Social network construction method and system based on life service consumption scenario

Abstract

A method and device for constructing a social network based on a life service consumption scenario, by constructing a user object and a life service object, the user object includes a preset user node; creating a first link expression between preset user nodes; constructing a second link expression for a specified user node and a life service object; calculating the intimacy of the user nodes contained in the user object in the social network based on the commonly associated life service objects; and determining the sorting priority of the life service objects recommended to the user node according to the recommendation score of the life service object. The present invention is not only centered on a single user, but also considers the user as a whole in the social network node, calculates the intimacy function of the target user node and the surrounding user nodes, and then intelligently recommends the services that the target user is interested in based on the collaborative filtering of the social network, so that it can be guaranteed that the recommendation is not only a service that the target user likes, but also a service that he or she empathizes with and shares with his or her common friends.

Description

Technical Field

[0001] The present invention belongs to the technical field of consumption data processing, and specifically relates to a social network construction method and system based on life service consumption scenarios. Background Art

[0002] At present, the development of mobile payment and mobile Internet has profoundly changed the way users consume offline life services. The DNA of future business is network collaboration and data intelligence. The world's most valuable Internet companies all present a "double helix" of the two. Google's two core values ​​are: precise advertising technology (data intelligence) and a huge advertising alliance (network collaboration). Taobao's value comes from the retail network of buyers, sellers and other third-party roles (network collaboration), as well as the search and recommendation engine behind it (data intelligence). Leading companies are either strong in data intelligence or strong in network collaboration. If a company does not have a qualitative breakthrough in either data or network, it will inevitably have no room for survival in the new round of competition.

[0003] Recommendation algorithm is a kind of algorithm in computer science that can infer what users may like. At present, the application of recommendation algorithm is mainly in the Internet, among which Taobao is relatively good. The so-called recommendation algorithm is to use some user behaviors and some mathematical algorithms to infer what users may like.

[0004] The recommendation algorithm based on collaborative filtering is one of the earliest and most successful technologies used in recommendation systems. It generally uses the nearest neighbor technology, uses the user's historical preference information to calculate the distance between users, and then uses the weighted evaluation value of the target user's nearest neighbor users on the product to predict the target user's preference for a specific product, so as to recommend the target user based on this preference. The biggest advantage of the recommendation algorithm based on collaborative filtering is that it has no special requirements for the recommended object and can handle unstructured complex objects, such as music, movies, etc.

[0005] The demand for offline life services such as eating, drinking, and playing is essentially a social demand. The centralized life service e-commerce platform uses machine learning and intelligent recommendation algorithms by tagging users, which is overly focused on individual users. It cannot accurately and efficiently determine which food, drink, and play service categories are the most empathetic and frequent for target users and their friends. It cannot cope with different life service scenarios in reality and cannot meet users' complex consumption needs. Summary of the invention

[0006] To this end, the present invention provides a social network construction method and system based on life service consumption scenarios, which is not only centered on a single user, but also considers the user as a whole in the social network node, which can ensure that the recommended services are not only the target user's favorite services, but also the services that they empathize with and share with their common friends.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for constructing a social network based on a life service consumption scenario, comprising the following steps:

[0008] Constructing a user object C and a life service object S, wherein the user object C includes a preset user node;

[0009] Creating a preset first link expression C(X, R) between the user nodes, where X in the first link expression is the total number of users linked to the specified user node in the social network, and R in the first link expression is the total frequency of the specified user node interacting with the remaining user nodes in the social network;

[0010] Construct the second link expression C that specifies the user node and the life service object S s (Y, L), where Y in the second link expression is the total number of life service objects linked to the specified user node in the social network, and L in the second link expression is the total frequency of interaction of the specified user node with the linked life service objects;

[0011] Calculate the intimacy of the user nodes contained in the user object C in the social network based on the commonly associated life service objects S;

[0012] According to the recommendation score L of the life service object S, the sorting priority of the life service object S recommended to the user node is determined.

[0013] As a preferred solution of the social network construction method based on the life service consumption scenario, the total intimacy of the user nodes contained in the user object C based on the commonly associated life service objects S in the social network is calculated: K C1-C2 =a(e+j) d+1 +ah;

[0014] Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters;

[0015] e: the number of friend nodes associated with user nodes C1 and C2 in user object C;

[0016] j: the number of service nodes commonly associated with user nodes C1 and C2 in user object C;

[0017] h: user activity correlation constant between user nodes C1 and C2 in user object C;

[0018] a: The common frequency constant between user nodes C1 and C2 in user object C.

