 104:

[0083] In this embodiment of the invention, in order to more clearly determine the relationship between the first audience user set, the second audience user set, and the overlapping audience user set, the execution subject of this embodiment of the invention is determined by constructing a circle.

[0084] Specifically, firstly, the size of the first circle is determined by the area of ​​the first circle, which is the number of users in the first target audience group. The size of the second circle is determined by the area of ​​the second circle, which is the number of users in the second target audience group. Then, the relative positions of the first and second circles are determined by the overlapping areas of the first and second circles, which are the number of users in the overlapping target audience groups. This process establishes the first and second circles. It is understood that the terms "first circle" and "second circle" here refer to both their sizes and their relative positions.

[0085] Then, the distance between the centers of the first and second circles can be determined. Specifically, a system of equations to be solved can be constructed and solved to obtain the distance between the centers of the first and second circles.

[0086] For details, see Figure 2 This is an example of the first and second circles. For example... Figure 2 As shown in the figure, the overlapping area of ​​the first circle O1 and the second circle O2 represents the number of overlapping audience users in the overlapping audience user group. According to... Figure 2 As shown, the following system of equations (I) can be obtained:

[0087]

[0088] Among them, UV A The number of users concentrated in the primary audience, UV B The number of users concentrated in the second audience, UV AB Let r1 be the radius of the first circle, r2 be the radius of the second circle, and θ1 be half the angle between the first and second vectors. That is, as shown... Figure 2 As shown in the diagram, θ1, the first vector and the second vector both originate from the center of the first circle, and the first vector and the second vector respectively terminate at the two intersection points of the first circle and the second circle. θ2 is half the angle between the third vector and the fourth vector, that is, as shown in the diagram. Figure 2 As shown, θ2, the third vector, and the fourth vector all originate from the center of the second circle, and the third vector and the fourth vector respectively terminate at the two intersection points of the first circle and the second circle. d is the distance between the centers of the first circle and the second circle. Figure 2 The r shown.

[0089] Step 105: Determine the similarity between the first object and the second object based on the center distance.

[0090] In one embodiment, the executing entity of this invention may determine the center distance between the first circle and the second circle as the similarity between the first object and the second object.

[0091] In another embodiment, since the above-mentioned center distance is affected by the size of the first circle and the second circle (that is, the number of the first audience user group and the number of the second audience user group), the execution subject of this embodiment of the invention can input the radius of the first circle, the radius of the second circle, and the center distance into the preset similarity calculation formula shown in the following formula (II) to obtain the similarity between the first object and the second object when determining the similarity between the first object and the second object.

[0092]

[0093] Among them, S AB d represents the similarity between the first and second objects; r1 represents the radius of the first circle; and r2 represents the radius of the second circle.

[0094] From the above equation (II), we can obtain that: the execution subject of this embodiment of the invention eliminates the influence of the size of the first circle and the second circle on the similarity between the first object and the second object by dividing the center distance by the sum of the radius r1 of the first circle and the radius r2 of the second circle, thereby obtaining a more accurate similarity between the first object and the second object.

[0095] Furthermore, to verify the accuracy of the similarity between the first and second objects obtained according to the above similarity calculation formula, three exemplary application scenarios are shown below for illustration:

[0096] Application Scenario 1: If the number of users in the first target audience, the second target audience, and the overlapping target audience are all the same, then see... Figure 3A This is another example of the first and second circles. (e.g.) Figure 3A As shown, the first circle and the second circle completely overlap. Therefore, after calculation using the above similarity calculation formula, the similarity between the first object and the second object is 1.

[0097] Application Scenario 2: The number of overlapping audience users in the aforementioned overlapping audience user group is a preset threshold, for example, 0. Then, see [link to relevant information]. Figure 3B This is yet another example of the first and second circles. For example... Figure 3BAs shown, the first circle and the second circle are externally tangent. After calculation using the above similarity calculation formula, the similarity between the first object and the second object is 0.

