CN107679053A - Location recommendation method, device, computer equipment and storage medium - Google Patents

Location recommendation method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN107679053A
CN107679053A CN201710439338.0A CN201710439338A CN107679053A CN 107679053 A CN107679053 A CN 107679053A CN 201710439338 A CN201710439338 A CN 201710439338A CN 107679053 A CN107679053 A CN 107679053A
Authority
CN
China
Prior art keywords
user
check
place
recommended
query
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710439338.0A
Other languages
Chinese (zh)
Other versions
CN107679053B (en
Inventor
王健宗
黄章成
吴天博
肖京
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201710439338.0A priority Critical patent/CN107679053B/en
Priority to PCT/CN2017/099735 priority patent/WO2018227773A1/en
Publication of CN107679053A publication Critical patent/CN107679053A/en
Application granted granted Critical
Publication of CN107679053B publication Critical patent/CN107679053B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention relates to a kind of location recommendation method, specifically comprise the following steps：The place recommendation request that inquiry user terminal is sent is received, inquiry user's mark is carried in the recommendation request of place；Search the data of registering of inquiry user corresponding with inquiry user's mark, wherein, position social network-i i-platform is generated and registered data set according to the behavior of registering of the history of user, in data set of registering each the data of registering of user including place of registering；The association user of inquiry user is searched in data set of registering；Calculate the similarity between inquiry user and each association user, and the similar users collection according to corresponding to the similarity of calculating determines inquiry user；Determine the ground point set of registering corresponding to similar users collection；The place of registering overlapped in ground point set of registering with inquiry user is removed, obtains recommending ground point set, the recommendation place included in ground point set will be recommended to push to inquiry user terminal.The above method can make the place of recommendation more versatile and flexible and more be bonded user preference.