[0019] As a preferred solution of the social network construction method based on the life service consumption scenario, the common frequency constant between user nodes C1 and C2 in user object C is: a=R e +L j ;

[0020] In the formula, R e is the sum of the interaction frequencies between user nodes C1 and C2 in user object C and their common friends;

[0021] L j It is the sum of the frequencies of interactions between user nodes C1 and C2 in user object C and the commonly associated life service objects.

[0022] As a preferred solution for the social network construction method based on the life service consumption scenario, when it is impossible to accurately obtain whether the user nodes C1 and C2 in the user object C have common friends:

[0023] The total intimacy of the user nodes contained in the user object C based on the commonly associated life service object S in the social network: K C1-C2 =aj d+1 +ah;

[0024] Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters;

[0025] j: the number of service nodes commonly associated with user nodes C1 and C2 in user object C;

[0026] h: user activity correlation constant between user nodes C1 and C2 in user object C;

[0027] a: The common frequency constant between user nodes C1 and C2 in user object C.

[0028] As a preferred solution of the social network construction method based on the life service consumption scenario, the intimacy of the user node contained in the user object C based on the commonly associated single life service object S in the social network is calculated: K C1-C2 =a(e+1) d+1 +ah;

[0029] Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters;

[0030] e: the number of friend nodes associated with user nodes C1 and C2 in user object C;

[0031] h: user activity correlation constant between user nodes C1 and C2 in user object C;

[0032] a: The common frequency constant between user nodes C1 and C2 in user object C.

[0033] As a preferred solution of the social network construction method based on the life service consumption scenario, the common frequency constant between user nodes C1 and C2 in user object C is: a=R e +L1;

[0034] In the formula, R e is the sum of the interaction frequencies between user nodes C1 and C2 in user object C and their common friends;

[0035] L1 is the total frequency of interactions between user nodes C1 and C2 in user object C and a single life service object associated with the social network.

[0036] As a preferred solution of the social network construction method based on the life service consumption scenario, the calculation formula of the recommendation score L of the life service object S is: L = m + 10n + 50f + 60u + 70v + 90w;

[0037] Among them, m: click; n: browse; f: help; u: collection; v: pending payment; w: purchase.

[0038] As a preferred solution of the social network construction method based on the life service consumption scenario, the activity of user object C in the social network of the life service consumption scenario is: H C =X×R+Y×L.

[0039] As a preferred solution of the social network construction method based on the life service consumption scenario, when the activity of user nodes C1 and C2 in user object C is greater than the overall average, the maximum activity of user nodes C1 and C2 is taken;

[0040] When the activity of user nodes C1 and C2 in user object C is less than the overall average, take the minimum value of the activity of user nodes C1 and C2;

[0041] When one or more of the activities of user nodes C1 and C2 in user object C is less than the overall average, the average of the activities of C1 and C2 is taken.

[0042] The present invention also provides a social network construction device based on a life service consumption scenario, which adopts the above-mentioned social network construction method based on a life service consumption scenario, including:

[0043] An object construction module, used to construct a user object C and a life service object S, wherein the user object C includes a preset user node;

[0044] A first link expression module, used to create a preset first link expression C(X, R) between the user nodes, where X in the first link expression is the total number of users linked to the specified user node in the social network, and R in the first link expression is the total frequency of the specified user node interacting with the remaining user nodes in the social network;

[0045] The second link expression module is used to construct a second link expression C for specifying a user node and a life service object S. s (Y, L), where Y in the second link expression is the total number of life service objects linked to the specified user node in the social network, and L in the second link expression is the total frequency of interaction of the specified user node with the linked life service objects;

[0046] An intimacy calculation module, used to calculate the intimacy of the user nodes included in the user object C based on the commonly associated life service objects S in the social network;

[0047] The recommendation processing module is used to determine the sorting priority of the life service object S recommended to the user node according to the recommendation score L of the life service object S.