[0098] Application Scenario 3: If the number of overlapping audience users exceeds the aforementioned threshold, then please refer to... Figure 3C This is yet another example of the first and second circles. For example... Figure 3C As shown, if the first circle and the second circle intersect or are internally tangent, then after calculation using the above similarity calculation formula, the similarity between the first object and the second object can be obtained as a decimal greater than 0 and less than 1.

[0099] The technical solution provided by this invention determines a first set of audience users for a first object and a second set of audience users for a second object. Based on the first and second set of audience users, an overlapping set of audience users between the first and second objects is determined. A first circle and a second circle are defined by the number of audience users in the first set, the number of audience users in the second set, and the number of overlapping audience users in the overlapping set. The center-to-center distance between the first and second circles is then determined, and the similarity between the first and second objects is determined based on this center-to-center distance. This technical solution establishes a first circle with the number of audience users of the first object as its area and a second circle with the number of audience users of the second object as its area. The relative positions of the first and second circles are determined based on the number of overlapping audience users. The similarity between the first and second objects is then determined based on the center-to-center distance. This method measures the similarity between the first and second objects based on their overlapping audience users, without requiring an understanding of the content itself, and can directly output a quantified object similarity based on the overlapping audience users. It avoids the limitations of determining the similarity between objects based on content tags, object file information, etc., and realizes a quantifiable determination of the similarity between objects.

[0100] See Figure 4 This is a flowchart illustrating an embodiment of another method for determining the similarity between objects provided by an embodiment of the present invention. Figure 4 As shown, the process may include the following steps:

[0101] Step 401: Determine the first audience user set of the first object, and determine the second audience user set of the second object.

[0102] Step 402: Based on the first audience user set and the second audience user set mentioned above, determine the overlapping audience user set of the first object and the second object.

[0103] Step 403: Determine the number of overlapping audience users in the above-mentioned overlapping audience user group.

[0104] For a detailed description of steps 401 to 403 above, please refer to the descriptions in steps 101 to 102, which will not be repeated here.

[0105] Step 404: For each overlapping audience user in the overlapping audience user set, determine the number of interest points of the overlapping audience user.

[0106] In an embodiment, the executing entity of this invention may determine the number of points of interest for each overlapping audience user in the overlapping audience user set.

[0107] Specifically, the browsing history of the overlapping audience users can be obtained. Based on this history, the objects browsed by these overlapping audience users can be categorized, with different categories corresponding to different interests of the overlapping audience users. Ultimately, the number of object categories obtained can be determined as the number of interests of the overlapping audience users.

[0108] Step 405: Determine the weight value corresponding to the overlapping audience users based on the number of interest points, where the number of interest points and the weight value are negatively correlated.

[0109] Step 406: Adjust the number of overlapping audience users in the overlapping audience user set according to the weight value corresponding to each overlapping audience user, and then execute step 407 based on the adjusted number of overlapping audience users.

[0110] The following provides a unified explanation of steps 405 and 406:

[0111] In practical applications, the more interests a user has, the more likely the objects they browse will correspond to different interests, resulting in lower similarity between the browsed objects. Therefore, when determining the similarity between two objects based on a user's browsing history, the user's reference value is lower, and their corresponding weight value is also lower. In other words, the number of interests and the user's corresponding weight value are negatively correlated.

[0112] In this embodiment of the invention, the weight value corresponding to each overlapping audience user can be determined according to the number of interest points of each overlapping audience user. For example, the weight value corresponding to an overlapping audience user with 10 interest points is 0.5, and the weight value corresponding to an overlapping audience user with 15 interest points is 0.3.

[0113] Then, based on the weight value corresponding to each overlapping audience user, the number of overlapping audience users in the overlapping audience user set is adjusted, and step 407 is executed based on the adjusted number of overlapping audience users.

[0114] Specifically, the weight values ​​corresponding to each overlapping audience user in the overlapping audience user set can be added together to obtain a first number, and this first number can be used as the adjusted number of overlapping audience users.

[0115] Furthermore, in this embodiment of the invention, the number of interest points for each audience user in the first audience user set and the second audience user set can be determined, and a weight value for each audience user can be determined based on the number of interest points. Then, based on the weight value of each audience user, the number of audience users in the first audience user set and the second audience user set can be adjusted, and step 407 is executed based on the adjusted number of audience users in the first audience user set, the number of audience users in the second audience user set, and the number of overlapping audience users.