Description

Site recommendation method and device, computer equipment and storage medium
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a location recommendation method and apparatus, a computer device, and a storage medium.
Background
In the information explosion age of big data, personalized recommendation can help users to filter out information which is not interested by the users from abundant and miscellaneous data, and the preferences of the users can be better found, so that the activeness of the users in a social network is increased.
Most of the traditional personalized position recommendation methods analyze according to historical track data of users to obtain position preference of the users, and then recommend positions similar to the preference to the users. The position recommending mode based on the user track data has the following defects: first, since the user has a small and single track data amount, the recommended position is also relatively single. Secondly, places which are not preferred by the user may exist in the user historical track data, so that accurate fitting of the user preference cannot be ensured when personalized recommendation is performed based on the user historical track data.
Disclosure of Invention
In view of the above, it is desirable to provide a location recommendation method, device, computer device and storage medium, which can recommend locations more flexibly and more appropriately according to user preferences.
A method of site recommendation, the method comprising:
receiving a place recommendation request sent by a query user terminal, wherein the place recommendation request carries a query user identifier;
searching check-in data of the query user corresponding to the query user identification, wherein a location social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place;
searching for associated users of the inquiring user in the check-in data set, wherein at least one check-in place of the associated users is overlapped with the check-in place of the inquiring user;
calculating the similarity between the inquiry user and each associated user, and determining a similar user set corresponding to the inquiry user according to the calculated similarity;
determining a check-in place set corresponding to the similar user set, wherein the check-in place set comprises check-in places checked in by all associated users in the similar user set;
and removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
In one embodiment, the check-in data further includes a score for the check-in location;
the step of calculating the similarity between the query user and each associated user and determining a similar user set corresponding to the query user according to the calculated similarity comprises the following steps:
calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places checked by the query user and the associated users are, the closer the scores of the common check-in places are, and the larger the calculated similarity value is;
and forming the associated users with the similarity larger than a set threshold value into a similar user set of the query user.
In one embodiment, the step of calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places checked by the query user and the associated user are, the closer the scores of the common check-in places are, the larger the similarity value is calculated as follows:
calculating the similarity between each of the associated users and the querying user by the following formula:
wherein u and v represent a query user and an associated user respectively; sim (u, v) is the similarity between the associated user and the query user;a common check-in place of the associated user and the inquiry user is obtained;a check-in place which is not common to the associated user and the query user is set; r is ui And R vi Scoring the location i for the query user and the associated user respectively; r is a radical of hydrogen max The check-in times corresponding to the check-in place with the maximum check-in times by any user in the location social network platform are obtained.
In one embodiment, the step of removing the check-in places coinciding with the query user in the check-in place set to obtain a recommended place set, and the step of pushing the recommended places included in the recommended place set to the query user terminal includes:
removing check-in places coincident with the query user in the check-in place set to obtain a place set to be recommended;
calculating the interest degree of the query user and each place to be recommended in the place set to be recommended, and pushing the places to be recommended with the interest degree larger than a set threshold value to the query user terminal;
the interestingness is calculated through the similarity between the query user and the associated users who are logged in the place to be recommended in the similar user set and the scores of the associated users on the place to be recommended.
In one embodiment, the calculation formula of the interest degree between the query user and the to-be-recommended place is as follows:
wherein u is a query user, and j is a place to be recommended in the determined place set to be recommendedA recommended location; u is a similar user set of the query user, U k The similar users are associated users which check in the place j to be recommended in the similar user set; sim (u, u) k ) For querying user u and associated user u k The degree of similarity between the two images,for associated user u k And (4) scoring the to-be-recommended place j.
A location recommendation apparatus, the apparatus comprising:
the system comprises a request receiving module, a location recommending module and a query module, wherein the request receiving module is used for receiving a location recommending request sent by a query user terminal, and the location recommending request carries a query user identifier;
the check-in data searching module is used for searching check-in data of the inquiring user corresponding to the inquiring user identification, wherein the position social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place;
the associated user determining module is used for searching for associated users of the inquiring user in the check-in data set, and at least one check-in place of the associated users is overlapped with the check-in place of the inquiring user;
the similar user set determining module is used for calculating the similarity between the query user and each associated user and determining a similar user set corresponding to the query user according to the calculated similarity;
a check-in place set determining module, configured to determine a check-in place set corresponding to the similar user set, where the check-in place set includes check-in places checked in by all associated users in the similar user set;
and the recommended place determining module is used for removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
In one embodiment, the check-in data further includes a score for the check-in location; the similar user set determining module is further configured to calculate similarity between each associated user and the query user, wherein the more concentrated the check-in places where the query user and the associated users check in, the closer scores to the common check-in places, the larger the calculated similarity value is; and forming the associated users with the similarity larger than a set threshold value into a similar user set of the query user.
In one embodiment, the recommended place determining module is further configured to remove a check-in place coinciding with the query user in the check-in place set, so as to obtain a place set to be recommended; calculating the interest degree of the query user and each place to be recommended in the place set to be recommended, and pushing the places to be recommended with the interest degree larger than a set threshold value to the query user terminal; the interestingness is obtained by calculating the similarity between the query user and the associated user who is checked in the place to be recommended in the similar user set and the score of the associated user on the place to be recommended.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as described above.
According to the place recommending method, the place recommending device, the computer equipment and the storage medium, the place is recommended to each inquiring user through the place check-in information in the position social network platform. Firstly, determining associated users of the query user according to the check-in place information of the query user, wherein the associated users and the query user have at least one overlapped check-in place, further screening out similar users which have common preference with the query user to a certain extent from the determined associated users to form a similar user set, and then pushing places which are not checked-in by the query user and exist in the similar user set to the query user. That is, the recommended places to the inquiring user are not the same kind of places where the inquiring user visits, but the places visited by other users, and the recommended places are more flexible and diversified; and similar place preferences exist between the associated users in the similar user set and the query user, so that the recommended places can better fit with the preferences of the query user.