[0048] The present invention has the following advantages: by constructing user objects and life service objects, the user objects include preset user nodes; creating a first link expression between preset user nodes; constructing a second link expression that specifies user nodes and life service objects; calculating the intimacy of user nodes included in the user object in a social network based on commonly associated life service objects; and determining the sorting priority of life service objects recommended to user nodes according to the recommendation scores of the life service objects. The present invention is not only centered on a single user, but also considers the user as a whole in the social network node, calculates the intimacy function between the target user node and the surrounding user nodes, and then intelligently recommends services that the target user is interested in based on social network collaborative filtering. Therefore, it can be guaranteed that the recommendation is not only a service that the target user likes, but also a service that he or she and his or her common friends empathize with and share the same frequency with. Compared with traditional centralized labeling recommendations, the present invention can filter information that is difficult to perform automatic machine content analysis, such as artwork, music, movies, food, etc.; it shares other people's experiences, avoids incomplete and imprecise content analysis, and can filter based on some complex and difficult-to-express concepts (such as information quality, personal taste); it has the ability to recommend new information; it can discover information that is completely dissimilar in content, and users cannot anticipate the content of recommended information in advance; it can effectively use feedback information from other similar users, reduce the amount of user feedback, and speed up personalized learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0050] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0051] Figure 1 A schematic diagram of a method for constructing a social network based on a life service consumption scenario provided in Example 1 of the present invention;

[0052] Figure 2 The user object relationship model in the social network construction method based on the life service consumption scenario provided in Example 1 of the present invention;

[0053] Figure 3 A relationship model between user objects and life service objects in the social network construction method based on the life service consumption scenario provided in Example 1 of the present invention;

[0054] Figure 4 A schematic diagram of an intimacy model in a social network construction method based on a life service consumption scenario provided in Example 1 of the present invention;

[0055] Figure 5 A schematic diagram of an activity model in a social network construction method based on a life service consumption scenario provided in Example 1 of the present invention;

[0056] Figure 6 This is a schematic diagram of a device for building a social network based on a life service consumption scenario provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0057] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] See also Figure 1 , Figure 2 , Figure 3 and Figure 4 , a method for building a social network based on a life service consumption scenario is provided, comprising the following steps:

[0060] S1. Construct a user object C and a life service object S, wherein the user object C includes a preset user node;

[0061] S2. Create a preset first link expression C(X, R) between the user nodes, where X in the first link expression is the total number of users linked to the specified user node in the social network, and R in the first link expression is the total frequency of the specified user node interacting with the remaining user nodes in the social network;

[0062] S3. Construct a second link expression C specifying the user node and the life service object S. s (Y, L), where Y in the second link expression is the total number of life service objects linked to the specified user node in the social network, and L in the second link expression is the total frequency of interaction of the specified user node with the linked life service objects;

[0063] S4, calculating the intimacy of the user nodes included in the user object C in the social network based on the commonly associated life service objects S;

[0064] S5. Determine the sorting priority of the life service object S recommended to the user node according to the recommendation score L of the life service object S.

[0065] See also Figure 2 In this embodiment, taking the user nodes C1 and C2 included in the user object C as an example, the link expression between the user nodes C1 and C2 is: 1-2 (X 1-2 , R 1-2 ), X 1-2 is the link count (black line number) between user nodes C1 and C2, which is always equal to 1. 1-2 is the interaction frequency between user nodes C1 and C2 (the thickness of the black line).

[0066] See also Figure 3 In this embodiment, the circle represents the user object, the triangle represents the life service object, and the link expression between a user object C and a life service object S is: C s (Y c-s , L c-s ), Y c-s is the count of the links between a user object C and a life service object S (the number of dotted lines), which is always equal to 1. c-sIt is the interaction frequency between user object C and a life service object S (the thickness of the dotted line).

[0067] In this embodiment, the total intimacy of the user nodes included in the user object C based on the commonly associated life service objects S in the social network is calculated: K C1-C2 =a(e+j) d+1 +ah;

[0068] Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters;

[0069] e: the number of friend nodes associated with user nodes C1 and C2 in user object C;

[0070] j: the number of service nodes commonly associated with user nodes C1 and C2 in user object C;

[0071] h: user activity correlation constant between user nodes C1 and C2 in user object C;

[0072] a: The common frequency constant between user nodes C1 and C2 in user object C.