[0116] Step 407: Determine the first circle and the second circle by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the adjusted overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0117] Step 408: Determine the distance between the centers of the first circle and the second circle.

[0118] Step 409: Determine the similarity between the first object and the second object based on the center distance.

[0119] For a detailed description of steps 407 to 409, please refer to the descriptions in steps 103 to 105, which will not be repeated here.

[0120] The technical solution provided by this invention further determines the number of interest points for each overlapping audience user within the overlapping audience user set. Based on the number of interest points, a weight value is determined for each overlapping audience user. The number of overlapping audience users is then adjusted based on their respective weight values. This adjusted number of overlapping audience users then forms a first circle and a second circle, thereby determining the similarity between the first object and the second object. This technical solution, by further determining the weight value of each overlapping audience user based on their number of interest points, can filter out some overlapping audience users with numerous interest points but little reference value, thus improving the accuracy of determining the similarity between the first object and the second object based on audience users.

[0121] See Figure 5 This is a flowchart illustrating another embodiment of a method for determining the similarity between objects provided by an embodiment of the present invention. Figure 5 As shown, the process may include the following steps:

[0122] Step 501: Determine the first audience user set of the first object, and determine the second audience user set of the second object.

[0123] Step 502: Determine the overlapping audience set between the first object and the second object based on the first audience user set and the second audience user set.

[0124] For a detailed description of steps 501 and 502, please refer to the descriptions in steps 101 and 102, which will not be repeated here.

[0125] Step 503: Determine the first publication time of the first object and the second publication time of the second object.

[0126] Step 504: Determine the release time interval between the first object and the second object based on the first release time and the second release time mentioned above.

[0127] The following provides a unified explanation of steps 503 and 504:

[0128] The aforementioned publication time can be the time when the object is published online. Accordingly, the aforementioned first publication time is the publication time corresponding to the aforementioned first object; the aforementioned second publication time is the publication time corresponding to the aforementioned second object.

[0129] In one embodiment, the executing entity of this invention can read the publication information corresponding to the first object and the second object respectively, and determine the publication time of the first object and the publication time of the second object based on the corresponding publication information. Then, the publication time interval between the first object and the second object can be determined based on the first publication time and the second publication time.

[0130] For example, suppose the first publication time of the first object is 12:00 noon on May 6, 2022, and the second publication time of the second object is 12:00 noon on May 8, 2022, then the publication time interval between the first object and the second object is 48 hours.

[0131] Step 505: Adjust the overlapping audience user set according to the release time interval, and then perform step 506 based on the adjusted overlapping audience user set.

[0132] In one embodiment, the executing entity of this invention may obtain historical data on the release time interval and the aforementioned overlapping audience user set from a preset database, and determine the correspondence between the release time interval and the aforementioned overlapping audience user set based on the historical data.

[0133] Based on this, the aforementioned correspondence can be found according to the publication time interval between the first object and the second object to determine the reference overlapping audience user set corresponding to the publication time interval between the first object and the second object. Then, the overlapping audience user set between the first object and the second object is adjusted according to the reference overlapping audience user set. For example, the similarity between each overlapping audience user in the aforementioned overlapping audience user set and each reference overlapping audience user in the aforementioned reference overlapping audience user set is determined, and overlapping audience users with similarity less than a preset similarity threshold are deleted, thereby adjusting the overlapping audience user set between the first object and the second object.

[0134] Then, step 506 can be performed based on the adjusted overlapping audience user set.

[0135] Step 506: Determine the first circle and the second circle by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the adjusted overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0136] Step 507: Determine the distance between the centers of the first circle and the second circle.

[0137] Step 508: Determine the similarity between the first object and the second object based on the center distance.

[0138] For a detailed description of steps 506 to 508, please refer to the descriptions in steps 103 to 105, which will not be repeated here.