Drawings
FIG. 1 is a diagram of an application environment of a location recommendation method in one embodiment;
FIG. 2 is a diagram illustrating an internal architecture of a server according to an embodiment;
FIG. 3 is a flow diagram of a method for location recommendation in one embodiment;
FIG. 4 is a flow diagram involved in computing a similarity of a querying user and an associated user in one embodiment;
FIG. 5 is a flow diagram that illustrates the steps involved in the location recommendation step in one embodiment;
fig. 6 is a block diagram showing the structure of a place recommending apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, in one embodiment, an application environment diagram of a location recommendation method is provided, and includes a query terminal 110 and a server 120. Query terminal 110 may communicate with server 120 over a network. The query terminal 110 may be at least one of a smart phone, a tablet computer, a notebook computer, and a desktop computer, but is not limited thereto. The server 120 is a server or a server cluster of a Location-based Social Network platform (lbs n), and the database of the server cluster stores check-in data of users. The server 120 receives a place recommendation request sent by the query user terminal, searches the check-in data of the query user from the check-in database according to the carried query user identifier, and then searches the associated users having overlapped check-in places with the query user from the check-in database. The server 120 calculates the similarity between the query user and the associated user according to the check-in data of the query user and the check-in data of the associated user, and determines the associated user with the similarity meeting the set conditions as a member in the similar user set corresponding to the query user. The members in the similar user set have similar location preferences with the inquiry user, the check-in locations of the members in the similar user set can better conform to the preferences of the inquiry user, and the check-in locations have certain diversity relative to the historical check-in locations of the inquiry user.
As shown in fig. 2, in one embodiment, a server 120 is provided, which may be a physical server or a server cluster composed of a plurality of servers. Server 120 includes a processor, non-volatile storage media, internal memory, and a network interface connected by a system bus. The non-volatile storage medium of the server 120 stores, among other things, an operating system, a database, and at least one computer-executable instruction. The computer executable instructions, when executed by the processor, may cause the processor to perform a location recommendation method as shown in fig. 3. The database is used for storing data, such as check-in data of users. The processor is used to provide computational and control capabilities that support the operation of the entire server 120. The internal memory provides an environment for the operation of the location recommendation device in the non-volatile storage medium. The network interface is used for communication connection with the inquiry terminal 110. Those skilled in the art will appreciate that the configuration of the server shown in fig. 2 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation on the server to which the present application applies, and that a particular server may include more or less components than those shown, or combine certain components, or have a different arrangement of components.
As shown in fig. 3, in an embodiment, a location recommendation method is provided, which is exemplified by being applied in the server in fig. 2, and specifically includes the following steps:
step S202: and receiving a place recommendation request sent by a query user terminal, wherein the place recommendation request carries a query user identifier.
The inquiry user terminal is provided with a terminal application which can be communicated with the position social network platform server, and sends a place recommendation request to the server through the terminal application. In one embodiment, the recommendation request may be sent by clicking on a "place recommendation" button in the application interface. Or after the terminal logs in the server, the user regularly shakes the terminal body to send a recommendation request to the server. In another embodiment, when the server receives the user login platform request, it is considered that the terminal where the querying user is located sends a location recommendation request to the server, that is, the server performs location recommendation for each logged-in user.
The location social networking platform may be Foursquare, gowalla, or Facebook Places. The time of the user's check-in, the place of the check-in, and the content of the rating made to the place are all contained in these location-based social networking platforms. The evaluation content of the place made by the user can comprise a text evaluation and a scoring evaluation.
Step S204: and searching check-in data of the query user corresponding to the query user identification, wherein the position social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place.
And the server searches corresponding check-in data in the check-in data set according to the user identification of the query user. The check-in data set is a set of check-in data generated according to check-in behaviors of users in the platform, the check-in behaviors of the users are check-in request behaviors sent to the server by the users at a certain place in a historical time period, and the check-in requests carry evaluation information of the users on check-in positions. The server generates the check-in data according to the check-in behavior of the user, and the check-in data comprises the following steps: and acquiring the position information of the user when the user signs in, and positioning sign-in places such as restaurants, tourist attractions and the like according to the position information. In another embodiment, the check-in data further includes generating numerical rating information for the check-in location based on the rating information input by the user.
Step S206: and searching for associated users of the query user in the check-in data set, wherein at least one check-in place of the associated users is overlapped with the check-in place of the query user.
And the server searches whether check-in data coincident with the check-in place of the inquiry user exists in the check-in data set, and if so, defines the user corresponding to the searched check-in data as the associated user of the inquiry user. The associated user and the inquiring user may have one check-in place coincidence or a plurality of check-in places coincidence.
For example, the check-in data of query user u is: a. b and c, the check-in data of the user v is as follows: a. d, e, the check-in data of the user w is: b. the values of a, f,. User v has a place a commonly visited with query user u, and thus, user v is the associated user of query user u. User w and querying user u have two places, b and a, visited together, so that user w is the associated user of querying user u.
Step S208: and calculating the similarity between the query user and each associated user, and determining a similar user set corresponding to the query user according to the calculated similarity.
According to the fact that the associated users of the query user determined in step S206 may be a user group with a larger number, in order to recommend places to the query user more accurately, the step filters the determined associated users, and determines a user group with more similar place preference to the query user from the associated users, that is, determines a similar user set of the query user.
In one embodiment, the specific method for determining the similar user set of the query user is as follows: and calculating the similarity between the inquiry user and the associated user according to the check-in data of the inquiry user and the associated user, and selecting the associated users corresponding to the similarity with the preset number in the front as a similar user set of the inquiry user according to the arrangement sequence of the similarity from large to small. That is, the associated users corresponding to the top N maximum similarity degrees are selected as the similar user set of the querying user.
When the similarity between the query user and the associated user is calculated according to the check-in data of the query user and the associated user, the more places the associated user and the query user visit together, the greater the similarity between the two places. Or the closer the attributes of the query user and the place visited by the associated user are, the greater the similarity between the query user and the place visited by the associated user is.