[0073] Specifically, the common frequency constant between user nodes C1 and C2 in user object C is: a = R e +L j ;

[0074] In the formula, R e is the sum of the interaction frequencies between user nodes C1 and C2 in user object C and their common friends;

[0075] L j is the sum of the frequencies of interactions between user nodes C1 and C2 in user object C and the commonly associated life service objects, L j =sum(l C1-s1 :l C1-sj )+sum(l C2-s1 :l C2-sj ).

[0076] In this embodiment, when it is impossible to accurately obtain whether the user nodes C1 and C2 in the user object C have common friends:

[0077] The total intimacy of the user nodes contained in the user object C based on the commonly associated life service object S in the social network: K C1-C2 =aj d+1 +ah;

[0078] Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters;

[0079] j: the number of service nodes commonly associated with user nodes C1 and C2 in user object C;

[0080] h: user activity correlation constant between user nodes C1 and C2 in user object C;

[0081] a: the common frequency constant between user nodes C1 and C2 in user object C, a=L j At this time, the intimacy between user nodes C1 and C2 based on a certain S1 in the involved network (calculated only when d>3): K C1-s1-C2 =(l C1-s1 +l C2-s1 ) d+1 +h d .

[0082] In this embodiment, the intimacy of the user nodes contained in the user object C based on the commonly associated single life service object S in the social network is calculated: K C1-C2 =a(e+1) d+1 +ah;

[0083] Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters;

[0084] e: the number of friend nodes associated with user nodes C1 and C2 in user object C;

[0085] h: user activity correlation constant between user nodes C1 and C2 in user object C;

[0086] a: The common frequency constant between user nodes C1 and C2 in user object C.

[0087] Specifically, the common frequency constant between user nodes C1 and C2 in user object C is: a = R e +L1;

[0088] In the formula, R e is the sum of the interaction frequencies between user nodes C1 and C2 in user object C and their common friends;

[0089] L1 is the total frequency of interactions between user nodes C1 and C2 in user object C and a single life service object associated with the social network.

[0090] In this embodiment, the calculation formula of the recommendation score L of the life service object S is: L=m+10n+50f+60u+70v+90w;

[0091] Among them, m: click; n: browse; f: help; u: collection; v: pending payment; w: purchase.

[0092] Specifically, the set S of life service objects S associated with the user node C1 C1 = Enum(Y), Enum() is an enumeration function. The essential difference from the recommendation ranking of centralized e-commerce platforms is that S C1 Different from the present invention, S C1 It is a life service object S associated with friend interaction.

[0093] See also Figure 5 In this embodiment, the activity of user object C in the social network of the life service consumption scenario is: H C =X×R+Y×L. When the activity of user nodes C1 and C2 in user object C is greater than the overall average, the maximum activity of user nodes C1 and C2 is taken;

[0094] When the activity of user nodes C1 and C2 in user object C is less than the overall average, take the minimum value of the activity of user nodes C1 and C2;

[0095] When one or more of the activities of user nodes C1 and C2 in user object C is less than the overall average, the average of the activities of C1 and C2 is taken.

[0096] Based on the technical solution of the present invention, algorithm simulation is performed to construct user objects: user C(X,R), C1 / C2 / C3...C n , the following algorithm simulates the situation of only three users: C1, C2, C3; construct life service object S(Y,L), S1 / S2 / S3...S n ,The following can simulate n (n>3) life service SKUs (a product, each model has a SKU to facilitate e-commerce brands to identify products).

[0097] Initialization (taking n=60 as an example):

[0098] 1. Cycle reading of C1 and S1 / S2 / S3...S 60 Initialization parameters between (Yc-s, Lc-s)

[0099] Example: C1:S1(Y 1-1 ,L 1-1) 、C1:S2(Y 1-2 ,L 1-2 )、C2:S1(Y 2-1 ,L 2-1 )...

[0100] L=m+10*n+50*f+60*u+70*v+90*w

[0101] When L=0, Y is always equal to 0. When L>0, Y is always equal to 1.

[0102] 2. Please input: m = ?; n = ?; f = ?; u = ?; v = ?; w = ?. "?" represents the input value. Input 180 times in a loop, which is S1-S 60 Assignment. Read C1.txt, C2.txt, and user initialization data in C2.txt.

[0103] Initialization completed.