[0139] The technical solution provided by this invention further determines the first publication time of a first object and the second publication time of a second object, determines the publication time interval between the first object and the second object, and adjusts the overlapping audience user set according to the publication time interval, so as to determine the similarity between the first object and the second object based on the adjusted overlapping audience user set. This technical solution, by adjusting the overlapping audience user set of the two objects according to the publication time interval, can eliminate the influence of different publication times on the overlapping audience user set, thereby affecting the accuracy of the similarity between the first object and the second object. This improves the accuracy of determining the similarity between the first object and the second object based on the audience user.

[0140] See Figure 6 This is a block diagram illustrating an embodiment of a device for determining the similarity between objects, provided by an embodiment of the present invention. Figure 6 As shown, the device includes:

[0141] The first determining module 61 is used to determine the first audience user set of the first object and the second audience user set of the second object;

[0142] The second determining module 62 is used to determine the overlapping audience set between the first object and the second object based on the first audience set and the second audience set;

[0143] The third determining module 63 is used to determine the first circle and the second circle by taking the number of the first audience users as the area of ​​the first circle, the number of the second audience users as the area of ​​the second circle, and the number of the overlapping audience users as the overlapping area of ​​the first circle and the second circle.

[0144] The fourth determining module 64 is used to determine the center distance between the first circle and the second circle;

[0145] The fifth determining module 65 is used to determine the similarity between the first object and the second object based on the center distance.

[0146] In one possible implementation, the second determining module 62 is specifically used for:

[0147] Audience users who exist simultaneously in both the first audience user set and the second audience user set are identified as overlapping audience users between the first object and the second object; or, audience users whose feature similarity between the first audience user set and the second audience user set is greater than a preset similarity threshold are identified as overlapping audience users between the first object and the second object.

[0148] The overlapping audience users are grouped into the overlapping audience user set.

[0149] In one possible implementation, the fourth determining module 64 is specifically used for:

[0150] The following system of equations is constructed and solved to obtain the distance between the centers of the first circle and the second circle:

[0151]

[0152] Wherein, the UV A The number of users in the first target audience group, the UV B The number of users in the second target audience group, the UV ABThe number of overlapping audience users in the overlapping audience user set, r1 is the radius of the first circle, r2 is the radius of the second circle, θ1 is half the angle between the first vector and the second vector, the first vector and the second vector both start from the center of the first circle, and the first vector and the second vector each end at the two intersection points of the first circle and the second circle, respectively, θ2 is half the angle between the third vector and the fourth vector, the third vector and the fourth vector both start from the center of the second circle, and the third vector and the fourth vector each end at the two intersection points of the first circle and the second circle, respectively, and d is the distance between the centers of the first circle and the second circle.

[0153] In one possible implementation, the fifth determining module 65 is specifically used for:

[0154] The radius of the first circle, the radius of the second circle, and the distance between their centers are input into a preset similarity calculation formula to obtain the similarity between the first object and the second object. The similarity calculation formula is as follows:

[0155]

[0156] Wherein, the S AB The similarity between the first object and the second object is denoted by d; the center distance of the circles is d; r1 is the radius of the first circle and r2 is the radius of the second circle.

[0157] In one possible implementation, the device further includes (not shown in the figure):

[0158] The sixth determining module is used to determine the area of ​​a first circle (based on the number of users in the first audience user set), the area of ​​a second circle (based on the number of users in the second audience user set), and the overlapping area of ​​the first and second circles (based on the number of overlapping users in the overlapping audience user set) before determining the first and second circles. Specifically, for each overlapping audience user in the overlapping audience user set, the module determines the number of interest points for that overlapping audience user. Based on the number of interest points, the module determines the weight value corresponding to the overlapping audience user, wherein the number of interest points and the weight value are negatively correlated.