Step S210: and determining a check-in place set corresponding to the similar user set, wherein the check-in place set comprises check-in places checked in by all associated users in the similar user set.
Step S212: and removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
And determining a check-in place set corresponding to the similar user set according to check-in data of all associated users included in the similar user set. That is, check-in places visited by all associated users in the set of similar users can be found in the corresponding set of check-in places.
For example, the associated users in the similar user set are: and (3) associating the user A: a. d, e; and (4) associating the user B: b, a, f; and associated user C: c. b, e, the check-in place set corresponding to the similar user set is { a, b, c, d, e, f }.
And removing check-in places checked in by the query user from the check-in place sets corresponding to the similar user sets to obtain a recommended place set. And if the check-in place set of the query user is { a, b, c }, the recommendation place set is { d, e, f }, and the recommendation places in the recommendation place set are pushed to the query user terminal.
In this embodiment, the users in the similar user set of the query user have similar location preferences to the query user, and locations visited by the users in the similar user set can be matched with the preferences of the query user at a certain probability. And the check-in place corresponding to the similar user set is used as a recommended place basis, and the recommended places are more diverse due to the diversity of the users. The recommended places are not limited to the same type of places as the places visited by the querying user itself, and may be other types of places that fit the preferences of the querying user to some extent.
In one embodiment, the check-in data further includes generating numerical rating information for the check-in location based on the rating information input by the user.
For example, check-in data of the querying user may include (a, 0.8), (b, 0.5), (c, 0.3) 3 pieces of check-in data. The check-in data comprises a check-in place of a query user, a value of each piece of data is a score of the query user on the check-in place, and the score of the query user on the check-in place is a score of the check-in place of the query user. Each check-in data of the query user corresponds to a specific check-in time, when the query user checks in one check-in place at different check-in times, a plurality of pieces of check-in data are generated, for example, at the time t 1 、t 2 If the querying user has checked in to location a, two pieces of check-in data, e.g., (a, 0.8), (a, 0.9), will be generated.
As shown in fig. 4, step S208: calculating the similarity between the query user and each associated user, and determining a similar user set corresponding to the query user according to the calculated similarity, comprising the following steps:
step S302: and calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places checked by the query user and the associated users are, the closer the scores of the common check-in places are, and the larger the calculated similarity value is.
Specifically, whether the check-in places of the query user and the associated user are collectively judged depends on the following factors: the total number of check-ins to the same place (considering the case where one user checks-in to a common check-in place multiple times) and the total number of check-ins to non-common check-in places. The larger the sum of the number of check-in times to the same place and the smaller the sum of the number of check-in times to non-common check-in places, the more concentrated the check-in places of the associated user and the querying user.
For example, the set of check-in places of query users is { a, B, c, a, d, e, f, e, h }, the set of check-in places of associated user a is { a, m, i, l, m, B, f, k, h }, and the set of check-in places of associated user B is { a, B, e, o, f, k, m }
The sum of the number of times of signing in the same place by the associated user A and the inquiring user is 5, namely a, b, f and h, and the number of times of signing in the non-common sign-in place is 9, namely c, d, e, m, i, l, m and k; the sum of the number of times of the associated user B and the inquiring user signing in the same place is 6, namely a, B, a, e and f, and the number of times of signing in the non-common signing-in place is 6, namely c, d, h, o, m and k. As can be seen from the above analysis, the check-in places of the associated user B and the inquiring user are more concentrated.
In one embodiment, whether the scores of the query user and the associated user for a common check-in place are relatively close may be determined by calculating the variance or standard deviation or the absolute value of the score difference of the scores of the two for the same check-in place. Taking the absolute value of the score difference as an example, if the co-visited places of the query user and the associated user are a and b respectively, and the scores of the query user and the associated user are {0.6,0.8} and {0.5,0.9}, respectively, the score closeness of the query user and the associated user is |0.6-0.5| + |0.8-0.9|, and the smaller the value is, the closer the score between the associated user and the query user is, the greater the similarity is.
Step S304: and forming a similar user set of the query user by the associated users with the similarity greater than the set threshold.
And calculating the similarity between the query user and the associated user according to whether the check-in places are concentrated or not and whether the scores of the common check-in places are close to the two factors, and taking the associated user with the similarity larger than a set threshold value as a member in the similar user set of the query user.
The threshold value may be set in advance, and may be 0.8, for example. And the associated users with the similarity greater than 0.8 form a similar user set of the query user. If the member size of the similar user set determined according to the preset threshold is small (if the number of the determined related users in the similar user set is less than 2), adjusting the size of the set threshold, and re-determining the similar user set.
In one embodiment, the server presets a plurality of levels of similarity thresholds, such as a precision threshold (e.g., 0.8), a standard threshold (e.g., 0.6), and a rough threshold (e.g., 0.4), where the precision threshold > the standard threshold > the rough threshold. And when the similar user set cannot be determined according to the accurate threshold or the determined similar user set is small in size, adjusting the threshold to be the standard threshold. Further, if the similar user set cannot be determined according to the standard threshold or the determined similar user set is small in size, the threshold is adjusted to be a rough threshold.
In the embodiment, the check-in times and the check-in place score are comprehensively considered, so that the calculated similarity can reflect the similarity between the associated user and the query user, and the place recommendation according to the similar user can be more related to the preference of the user to the place.
In one embodiment, the similarity between each associated user and the querying user may be calculated by the following formula:
wherein u and v represent a query user and an associated user respectively; sim (u, v) is the similarity between the associated user and the query user;a common check-in place of the associated user and the inquiry user is obtained;a check-in place which is not common to the associated user and the query user is set; r ui And R vi Scoring the location i for the query user and the associated user respectively; r is j Checking in times of the location j for the query user or the associated user; r is a radical of hydrogen max For the check-in times corresponding to the check-in place with the maximum check-in times of any user in the position social network platform r, aiming at the same position social network platform r max It is essentially a constant value, and it is used to normalize the score.
For example, assume that there are two users u and v, r max Assuming 5, the corresponding check-in data are:
u：(a,0.6)、(b,0.5)、(a,0.7)
v: (a, 0.5), (c, 0.4), then i check-in places a, j in equation (1) refer to check-in places b and c,
then
The similarity calculated by the formula (1) not only weighs the set of places visited by two users together, but also fully considers other places not visited together, namely the dispersion degree (or concentration degree) of the places visited by the two users, and in addition, the consideration of the scoring factor of the places visited by the users makes the calculated similarity capable of more accurately evaluating whether the place preference between the two users is similar.
In one embodiment, as shown in FIG. 5, step S210: the steps of removing the check-in place coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended place contained in the recommended place set to the inquiry user terminal include:
step S402: and removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a place set to be recommended.
And all places which are not checked in by the query user in the similar user set are the place set to be recommended. The places recommended to the querying user should be places that the querying user has not visited.
In this embodiment, the places to be recommended by the query user are extracted from the check-in place set corresponding to the similar user set. The associated users in the similar user set have certain place preference similarity with the inquiring user, and the place recommendation of the inquiring user based on the check-in places corresponding to the similar user set is fit with the preference of the inquiring user to a certain degree.
Step S404: calculating the interest degree of the query user and each to-be-recommended place in the to-be-recommended place set, and pushing the to-be-recommended places with the interest degrees larger than a set threshold value to a query user terminal; the interestingness is obtained by inquiring the similarity between the user and the associated users who are checked in the place to be recommended in the similar user set and calculating the scores of the places to be recommended by the associated users.
In order to make the recommended places more accurately fit with the preferences of the query user, in this embodiment, the determined places to be recommended are further accurately selected to select the places which can best fit with the real preferences of the query user. The method specifically comprises the following steps: and calculating the interestingness between the place to be recommended and the query user. The higher the interest degree between the place to be recommended and the query user is, the higher the fitting degree between the place and the preference of the query user is.
In this embodiment, first, the related users who check in the place to be recommended are searched in the similar user set. Then, according to the similarity between the searched associated user and the query user and the score of the check-in place of the associated user, which are calculated in the step S208, the interestingness between the query user and the place to be queried is calculated. That is, the interestingness relationship between the query user and the location is obtained through the similarity relationship between the correlation user and the query user and the scoring relationship between the correlation user and the location.
For example, the interestingness between the place A to be recommended and the query user is calculated. Searching the associated users who have visited the place A to be recommended in the similar user set and respectively taking the associated users as the associated users u 1 、u 2 、u 3 . Associated user u 1 、u 2 、u 3 The respective check-in data comprises score information of the recommended place A, and the interest degree of the query user and the recommended place A is calculated according to the calculated similarity of the associated user and the query user and the score of the associated user on the recommended place A, wherein the higher the score of the associated user on the recommended place is, the higher the similarity of the associated user and the query user is, and the higher the interest degree of the recommended place and the query user is.
In one embodiment, the interestingness between the query user and the place to be recommended can be calculated by the following formula (2):
u is a query user, and j is a place to be recommended in the determined place set to be recommended; u is a set of similar users of the querying user, U k The similar users are associated users who check in the place j to be recommended in the similar user set; sim (u, u) k ) For querying user u and associated user u k The degree of similarity between the two images,for associated user u k And (4) scoring the to-be-recommended place j.
Suppose that: and calculating the interestingness between the query user u and the place A to be recommended. Searching the associated users who have checked in the place A to be recommended in the similar user set of u and respectively taking the associated users u as the associated users 1 、u 2 、u 3 Associating user u 1 、u 2 、u 3 The scores of the place A to be recommended are respectivelyInquiring user and associated user u 1 、u 2 、u 3 Respectively has similarity of sim (u, u) 1 )、sim(u,u 2 ) And sim (u, u) 3 ) (ii) a Inquiring the interestingness between the user u and the place A to be recommended:
according to the formula (2), the interest degree between the query user and the to-be-recommended place can be calculated by utilizing the relation between the query user and the associated user and the relation between the associated user and the to-be-recommended place, and the interest degree can well reflect the interest degree of the query user in the to-be-recommended place. The place to be recommended with a large interest degree is pushed to the query user terminal, so that the pushed place is more suitable for the real preference of the user, and accurate pushing for the user is achieved.
In one embodiment, as shown in fig. 6, there is provided a location recommendation apparatus including:
the request receiving module 502 is configured to receive a location recommendation request sent by a querying user terminal, where the location recommendation request carries a querying user identifier.
And the check-in data searching module 504 is used for searching check-in data of the query user corresponding to the query user identifier, wherein the location social network platform generates a check-in data set according to the historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place.
The associated user determining module 506 searches for associated users of the querying user in the check-in dataset, wherein at least one check-in place of the associated users coincides with the check-in place of the querying user.
The similar user set determining module 508 is configured to calculate similarity between the querying user and each associated user, and determine a similar user set corresponding to the querying user according to the calculated similarity.
The check-in place set determining module 510 is configured to determine a check-in place set corresponding to the similar user set, where the check-in place set includes check-in places checked in by all associated users in the similar user set.
And the recommended place determining module 512 is configured to remove the check-in places which coincide with the query user in the check-in place set, obtain a recommended place set, and push the recommended places contained in the recommended place set to the query user terminal.
In one embodiment, the check-in data further includes a score for the check-in location; the similar user set determining module 508 is further configured to calculate similarity between each associated user and the query user, where the more concentrated the check-in places checked by the query user and the associated users are, the closer scores to the common check-in places are, and the larger the calculated similarity value is; and forming a similar user set of the query user by the associated users with the similarity greater than the set threshold.
In one embodiment, the similarity between each associated user and the querying user is calculated by the following formula:
wherein u and v represent a query user and an associated user respectively; sim (u, v) is the similarity between the associated user and the query user;a common check-in place of the associated user and the inquiry user is obtained;checking in places which are not common to the associated user and the inquiry user; r ui And R vi Scoring the location i for the query user and the associated user respectively; r is max The check-in times corresponding to the check-in place with the maximum check-in times by any user in the location social network platform are obtained.
In an embodiment, the recommended place determining module 512 is further configured to remove a check-in place coinciding with the querying user in the check-in place set, so as to obtain a to-be-recommended place set; the method comprises the steps of calculating the interestingness of a query user and each to-be-recommended place in a to-be-recommended place set, and pushing the to-be-recommended places with the interestingness larger than a set threshold value to a query user terminal, wherein the interestingness is obtained through the similarity between the query user and associated users who are intensively checked in the to-be-recommended places by similar users and the score calculation of the associated users on the to-be-recommended places.
In one embodiment, the calculation formula for inquiring the interestingness of the user and the place to be recommended is as follows:
u is a query user, and j is a place to be recommended in the determined place set to be recommended; u is a set of similar users of the querying user, U k Are similar usersIntensively checking in the associated users of the place j to be recommended; sim (u, u) k ) For querying user u and associated user u k The degree of similarity between the two images,for associated user u k And (4) scoring the place to be recommended j.