[0104] 4. Find the set S of S associated with C1 C1 , which is the set of all S in Y1-60 where Y>0. For example (S1, S8, S9, S 17 ,S 60 ).

[0105] 5. Find the set S of S associated with C2 C2 , which is the set of all S in Y2-60 where Y>0. For example (S1, S8, S 11 ,S 25 ,S 60 ).

[0106] 6. Find the set S of S associated with C3 c3 , which is the set of all S in Y3-60 where Y>0. For example (S2, S8, S 21 ,S 25 ,S 60 ).

[0107] 7. Find S1, which is S C1 &S C2 &S c3 Intersection, for example (S8,S 60 ).

[0108] 8. Find S2, which is S C1 &S C2 Remove S1 from the intersection of .

[0109] 9. Find S3, which is S C1 &S c3 Remove S1 from the intersection of . 。

[0110] 10. Find S4, which is S C1 Remove S1+S2+S3 from the equation.

[0111] 11. Find S5, which is S C2 &S c3 Remove S1 from the intersection of .

[0112] 12, find S6, which is S C2 Remove S1+S2+S5 from the equation.

[0113] 13. Find S7, which is S c3 Remove S1+S3+S5 from the equation.

[0114] 14. Please enter the recommended object C=?; "?" represents the input value. For example, C=1 means intelligent recommendation for C1.

[0115] 14-1, find the intimacy function between C1 and C2, K C1-C2 =a(e+j) d+1 +h;

[0116] 14-1-1:

[0117] Please input d=?: space-time correlation constant, “?” represents the input value, the number of times the absolute distance between C1 and C2 is less than or equal to 15 meters.

[0118] 14-1-2:

[0119] e=1: The number of friend nodes that C1 and C2 are associated with. It is always equal to 1.

[0120] 14-1-3:

[0121] Calculate j: The number of service nodes commonly associated with C1 and C2, which is the number of elements S in the set S1+S2.

[0122] 14-1-4:

[0123] Calculate h: the correlation constant between user activity of C1 and C2;

[0124] The activity of user C1 in the social network of life service consumption scenarios, that is, measuring the correlation between C1 and all users and all services involved in the network.

[0125] H C1 =X1*R+Y1*L1

[0126] At this time, X1=x 1-1 +x 1-2 ; R = r 1-2 +r 1-3 .X1=2,R=2;

[0127] Y1=Y 1_1 +Y 1_2 +...Y 1_60 ; L1=L 1_1 +L 1_2. ..+L 1_60 ;

[0128] Similarly, calculate H C2 .

[0129] C1 and C2 user activity correlation constant h: h = (HC MAX , HC MIN , HC AVG );

[0130] When the activity of C1 and C2 is greater than the overall average, take the maximum value of C1 and C2. When the activity of C1 and C2 is less than the overall average, take the minimum value of C1 and C2. When one and only one of the activity of C1 and C2 is less than the overall average, take the average of C1 and C2.

[0131] 14-1-5:

[0132] Calculate a: The common frequency constant between C1 and C2: a = R e +L j ;

[0133] Re: The total frequency of interactions between C1 and C2 and their common friends. At this time, Re = 2;

[0134] L j : The sum of the frequencies of interactions between C1 and C2 and their commonly associated services.

[0135] That is, the sum of L of all elements S in the set S1+S2.

[0136] 14-1-6, same as above, find the intimacy function between C1 and C3, K C1-c3 =a(e+j) d+1 +ah.

[0137] 14-1-7, same as above, find the intimacy function between C2 and C3, K C2-c3 =a(e+j) d+1 +ah.

[0138] 14-1-8, against K C1-c3 ; K C2-c3 ; K C2-c3 Sort by size.

[0139] 14-1-9, determine the priority order of the S1, S2, S3...S7 sets.

[0140] For example, K C1-C2 >K C2-c3 >K C1-c3 Then S1>S2>S3>S4>S5>S6>S7.

[0141] 15. Recommendations for C1:

[0142] 15-1: First recommend S in S1 and sort them in descending order of priority. Output the recommendation results. For example, S1(S8,S60 ), where S8(Y 1-8 ,L 1-8 ),S 60( Y 1-60 ,L 1-60 ), the result is S8(1,9); S 60 (1,12). The output is: S 60 ; S8.

[0143] 15-2: Recommend S in S2 and sort them in descending order of priority. Output the recommendation results. ...