[0159] The first adjustment module is used to adjust the number of overlapping audience users according to the weight value corresponding to each overlapping audience user, so as to perform the step of determining the first circle and the second circle based on the adjusted number of overlapping audience users, with the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0160] In one possible implementation, the device further includes (not shown in the figure):

[0161] The seventh determining module is used to determine the first publication time of the first object and the second publication time of the second object after determining the overlapping audience user set between the first object and the second object;

[0162] The eighth determining module is used to determine the publication time interval between the first object and the second object based on the first publication time and the second publication time;

[0163] The second adjustment module is used to adjust the overlapping audience user set according to the release time interval, so as to perform the steps of determining the first circle and the second circle based on the number of audience users in the first audience user set as the area of ​​the first circle, the number of audience users in the second audience user set as the area of ​​the second circle, and the number of overlapping audience users in the overlapping audience user set as the overlapping area of ​​the first circle and the second circle.

[0164] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 7 The illustrated electronic device 700 includes at least one processor 701, a memory 702, at least one network interface 704, and a user interface 703. The various components in the electronic device 700 are coupled together via a bus system 705. It is understood that the bus system 705 is used to implement communication between these components. In addition to a data bus, the bus system 705 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 7 The general labeled all buses as Bus System 705.

[0165] The user interface 703 may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).

[0166] It is understood that the memory 702 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 702 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0167] In some implementations, memory 702 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 7021 and application program 7022.

[0168] The operating system 7021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 7022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 7022.

[0169] In this embodiment of the invention, by calling the program or instructions stored in the memory 702, specifically the program or instructions stored in the application program 7022, the processor 701 executes the method steps provided in each method embodiment, including, for example:

[0170] Determine the first audience set for the first object, and determine the second audience set for the second object;

[0171] Based on the first audience user set and the second audience user set, determine the overlapping audience user set between the first object and the second object;

[0172] The first circle and the second circle are determined by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0173] Determine the center distance between the first circle and the second circle;

[0174] The similarity between the first object and the second object is determined based on the center distance.

[0175] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 701. Processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 701 or by instructions in software form. The processor 701 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 702. Processor 701 reads the information in memory 702 and, in conjunction with its hardware, completes the steps of the above method.

[0176] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0177] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0178] The electronic device provided in this embodiment may be as follows: Figure 7 The electronic device shown can perform the following: Figure 1 , Figure 4-5 All steps of the method for determining similarity between objects, thereby achieving Figure 1 , Figure 4-5 For details on the technical effectiveness of the method for determining similarity between objects, please refer to [link / reference needed]. Figure 1 , Figure 4-5 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0179] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; the memory may also include combinations of the above types of memory.

[0180] When one or more programs in a storage medium can be executed by one or more processors to achieve the method described above for determining the similarity between objects executed on the electronic device side.

[0181] The processor is configured to execute a program stored in memory for determining the similarity between objects, to implement the following steps of a method for determining the similarity between objects executed on the electronic device side:

[0182] Determine the first audience set for the first object, and determine the second audience set for the second object;

[0183] Based on the first audience user set and the second audience user set, determine the overlapping audience user set between the first object and the second object;

[0184] The first circle and the second circle are determined by taking the number of the first audience user group as the area of ​​the first circle, the number of the second audience user group as the area of ​​the second circle, and the number of the overlapping audience users in the overlapping audience user group as the overlapping area of ​​the first circle and the second circle.

[0185] Determine the center distance between the first circle and the second circle;

[0186] The similarity between the first object and the second object is determined based on the center distance.

[0187] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0188] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0189] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method of determining similarity between objects, characterized by, The method comprises: determining a first audience user set of a first object and a second audience user set of a second object; determining an overlapping audience user set between the first object and the second object according to the first audience user set and the second audience user set; determining the first circle and the second circle according to the number of audience users in the first audience user set as the circular area of the first circle, the number of audience users in the second audience user set as the circular area of the second circle, and the number of overlapping audience users in the overlapping audience user set as the overlapping area of the first circle and the second circle; determining the center distance of the first circle and the second circle when the relative position relationship of the first circle and the second circle is complete coincidence, tangency or intersection; determining the similarity between the first object and the second object according to the center distance.

2. The method of claim 1, wherein, The determining of the overlapping audience user set between the first object and the second object according to the first audience user set and the second audience user set comprises: determining the audience users existing in the first audience user set and the second audience user set at the same time as the overlapping audience users between the first object and the second object, or determining the audience users in the first audience user set and the second audience user set with a feature similarity greater than a preset similarity threshold as the overlapping audience users between the first object and the second object; classifying the overlapping audience users into an overlapping audience user set.