In one embodiment, a computer device is provided, which may be a server, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program: receiving a place recommendation request sent by a query user terminal, wherein the place recommendation request carries a query user identifier; searching check-in data of a query user corresponding to the query user identification, wherein the location social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place; searching for associated users of the query user in the check-in data set, wherein at least one check-in place of the associated users is overlapped with the check-in place of the query user; calculating the similarity between the query user and each associated user, and determining a similar user set corresponding to the query user according to the calculated similarity; determining a check-in place set corresponding to the similar user set, wherein the check-in place set comprises check-in places checked in by all associated users in the similar user set; and removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
In one embodiment, the check-in data further includes a score for the check-in location; the steps of calculating the similarity between the inquiry user and each associated user and determining a similar user set corresponding to the inquiry user according to the calculated similarity, which are executed by a processor of the computer device, include: calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places of the query user and the associated users are, the closer the scores of the common check-in places are, and the larger the similarity value obtained by calculation is; and forming a similar user set of the query user by the associated users with the similarity greater than the set threshold.
In one embodiment, the step executed by the processor of the computer device of calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places checked by the query user and the associated user are, the closer the scores of the common check-in places are, the larger the calculated similarity value is, is:
calculating the similarity between each associated user and the query user through the following formula:
wherein u and v represent a query user and an associated user respectively; sim (u, v) is the similarity between the associated user and the query user;a common check-in place of the associated user and the inquiry user;checking in places which are not common to the associated user and the inquiry user; r ui And R vi Scoring the location i for the query user and the associated user respectively; r is max The check-in times corresponding to the check-in place with the maximum check-in times by any user in the location social network platform are obtained.
In one embodiment, the step of removing a check-in place coincident with the check-in place of the querying user in the check-in place set to obtain a recommended place set, which is executed by a processor of the computer device, and the step of pushing the recommended place contained in the recommended place set to the querying user terminal includes: removing check-in places which coincide with check-in places of the inquiry users in the check-in place set to obtain a place set to be recommended; calculating the interestingness of the query user and each to-be-recommended place in the to-be-recommended place set, pushing the to-be-recommended places with the interestingness larger than a set threshold value to the query user terminal, wherein the interestingness is obtained through the similarity between the query user and the associated users who are collectively checked in the to-be-recommended places by the similar users and the score calculation of the to-be-recommended places by the associated users.
In one embodiment, the calculation formula for inquiring the interest degree between the user and the place to be recommended executed by the processor of the computer device is as follows:
u is a query user, and j is a place to be recommended in the determined place set to be recommended; u is a similar user set of query users, U k The similar users are associated users who check in the place j to be recommended in the similar user set; sim (u, u) k ) For querying user u and associated user u k The degree of similarity between the two images,for associated user u k And (4) scoring the to-be-recommended place j.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: receiving a place recommendation request sent by a query user terminal, wherein the place recommendation request carries a query user identifier; searching check-in data of a query user corresponding to the query user identification, wherein the location social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place; searching for associated users of the query user in the check-in data set, wherein at least one check-in place of the associated users is overlapped with the check-in place of the query user; calculating the similarity between the query user and each associated user, and determining a similar user set corresponding to the query user according to the calculated similarity; determining a check-in place set corresponding to the similar user set, wherein the check-in place set comprises check-in places checked in by all associated users in the similar user set; and removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
In one embodiment, the check-in data further includes a score for the check-in location; the steps executed by the processor for calculating the similarity between the query user and each associated user and determining a similar user set corresponding to the query user according to the calculated similarity comprise the following steps: calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places of the query user and the associated users are, the closer the scores of the common check-in places are, and the larger the similarity value obtained by calculation is; and forming a similar user set of the query user by the associated users with the similarity greater than the set threshold.
In one embodiment, the similarity between each associated user and the query user is calculated by the processor, wherein the more concentrated the check-in places of the query user and the associated users are and the closer the scores of the common check-in places are, the larger the calculated similarity value is:
calculating the similarity between each associated user and the query user through the following formula:
wherein u and v represent a query user and an associated user respectively; sim (u, v) is the similarity between the associated user and the query user;a common check-in place of the associated user and the inquiry user is obtained;checking in places which are not common to the associated user and the inquiry user; r is ui And R vi Scoring the location i for the query user and the associated user respectively; r is max The check-in times corresponding to the check-in place with the maximum check-in times by any user in the location social network platform are obtained.
In one embodiment, the step of removing check-in places, which coincide with check-in places of the querying user, in the check-in place set by the processor to obtain a recommended place set, and the step of pushing recommended places contained in the recommended place set to the querying user terminal includes: removing check-in places which coincide with check-in places of the inquiry users in the check-in place set to obtain a place set to be recommended; calculating the interest degree of the query user and each to-be-recommended place in the to-be-recommended place set, and pushing the to-be-recommended places with the interest degrees larger than a set threshold value to a query user terminal; the interestingness is obtained by inquiring the similarity between the user and the associated users who are checked in the place to be recommended in the similar user set and calculating the scores of the places to be recommended by the associated users.
In one embodiment, the processor executes a calculation formula of the interest degree between the query user and the place to be recommended, wherein the calculation formula is as follows:
u is a query user, and j is a place to be recommended in the determined place set to be recommended; u is a similar user set of query users, U k The similar users are associated users who check in the place j to be recommended in the similar user set; sim (u, u) k ) For querying user u and associated user u k The degree of similarity between the two images,for associated user u k And (4) scoring the to-be-recommended place j.
It will be understood by those skilled in the art that all or part of the processes in the methods of the embodiments described above may be implemented by hardware related to instructions of a computer program, and the program may be stored in a computer readable storage medium, for example, in the storage medium of a computer system, and executed by at least one processor in the computer system, so as to implement the processes of the embodiments including the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent should be subject to the appended claims.