[0145] 15-7: Recommend S in S7 and sort them in descending order of priority. Output the recommendation results.

[0146] 16,The total result of the recommendation for C1 is the set of 15-1....15-7.

[0147] All S recommendations completed.

[0148] To summarize, the present invention constructs user objects and life service objects, wherein the user objects include preset user nodes; creates a first link expression between preset user nodes; constructs a second link expression that specifies user nodes and life service objects; calculates the intimacy of user nodes included in the user objects in a social network based on commonly associated life service objects; and determines the sorting priority of life service objects recommended to user nodes based on the recommendation scores of the life service objects. The present invention is not only centered on a single user, but also considers the user as a whole in the social network node, calculates the intimacy function between the target user node and the surrounding user nodes, and then intelligently recommends services that the target user is interested in based on social network collaborative filtering. Therefore, it can be guaranteed that the recommendation is not only a service that the target user likes, but also a service that he or she and his or her common friends empathize with and share the same frequency with. Compared with traditional centralized labeling recommendations, the present invention can filter information that is difficult to perform automatic machine content analysis, such as artwork, music, movies, food, etc.; it shares other people's experiences, avoids incomplete and imprecise content analysis, and can filter based on some complex and difficult-to-express concepts (such as information quality, personal taste); it has the ability to recommend new information; it can discover information that is completely dissimilar in content, and users cannot anticipate the content of recommended information in advance; it can effectively use feedback information from other similar users, reduce the amount of user feedback, and speed up personalized learning.

[0149] Example 2

[0150] See also Figure 6Embodiment 2 of the present invention further provides a device for constructing a social network based on a life service consumption scenario, and adopts a method for constructing a social network based on a life service consumption scenario of Embodiment 1 or any possible implementation thereof, including:

[0151] Object construction module 1, used to construct user object C and life service object S, wherein the user object C includes a preset user node;

[0152] A first link expression module 2, used to create a preset first link expression C (X, R) between the user nodes, where X in the first link expression is the total number of users linked to the specified user node in the social network, and R in the first link expression is the total frequency of the specified user node interacting with the remaining user nodes in the social network;

[0153] The second link expression module 3 is used to construct a second link expression C for specifying a user node and a life service object S. s (Y, L), where Y in the second link expression is the total number of life service objects linked to the specified user node in the social network, and L in the second link expression is the total frequency of interaction of the specified user node with the linked life service objects;

[0154] The intimacy calculation module 4 is used to calculate the intimacy of the user nodes included in the user object C based on the commonly associated life service objects S in the social network;

[0155] The recommendation processing module 5 is used to determine the sorting priority of the life service object S recommended to the user node according to the recommendation score L of the life service object S.

[0156] It should be noted that the information interaction, execution process, etc. between the modules / units of the above-mentioned device are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown in the previous part of the present application, and will not be repeated here.

[0157] Example 3

[0158] Embodiment 3 of the present invention provides a computer-readable storage medium, in which a program code for a method for building a social network based on a life service consumption scenario is stored. The program code includes instructions for executing embodiment 1 or any possible implementation method of the method for building a social network based on a life service consumption scenario.

[0159] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0160] Example 4

[0161] Embodiment 4 of the present invention provides an electronic device, comprising a processor, wherein the processor is coupled to a storage medium. When the processor executes instructions in the storage medium, the electronic device executes the social network construction method based on life service consumption scenarios of embodiment 1 or any possible implementation thereof.

[0162] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0163] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0164] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0165] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for constructing a social network based on life service consumption scenarios, characterized in that: The following steps are involved: Constructing a user object C and a life service object S, wherein the user object C includes a preset user node; Creating a preset first link expression C(X, R) between the user nodes, where X in the first link expression is the total number of users linked to the specified user node in the social network, and R in the first link expression is the total frequency of the specified user node interacting with the remaining user nodes in the social network; Construct the second link expression C that specifies the user node and the life service object S s (Y, L), where Y in the second link expression is the total number of life service objects linked to the specified user node in the social network, and L in the second link expression is the total frequency of interactions of the specified user node with the linked life service objects; Calculate the intimacy of the user nodes contained in the user object C in the social network based on the commonly associated life service objects S; Determine the sorting priority of the life service object S recommended to the user node according to the recommendation score L of the life service object S; Calculate the total intimacy of the user nodes contained in the user object C based on the commonly associated life service objects S in the social network: K C1-C2 =a(e+j) d+1 +ah; Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters; e: the number of friend nodes associated with user nodes C1 and C2 in user object C; j: the number of service nodes commonly associated with user nodes C1 and C2 in user object C; h: user activity correlation constant between user nodes C1 and C2 in user object C; a: The common frequency constant between user nodes C1 and C2 in user object C.