3. The method of claim 1, wherein, The determining of the center distance of the first circle and the second circle when the relative position relationship of the first circle and the second circle is intersection comprises: constructing the following equation group to be solved and solving the equation group to be solved to obtain the center distance of the first circle and the second circle: wherein the is the number of audience users in the first set of audience users, the is the number of audience users in the second set of audience users, the is the number of overlapping audience users in the overlapping set of audience users, the is the radius of the first circle, the is the radius of the second circle, the is half of the angle between a first vector and a second vector, the first vector and the second vector both originating at the center of the first circle, and the first vector and the second vector both terminating at the two intersection points of the first circle and the second circle, the is half of the angle between a third vector and a fourth vector, the third vector and the fourth vector both originating at the center of the second circle, and the third vector and the fourth vector both terminating at the two intersection points of the first circle and the second circle, the is the distance between the centers of the first circle and the second circle.

4. The method of claim 3, wherein, The determining of the similarity between the first object and the second object according to the center distance comprises: inputting the radius of the first circle, the radius of the second circle and the center distance into a preset similarity calculation formula to obtain the similarity between the first object and the second object, and the similarity calculation formula is: Among them, the The similarity between the first object and the second object; The distance between the centers of the circles; The radius of the first circle, the Let be the radius of the second circle.

5. The method of claim 1, wherein, Before the determining of the first circle and the second circle according to the number of audience users in the first audience user set as the circular area of the first circle, the number of audience users in the second audience user set as the circular area of the second circle, and the number of overlapping audience users in the overlapping audience user set as the overlapping area of the first circle and the second circle, the method further comprises: determining the number of interest points of each overlapping audience user in the overlapping audience user set, and determining the weight value corresponding to the overlapping audience user according to the number of interest points, wherein the number of interest points and the weight value are negatively correlated. According to the weight value corresponding to each of the overlapping audience users, the number of the overlapping audience users is adjusted, so that the first circle and the second circle are determined according to the number of the overlapping audience users after the adjustment.

6. The method of claim 1, wherein, After the set of overlapping audience users between the first object and the second object is determined, the method further includes: determining a first publishing time of the first object and a second publishing time of the second object; determining a publishing time interval between the first object and the second object according to the first publishing time and the second publishing time; adjusting the set of overlapping audience users according to the publishing time interval, so that the first circle and the second circle are determined according to the set of overlapping audience users after the adjustment.

7. An apparatus for determining similarity between objects, the apparatus comprising: The apparatus includes: a first determining module configured to determine a first set of audience users of a first object and determine a second set of audience users of a second object; a second determining module configured to determine a set of overlapping audience users between the first object and the second object according to the first set of audience users and the second set of audience users; a third determining module configured to determine a first circle and a second circle according to a circle area of the first circle with a number of audience users in the first set of audience users, a circle area of the second circle with a number of audience users in the second set of audience users, and an overlapping area of the first circle and the second circle with a number of overlapping audience users in the set of overlapping audience users; a fourth determining module configured to determine a center distance of the first circle and the second circle when a relative position relationship of the first circle and the second circle is one of complete coincidence, tangency or intersection; a fifth determining module configured to determine a similarity between the first object and the second object according to the center distance.

8. The apparatus of claim 7, wherein, The second determining module is specifically configured to: determine audience users existing in both the first set of audience users and the second set of audience users as the set of overlapping audience users between the first object and the second object, or determine audience users in the first set of audience users with a feature similarity greater than a preset similarity threshold in the second set of audience users as the set of overlapping audience users between the first object and the second object; group the set of overlapping audience users.

9. An electronic device, comprising: The apparatus includes: A processor and a memory, the processor being configured to execute a program stored in the memory for determining the similarity between objects to implement the method for determining the similarity between objects according to any one of claims 1-6.

10. A storage medium, characterized by The storage medium stores one or more programs, and the one or more programs are executable by one or more processors to implement the method for determining the similarity between objects according to any one of claims 1-6.

Images