Claims (10)

1. A method of place recommendation, the method comprising:
receiving a place recommendation request sent by a query user terminal, wherein the place recommendation request carries a query user identifier;
searching check-in data of the query user corresponding to the query user identification, wherein the location social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place;
searching for associated users of the inquiring user in the check-in data set, wherein at least one check-in place of the associated users is overlapped with the check-in place of the inquiring user;
calculating the similarity between the query user and each associated user, and determining a similar user set corresponding to the query user according to the calculated similarity;
determining a check-in place set corresponding to the similar user set, wherein the check-in place set comprises check-in places checked in by all associated users in the similar user set;
and removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
2. The method of claim 1, wherein the check-in data further comprises a score for the check-in location;
the step of calculating the similarity between the query user and each associated user and determining a similar user set corresponding to the query user according to the calculated similarity comprises the following steps:
calculating the similarity between each associated user and the query user, wherein the more concentrated the check-in places checked by the query user and the associated users are, the closer the scores of the common check-in places are, and the larger the calculated similarity value is;
and forming the associated users with the similarity larger than a set threshold value into a similar user set of the query user.
3. The method according to claim 2, wherein the step of calculating the similarity between each associated user and the query user is that the more concentrated the check-in places checked by the query user and the associated user are and the closer the scores of the common check-in places are, the larger the calculated similarity value is:
calculating the similarity between each of the associated users and the querying user by the following formula:
wherein u and v represent a query user and an associated user respectively; sim (u, v) is the similarity between the associated user and the query user;for associating usersA check-in place common to the querying user;checking in places which are not common to the associated user and the inquiry user; r ui And R vi Scoring the location i for the query user and the associated user respectively; r is max The check-in times corresponding to the check-in place with the maximum check-in times by any user in the location social network platform are obtained.
4. The method according to claim 2, wherein the step of removing the check-in places which coincide with the querying user in the check-in place set to obtain a recommended place set, and the step of pushing the recommended places included in the recommended place set to the querying user terminal includes:
removing check-in places which coincide with the inquiry user in the check-in place set to obtain a place set to be recommended;
calculating the interest degree of the query user and each to-be-recommended place in the to-be-recommended place set, and pushing the to-be-recommended places with the interest degrees larger than a set threshold value to the query user terminal;
the interestingness is obtained by calculating the similarity between the query user and the associated user who is checked in the place to be recommended in the similar user set and the score of the associated user on the place to be recommended.
5. The method according to claim 4, wherein the calculation formula of the interest degree of the query user and the place to be recommended is as follows:
u is a query user, and j is a place to be recommended in the determined place set to be recommended; u is a similar user set of the query user, U k Is a label in the similar user setThe associated users arrive at the place j to be recommended; sim (u, u) k ) For querying user u and associated user u k The degree of similarity between the two images,for associated user u k And (4) scoring the to-be-recommended place j.
6. A location recommendation device, the device comprising:
the system comprises a request receiving module, a query user terminal and a query processing module, wherein the request receiving module is used for receiving a place recommendation request sent by the query user terminal, and the place recommendation request carries a query user identifier;
the check-in data searching module is used for searching check-in data of the query user corresponding to the query user identification, wherein the location social network platform generates a check-in data set according to historical check-in behaviors of the user, and the check-in data of each user in the check-in data set comprises a check-in place;
the associated user determining module is used for searching for associated users of the inquiring user in the check-in data set, and at least one check-in place of the associated users is overlapped with the check-in place of the inquiring user;
the similar user set determining module is used for calculating the similarity between the query user and each associated user and determining a similar user set corresponding to the query user according to the calculated similarity;
the check-in place set determining module is used for determining a check-in place set corresponding to the similar user set, wherein the check-in place set comprises check-in places checked in by all associated users in the similar user set;
and the recommended place determining module is used for removing the check-in places which are coincident with the inquiry user in the check-in place set to obtain a recommended place set, and pushing the recommended places contained in the recommended place set to the inquiry user terminal.
7. The apparatus of claim 6, wherein the check-in data further comprises a score for the check-in location; the similar user set determining module is further configured to calculate similarity between each associated user and the query user, wherein the more concentrated the check-in places where the query user and the associated users check in, the closer scores to the common check-in places, the larger the calculated similarity value is; and forming the associated users with the similarity larger than a set threshold value into a similar user set of the query user.
8. The device according to claim 6, wherein the recommended place determining module is further configured to remove check-in places in the set of check-in places that coincide with the querying user, and obtain a set of places to be recommended; calculating the interest degree of the query user and each place to be recommended in the place set to be recommended, and pushing the places to be recommended with the interest degree larger than a set threshold value to the query user terminal;
the interestingness is calculated through the similarity between the query user and the associated users who are logged in the place to be recommended in the similar user set and the scores of the associated users on the place to be recommended.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1-5 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
CN201710439338.0A 2017-06-12 2017-06-12 Site recommendation method and device, computer equipment and storage medium Active CN107679053B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201710439338.0A CN107679053B (en) 2017-06-12 2017-06-12 Site recommendation method and device, computer equipment and storage medium
PCT/CN2017/099735 WO2018227773A1 (en) 2017-06-12 2017-08-30 Place recommendation method and apparatus, computer device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710439338.0A CN107679053B (en) 2017-06-12 2017-06-12 Site recommendation method and device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN107679053A true CN107679053A (en) 2018-02-09
CN107679053B CN107679053B (en) 2020-02-18