2. The method for constructing a social network based on life service consumption scenarios according to claim 1, characterized in that: The common frequency constant between user nodes C1 and C2 in user object C: a=R e +L j ; In the formula, R e is the sum of the interaction frequencies between user nodes C1 and C2 in user object C and their common friends; L j It is the sum of the frequencies of interactions between user nodes C1 and C2 in user object C and the commonly associated life service objects.

3. The method for constructing a social network based on life service consumption scenarios according to claim 1, characterized in that: When it is impossible to accurately obtain whether user nodes C1 and C2 in user object C have common friends: The total intimacy of the user nodes contained in the user object C based on the commonly associated life service object S in the social network: K C1-C2 =aj d+1 +ah; Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters; j: the number of service nodes commonly associated with user nodes C1 and C2 in user object C; h: user activity correlation constant between user nodes C1 and C2 in user object C; a: The common frequency constant between user nodes C1 and C2 in user object C.

4. The method for constructing a social network based on life service consumption scenarios according to claim 1, characterized in that: Calculate the intimacy of the user nodes contained in the user object C based on the commonly associated single life service object S in the social network: K C1-C2 =a(e+1) d+1 +ah; Where, d: spatiotemporal correlation constant, the number of times the absolute distance between user nodes C1 and C2 in user object C is less than or equal to 15 meters; e: the number of friend nodes associated with user nodes C1 and C2 in user object C; h: user activity correlation constant between user nodes C1 and C2 in user object C; a: The common frequency constant between user nodes C1 and C2 in user object C.

5. The method for constructing a social network based on life service consumption scenarios according to claim 4, characterized in that: The common frequency constant between user nodes C1 and C2 in user object C: a=R e +L1; In the formula, R e is the sum of the interaction frequencies between user nodes C1 and C2 in user object C and their common friends; L1 is the total frequency of interactions between user nodes C1 and C2 in user object C and a single life service object associated with the social network.

6. The method for constructing a social network based on life service consumption scenarios according to claim 1, characterized in that: The calculation formula of the recommended score L of the life service object S is: L = m + 10n + 50f + 60u + 70v + 90w; Among them, m: click; n: browse; f: help; u: collection; v: pending payment; w: purchase.

7. The method for constructing a social network based on life service consumption scenarios according to claim 1, characterized in that: The activity of user object C in the social network of the life service consumption scenario is: H C =X×R+Y×L.

8. The method for constructing a social network based on life service consumption scenarios according to claim 6, characterized in that: When the activity of user nodes C1 and C2 in user object C is greater than the overall average, the maximum activity of user nodes C1 and C2 is taken; When the activity of user nodes C1 and C2 in user object C is less than the overall average, take the minimum value of the activity of user nodes C1 and C2; When one or more of the activities of user nodes C1 and C2 in user object C is less than the overall average, the average of the activities of C1 and C2 is taken.

9. A social network construction device based on life service consumption scenarios, using a social network construction method based on life service consumption scenarios according to any one of claims 1 to 8, characterized in that: include: An object construction module, used to construct a user object C and a life service object S, wherein the user object C includes a preset user node; A first link expression module, used to create a preset first link expression C(X, R) between the user nodes, where X in the first link expression is the total number of users linked to the specified user node in the social network, and R in the first link expression is the total frequency of the specified user node interacting with the remaining user nodes in the social network; The second link expression module is used to construct a second link expression C for specifying a user node and a life service object S. s (Y, L), where Y in the second link expression is the total number of life service objects linked to the specified user node in the social network, and L in the second link expression is the total frequency of interaction of the specified user node with the linked life service objects; An intimacy calculation module, used to calculate the intimacy of the user nodes included in the user object C based on the commonly associated life service objects S in the social network; The recommendation processing module is used to determine the sorting priority of the life service object S recommended to the user node according to the recommendation score L of the life service object S.

Images