Family

ID=61133573

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710439338.0A Active CN107679053B (en) 2017-06-12 2017-06-12 Site recommendation method and device, computer equipment and storage medium

Country Status (2)

Country Link
CN (1) CN107679053B (en)
WO (1) WO2018227773A1 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109447731A (en) * 2018-09-18 2019-03-08 平安科技（深圳）有限公司 Cross-platform Products Show method, apparatus, computer equipment and storage medium
CN110059248A (en) * 2019-03-21 2019-07-26 腾讯科技（深圳）有限公司 A kind of recommended method, device and server
CN110866180A (en) * 2019-10-12 2020-03-06 平安国际智慧城市科技股份有限公司 Resource recommendation method, server and storage medium
CN111523031A (en) * 2020-04-22 2020-08-11 北京百度网讯科技有限公司 Method and device for recommending interest points
CN111737537A (en) * 2020-07-21 2020-10-02 杭州欧若数网科技有限公司 POI recommendation method, device and medium based on graph database

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103488678A (en) * 2013-08-05 2014-01-01 北京航空航天大学 Friend recommendation system based on user sign-in similarity
CN104978437A (en) * 2015-07-22 2015-10-14 浙江大学 Geographic position-based recommendation method and recommendation system
CN105740401A (en) * 2016-01-28 2016-07-06 北京理工大学 Individual behavior and group interest-based interest place recommendation method and device
CN106056455A (en) * 2016-06-02 2016-10-26 南京邮电大学 Group and place recommendation method based on location and social relationship

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103488678A (en) * 2013-08-05 2014-01-01 北京航空航天大学 Friend recommendation system based on user sign-in similarity
CN104978437A (en) * 2015-07-22 2015-10-14 浙江大学 Geographic position-based recommendation method and recommendation system
CN105740401A (en) * 2016-01-28 2016-07-06 北京理工大学 Individual behavior and group interest-based interest place recommendation method and device
CN106056455A (en) * 2016-06-02 2016-10-26 南京邮电大学 Group and place recommendation method based on location and social relationship

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109447731A (en) * 2018-09-18 2019-03-08 平安科技（深圳）有限公司 Cross-platform Products Show method, apparatus, computer equipment and storage medium
CN110059248A (en) * 2019-03-21 2019-07-26 腾讯科技（深圳）有限公司 A kind of recommended method, device and server
CN110059248B (en) * 2019-03-21 2022-12-13 腾讯科技（深圳）有限公司 Recommendation method and device and server
CN110866180A (en) * 2019-10-12 2020-03-06 平安国际智慧城市科技股份有限公司 Resource recommendation method, server and storage medium
CN110866180B (en) * 2019-10-12 2022-07-29 平安国际智慧城市科技股份有限公司 Resource recommendation method, server and storage medium
CN111523031A (en) * 2020-04-22 2020-08-11 北京百度网讯科技有限公司 Method and device for recommending interest points
CN111523031B (en) * 2020-04-22 2023-03-31 北京百度网讯科技有限公司 Method and device for recommending interest points
CN111737537A (en) * 2020-07-21 2020-10-02 杭州欧若数网科技有限公司 POI recommendation method, device and medium based on graph database
CN111737537B (en) * 2020-07-21 2020-11-27 杭州欧若数网科技有限公司 POI recommendation method, device and medium based on graph database

Also Published As

Publication number Publication date
CN107679053B (en) 2020-02-18
WO2018227773A1 (en) 2018-12-20

Similar Documents

Publication Publication Date Title
CN107679053B (en) Site recommendation method and device, computer equipment and storage medium
CN107766462B (en) Interest point recommendation method based on user preference, social reputation and geographic position
CN107798557B (en) Electronic device, service place recommendation method based on LBS data and storage medium
US11294981B2 (en) System and method for large scale crowdsourcing of map data cleanup and correction
US11727053B2 (en) Entity recognition from an image
US20160295372A1 (en) Venue identification from wireless scan data
EP3001332A1 (en) Target user determination method, device and network server
EP3163471A1 (en) Data information transaction method and system
US20190278822A1 (en) Cross-Platform Data Matching Method and Apparatus, Computer Device and Storage Medium
WO2015157344A2 (en) Systems and methods for large scale crowdsourcing of map data location, cleanup, and correction
CN109460520A (en) Point of interest recommended method based on geography-social relationships and deep implicit interest digging
US9158790B2 (en) Server, dictionary creation method, dictionary creation program, and computer-readable recording medium recording the program
CN108932646B (en) User tag verification method and device based on operator and electronic equipment
US10701513B2 (en) Raising priorities of information based on social media relationships
CN109816543A (en) A kind of image lookup method and device
CN109699003B (en) Position determination method and device
JP7092194B2 (en) Information processing equipment, judgment method, and program
US11622231B2 (en) System and method for identifying associated subjects from location histories
CN113793174A (en) Data association method and device, computer equipment and storage medium
WO2019080404A1 (en) Cross-social networking platform user matching method, data processing device, and readable storage medium
CN107181672A (en) The friend recommendation method based on Annual distribution relative entropy in the social networks of position
CN108875083B (en) Social network-based person searching method and device, computer equipment and storage medium
US11601509B1 (en) Systems and methods for identifying entities between networks
KR101233902B1 (en) Server, dictionary creation method, and computer-readable recording medium for recording dictionary creation program
EP2763052A1 (en) Search method and information management device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant