CN109522491B - Stranger social activity recommendation method and system based on location attribute - Google Patents
Stranger social activity recommendation method and system based on location attribute Download PDFInfo
- Publication number
- CN109522491B CN109522491B CN201811442178.6A CN201811442178A CN109522491B CN 109522491 B CN109522491 B CN 109522491B CN 201811442178 A CN201811442178 A CN 201811442178A CN 109522491 B CN109522491 B CN 109522491B
- Authority
- CN
- China
- Prior art keywords
- activity
- attribute vector
- current user
- dimension
- holding position
- 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.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The stranger social activity recommendation method based on the location attribute comprises the following steps: acquiring the handling position information of historical activities participated by a current user within a preset time period, and the position track information of the current user within the activity effective time and the daily activity space information of the current user; generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information; averaging the position attribute vectors to generate an average attribute vector of the current user; distributing a weight value to each dimension of the average attribute vector to generate a characteristic attribute vector; adjusting corresponding dimensions in the feature attribute vector according to the position track information to generate a final feature attribute vector; and recommending related social activities of strangers to the current user according to the final characteristic attribute vector, so that the user experience is improved, and the social development of the strangers is facilitated.
Description
Technical Field
The application relates to the technical field of internet, in particular to a stranger social activity recommendation method and system based on location attributes.
Background
Social interaction refers to the interpersonal communication between people in the society, and is the consciousness that people transmit information and communicate ideas in a certain mode (tool) so as to achieve various social activities with a certain purpose. With the development of scientific technology and the application of internet resources in life, the communication between people is realized by means of the internet, and strangers can also realize social contact through the internet, so that the purposes of further developing and expanding the strangers are realized. For example, some internet platforms and services have appeared in the prior art that are directed to strangers social services, such as searching for nearby people to have online conversations, transmitting network drift bottles, and the like.
A stranger social platform recently appeared in the prior art is that an activity organizer publishes a social activity (such as dinner gathering, outing, playing games, etc.) held at a predetermined time and place on the platform, and sets conditions (such as sex, age, etc.) to be met for participating in the social activity; other users can search the social activities which are interesting and meet the conditions of the other users on the platform, and the platform can also recommend the published social activities to the other users. Other users can log in the searched or recommended stranger social activities on line based on own wishes, and then the stranger social activities are attended to a predetermined place on time as activity participants to participate in the social activities.
When recommending social activities for a user, location-based activity recommendation is an important way to recommend. However, the conventional location-based activity recommendation method is mainly to recommend activities within a certain distance range from the user or preferentially recommend activities close to the user location in the recommended ranking according to the distance between the activity hosting location and the user location, so as to reduce the time and cost spent on the route traffic when the user participates in the social activity as much as possible, thereby improving the probability of successful recommendation.
However, when we consider the effect of location on the user's willingness to participate in the recommended social activity, it is clear that distance is not the only factor. For example, the user may consider the security of the event hosting location and the familiarity with the event hosting location, especially for the application scenario of stranger social contact, because the people to be contacted are strange, the user generally does not want to go to a more remote place or a place unfamiliar with the user to participate in the event, which further reduces the security of the user; of course, there are also situations where some users would rather like to go to an unfamiliar environment to engage in social activities to pursue a sense of freshness. In addition, the activity location itself may constitute a certain attraction, which is also different from person to person, in addition to elements such as the content, form, etc. of the recommended social activity; for example, for people who like shopping, eating, or entertaining, a social event held by a shopping mall with many shopping malls around is more attractive, since the user can also take shopping, eating, or entertaining in one go in addition to participating in the social event, and thus this location is itself attractive to him, even if he is far away, and the user would like to participate; on the contrary, for people who do not like to visit the street, the behavior habit of participating in the social activity is to go straight ahead to participate in the social activity, and the people leave immediately after participating in the social activity, so that the entertainment, diet and shopping places around the activity position have little influence on the user, and the activity position has no special attraction for the user.
Therefore, in the activity recommendation method based on the position in the prior art, the relative consideration of the factors is one-sided, the attraction of the factors such as the position attribute of the activity holding position, the surrounding environment and the relationship between the activity position and the behavior habit of the user to the social activity participated by the user is ignored, the user experience is influenced, the success rate of activity recommendation based on the position is not optimal, and the development of strangers in social activity is not facilitated.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method and a system for recommending strangers social activities based on location attributes, so as to solve the technical problems that in the prior art, the factors are considered relatively, the attractiveness of various factors of the activity hosting location to users is neglected, the user experience is influenced, and the development of strangers social activities is not facilitated.
In view of the above, in one aspect of the present application, a method for recommending social activities of strangers based on location attributes is provided, including:
acquiring the handling position information of historical activities participated by a current user in a preset time period, the position track information of the current user in an activity effective time and the daily activity space information of the current user;
generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information;
averaging the position attribute vectors to generate an average attribute vector of the current user;
distributing a weight value to each dimension of the average attribute vector to generate a characteristic attribute vector;
adjusting corresponding dimensions in the feature attribute vector according to the position track information to generate a final feature attribute vector;
and recommending related stranger social activities to the current user according to the final characteristic attribute vector.
In some embodiments, the hosting location information includes:
the method comprises the following steps of hosting the type of an area where a position is located, wherein the type of the area is divided into a downtown area, an urban and rural combined area and a suburban area;
the surrounding environment information of the holding position, namely the number of the surrounding of the holding position and the related places of the event.
In some embodiments, the location attribute vector comprises:
the system comprises a hosting location, a user activity space correlation dimension and an activity location concentration degree dimension.
In some embodiments, the distance between the hosting location and the preset reference point is used as a value of an area dimension of the hosting location, the number of places around the hosting location and related to the event is used as a value of a surrounding environment dimension of the hosting location, the distance between the hosting location and the daily activity space of the current user is used as a value of a user activity space correlation dimension, and the average distance between the hosting location and the hosting location of the social activity of the preset number of times that the user participates in before is used as an activity location concentration degree dimension.
In some embodiments, the location track information is a dwell time of the current user within a preset range of an event hosting location.
In some embodiments, the adjusting the corresponding dimension in the feature attribute vector according to the position trajectory information to generate a final feature attribute vector includes:
and adjusting the weight value of the surrounding environment dimension of the holding position in the characteristic attribute vector according to the average time of the current user staying in the preset range of the activity holding position within the activity effective time to generate a final characteristic attribute vector.
In some embodiments, the recommending relevant stranger social activities to the current user according to the final feature attribute vector comprises:
screening out a preset number of alternative stranger social activities according to the interest and hobbies of the user, calculating a position attribute feature vector of each alternative stranger social activity, calculating the distance between the feature vector and the final feature attribute vector, sequencing the alternative stranger social activities according to the calculation result, and recommending the alternative stranger social activities to the current user according to the sequencing result.
In another aspect of the present application, there is provided a stranger social activity recommendation system based on location attributes, including:
the information acquisition module is used for acquiring the handling position information of the historical activities participated by the current user in a preset time period, the position track information of the current user in the activity effective time and the daily activity space information of the current user;
the position attribute vector generating module is used for generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information;
the average attribute vector generation module is used for averaging the position attribute vectors to generate an average attribute vector of the current user;
the characteristic attribute vector generation module is used for distributing a weight value for each dimension of the average attribute vector to generate a characteristic attribute vector;
the final characteristic attribute vector generation module is used for adjusting corresponding dimensions in the characteristic attribute vectors according to the position track information to generate final characteristic attribute vectors;
and the stranger social activity recommending module is used for recommending relevant stranger social activities to the current user according to the final characteristic attribute vector.
In some embodiments, the final feature attribute vector generation module is specifically configured to:
and adjusting the weight value of the surrounding environment dimension of the holding position in the characteristic attribute vector according to the average time of the current user staying in the preset range of the activity holding position within the activity effective time to generate a final characteristic attribute vector.
In some embodiments, the stranger social activity recommendation module is specifically configured to:
screening out a preset number of alternative stranger social activities according to the interest and hobbies of the user, calculating a position attribute feature vector of each alternative stranger social activity, calculating the distance between the feature vector and the final feature attribute vector, sequencing the alternative stranger social activities according to the calculation result, and recommending the alternative stranger social activities to the current user according to the sequencing result.
The stranger social activity recommendation method based on the location attribute comprises the following steps: acquiring the handling position information of historical activities participated by a current user in a preset time period, the position track information of the current user in an activity effective time and the daily activity space information of the current user; generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information; averaging the position attribute vectors to generate an average attribute vector of the current user; distributing a weight value to each dimension of the average attribute vector to generate a characteristic attribute vector; adjusting corresponding dimensions in the feature attribute vector according to the position track information to generate a final feature attribute vector; and recommending related stranger social activities to the current user according to the final characteristic attribute vector. According to the stranger social activity recommendation method based on the location attributes, the attraction of the surrounding environment of the holding location of the stranger social activity to the user is comprehensively considered, the final feature attribute vector is generated, the stranger social activity is recommended to the user according to the final feature attribute vector, the user experience is improved, and the stranger social activity recommendation method is beneficial to the development of stranger social activity.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a flowchart of a stranger social activity recommendation method based on location attributes according to a first embodiment of the present application;
fig. 2 is a schematic structural diagram of a stranger social activity recommendation system based on a location attribute according to a second embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The invention provides a stranger social activity recommendation method and system based on location attributes, and the method and system provided by the invention have the following steps that the holding locations of the social activities participated by the past registration of a user are extracted, the location attributes of the holding locations of the social activities are analyzed, and the location attributes are divided into four conditions: first, the regional attributes of the hosting location itself, such as whether it is in an downtown area or a remote area; secondly, the surrounding environment attribute is single or has a plurality of shopping, eating and entertainment places; third, a location attribute associated with the user activity space, such as a degree of overlap of the host location of the social activity in which the user participates with the user's place of residence or place of employment; and fourthly, the position concentration degree attribute, namely whether the social activities participated by the user are concentrated in a certain area or dispersed. Then, the user behavior related to the location attribute is determined, for example, whether the user stays at the holding location for shopping or leaves directly after participating in the social event for a period of time before and after participating in the social event. Adjusting the influence degree weight of various position attributes according to the user behavior; and finally recommending the social activity with similar characteristics of the position attribute of the holding position to the user.
Specifically, as shown in fig. 1, the method is a flowchart of a stranger social activity recommendation method based on a location attribute according to an embodiment of the present application. As can be seen from fig. 1, the stranger social activity recommendation method based on location attributes according to the embodiment may include the following steps:
s101: the method comprises the steps of obtaining holding position information of historical activities participated by a current user in a preset time period, position track information of the current user in an activity effective time, and daily activity space information of the current user.
The method is used for pushing stranger social activities to a user. Specifically, stranger social activities may be pushed to the user through the smart terminal, and the smart terminal mentioned in this embodiment and subsequent embodiments may be a smart phone, a tablet computer, a portable computer, and the like. The intelligent terminal can be provided with an APP (application), and a user can register an account in the APP to realize social contact among strangers.
When a stranger social activity needs to be recommended to a current user, the holding position information of a historical activity in which the current user participates within a preset time period, the position track information of the current user within an activity effective time period and the daily activity space information of the current user need to be acquired. The holding location information may include an area where the holding location itself is located, the area is divided into a downtown area, an urban and rural area and a suburban area, and a surrounding environment of the holding location, that is, how many places around the holding location and related places of activities are, where the related places may be shopping places, eating places or entertainment places. The position track information may be a position track of the current user within 1 hour before the event hosting time and 1.5 hours after the event ending time, and specifically, the position of the current user may be obtained from time to time through a mobile terminal carried by the user, and the position track is generated according to the obtained position. The daily activity space information may be a living area of the current user or a working area of the current user. The position of the current user can be obtained according to a preset time interval through a mobile terminal carried by the user, and the daily activity track of the current user is generated.
S102: and generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information.
Specifically, the location attribute vector in this embodiment may be a four-dimensional vector, including a region dimension of the hosting location itself, a surrounding environment dimension of the hosting location, a user activity space correlation dimension, and an activity location concentration dimension. Specifically, the distance between the hosting location and a preset reference point may be taken as a value of an area dimension of the hosting location itself, where the preset reference point may be a plurality of identified buildings or units located in a busy district in a predefined urban area, for example, beijing may take landmark places of the busy districts in the urban areas such as qinghua university, tianmen square, new visitors, and the like as the preset reference point, and then, according to the value of the distance between the hosting location and the nearest preset reference point, the value of the distance may be taken as the area dimension of the hosting location itself, for example, a historical event hosted in a stope museum, where the nearest preset reference point is the tianmen square, and the distance between the hosting location and the nearest preset reference point is 2KM, and it can be seen that the distance actually represents an attribute that the event hosting location is located in an downtown area, a rural area, and a suburban area. The number of places related to activities around the holding location is used as the value of the surrounding environment dimension of the holding location, that is, the total number of shopping places, eating places or entertainment places around the holding location is used as the value of the surrounding environment dimension of the holding location. The distance between the holding position and the daily activity space of the current user is used as the value of the correlation dimension of the activity space of the user, and specifically, the distance between the holding position of each activity and the residence or working place of the current user can be used as the value of the correlation dimension of the activity space of the user. Taking the average distance between the holding position and the holding position of the social events which are participated in by the user for a preset number of times before as an event position concentration degree dimension, wherein the preset number of times can be set manually or determined by experience values, and can be 5 or 10, for example; the average distance reflects the concentration of the hosting locations where the users participate in the social event, for example, if the users are concentrated in a small urban area and frequently participate in the social event, it is obvious that the value of the average distance is relatively small. The location attribute vector can accordingly be denoted as Vi=（Li，Ei，Ri，Ci). Wherein i represents a number of historical activities in which the current user is engaged. Assuming that the preset time period is one month, the number of historical activities participated by the current user in one month is 20, the value range of i is 1 to 20, and the position attribute vector of each historical activity is recorded as Vi=（Li，Ei，Ri，Ci），（i=1，2，3，……，20）。
S103: averaging the position attribute vectors to generate an average attribute vector of the current user.
After generating the location attribute vector of each historical activity, averaging the location attribute vectors, that is, obtaining an average value of the location attribute vectors in each dimension, and further generating an average attribute vector of the current user, where the average attribute vector may be recorded as V1，i=（L1，i，E1，i，R1，i，C1，i) Wherein X is1i=（X1，1+X1，2+X1，3+……+X1，20) /20, wherein X1iIs L1，i，E1，i，R1，i，C1，iOne of them. According to the above formula, an average attribute vector of the current user can be determined.
S104: and assigning a weight value to each dimension of the characteristic attribute vector to generate the characteristic attribute vector.
After the average attribute vector of the current user is generated, a weight value may be assigned to each dimension of the average attribute vector, so as to generate a feature attribute vector, which may be denoted as V2，i，V2，i=（aL1，i，bE1，i，cR1，i，dC1，i) Wherein a, b, c and d are weighted values. Because the influence of each dimension of the average attribute vector on the social activities of the user registering and the strangers is different, each dimension can be assigned with a weight value, and the dimension can be changed by changing the corresponding weight value to the influence of each dimension on the social activities of the user registering and the strangersThe influence value of the human social activity, for example, the time of the user in the activity effective time around the activity holding position is longer, which indicates that the user pays more attention to the surrounding environment of the activity holding position in the process of participating in the social activity, i.e. the magnitude of the correlation constant, so that the weight value b of the surrounding environment dimension of the holding position can be correspondingly increased, so that the probability that the social activity recommended to the user makes the user interested in participating is higher.
S105: and adjusting the corresponding dimension in the characteristic attribute vector according to the position track information to generate a final characteristic attribute vector.
After the feature attribute vector is generated, the corresponding dimension in the feature attribute vector can be adjusted according to the average value of the time of the peripheral activities of the activity holding position in the activity effective time of the historical activities in which the current user participates, and a final feature attribute vector is generated. Specifically, the threshold of the time of the peripheral activity of the activity holding position within the activity effective time of the user may be preset, and the threshold may be 0 to 45 minutes, 45 to 90 minutes, or 90 to 150 minutes. The activity effective time may be from 1 hour before the start of the activity to 1.5 hours after the end of the activity. If the average time of the peripheral activities of the activity holding position in the activity effective time of the user is within 0-45 minutes, reducing the value of the weight value b of the peripheral environment dimension of the holding position, if the average time of the peripheral activities of the activity holding position in the activity effective time of the user is within 45-90 minutes, keeping the value of the weight value b of the peripheral environment dimension of the holding position unchanged, if the average time of the peripheral activities of the activity holding position in the activity effective time of the user is within 90-150 minutes, increasing the value of the weight value b of the peripheral environment dimension of the holding position, and generating a final characteristic attribute vector, wherein the final characteristic attribute vector can be recorded as V3，i=（aL1，i，b1E1，i，cR1，i，dC1，i) Wherein b is1And b is the value after adjustment.
S106: and recommending related stranger social activities to the current user according to the final characteristic attribute vector.
After the final characteristic attribute vector is generated, a preset number of alternative stranger social activities can be screened out according to the interests and hobbies of the user, the position attribute characteristic vector of each alternative stranger social activity is calculated, the position attribute characteristic vector can also be a vector comprising the regional dimension of the holding position, the surrounding environment dimension of the holding position, the user activity space correlation dimension and the activity position concentration dimension, and each dimension can also be provided with a corresponding weight value. After the position attribute feature vector of each candidate stranger social activity is calculated, the distance between the position attribute feature vector and the final feature attribute vector is further calculated, the candidate stranger social activities are ranked according to the calculation result, the candidate stranger social activities are recommended to the current user according to the ranking result, and specifically, the candidate stranger social activities ranked 5 can be pushed to the current user according to actual needs.
According to the stranger social activity recommendation method based on the location attributes, the attraction of the surrounding environment of the holding location of the stranger social activity to the user is comprehensively considered, the final feature attribute vector is generated, the stranger social activity is recommended to the user according to the final feature attribute vector, the user experience is improved, and the stranger social activity recommendation method is beneficial to the development of stranger social activity.
Fig. 2 is a schematic structural diagram of a stranger social activity recommendation system based on a location attribute according to an embodiment of the present application. The stranger social activity recommendation system based on the location attribute of the embodiment may include:
the information acquisition module 201 is configured to acquire the holding position information of the historical activities in which the current user participates within a preset time period, the position track information of the current user within an activity effective time, and the daily activity space information of the current user.
When a stranger social activity needs to be recommended to a current user, the holding position information of a historical activity in which the current user participates within a preset time period, the position track information of the current user within an activity effective time period and the daily activity space information of the current user need to be acquired. The holding location information may include an area where the holding location itself is located, the area is divided into a downtown area, an urban and rural area and a suburban area, and a surrounding environment of the holding location, that is, how many places around the holding location and related places of activities are, where the related places may be shopping places, eating places or entertainment places. The position track information may be a position track of the current user within 1 hour before the event hosting time and 1.5 hours after the event ending time, and specifically, the position of the current user may be obtained from time to time through a mobile terminal carried by the user, and the position track is generated according to the obtained position. The daily activity space information may be a living area of the current user or a working area of the current user. The position of the current user can be obtained according to a preset time interval through a mobile terminal carried by the user, and the daily activity track of the current user is generated.
And the position attribute vector generating module 202 is configured to generate a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity spatial information.
Specifically, the location attribute vector in this embodiment may be a four-dimensional vector, including a region dimension of the hosting location itself, a surrounding environment dimension of the hosting location, a user activity space correlation dimension, and an activity location concentration dimension. Specifically, the distance between the hosting location and a preset reference point may be used as a value of the area dimension of the hosting location itself, where the preset reference point may be a plurality of identified buildings or units predefined to be located in a busy section of an urban area, and a distance between the hosting location and a closest preset reference point is used as a value of the area dimension of the hosting location itself. The number of places related to activities around the holding location is used as the value of the surrounding environment dimension of the holding location, that is, the total number of shopping places, eating places or casinos around the holding location is used as the value of the surrounding environment dimension of the holding location. Taking the distance between the holding position and the daily activity space of the current user as the value of the correlation dimension of the activity space of the user,specifically, the distance between the holding position of each event and the residence or working place of the current user may be used as the value of the spatial correlation dimension of the user event. The average distance between the holding position and the holding position of the social event of a preset number of times that the user has previously participated in is used as the activity position concentration degree dimension, and the preset number of times can be set manually or determined by experience values, for example, 15 or 20 can be used. The location attribute vector can accordingly be denoted as Vi=（Li，Ei，Ri，Ci). Wherein i represents a number of historical activities in which the current user is engaged. Assuming that the preset time period is one month, the number of historical activities the current user participates in one month is 20, i =20, and the location attribute vector of each historical activity is recorded as Vi=（Li，Ei，Ri，Ci），（i=1，2，3，……，20）。
An average attribute vector generating module 203, configured to average the location attribute vectors to generate an average attribute vector of the current user.
After generating the location attribute vector of each historical activity, averaging the location attribute vectors, that is, obtaining an average value of the location attribute vectors in each dimension, and further generating an average attribute vector of the current user, where the average attribute vector may be recorded as V1，i=（L1，i，E1，i，R1，i，C1，i) Wherein X is1i=（X1，1+X1，2+X1，3+……+X1，20) /20, wherein X1iIs L1，i，E1，i，R1，i，C1，iOne of them. According to the above formula, an average attribute vector of the current user can be determined.
The feature attribute vector generation module 204 assigns a weight value to each dimension of the average attribute vector to generate a feature attribute vector.
After generating the average attribute vector of the current user, each dimension of the average attribute vector may be assigned a weightWeight value, and then generating a feature attribute vector, which can be denoted as V2，i，V2，i=（aL1，i，bE1，i，cR1，i，dC1，i) Wherein a, b, c and d are weighted values. Because the influence of each dimension of the average attribute vector on the social activities of the user registering and participating strangers is different, a weight value can be distributed to each dimension, and the influence value of each dimension on the social activities of the user registering and participating strangers is changed by changing the size of the corresponding weight value, for example, the time of the user holding the peripheral activities of the activity holding position in the activity effective time is longer, which indicates that the user pays more attention to the peripheral environment of the activity holding position in the process of participating in the social activities, namely the number of the related constants, so that the weight value b of the peripheral environment dimension of the holding position can be correspondingly increased, and the social activities recommended to the user enable the probability of the user interested in participating to be larger.
A final feature attribute vector generation module 205, configured to adjust a corresponding dimension in the feature attribute vector according to the position trajectory information, and generate a final feature attribute vector.
After the feature attribute vector is generated, the corresponding dimension in the feature attribute vector can be adjusted according to the average value of the time of the peripheral activities of the activity holding position in the activity effective time of the historical activities in which the current user participates, and a final feature attribute vector is generated. Specifically, the threshold of the time of the peripheral activity of the activity holding position within the activity effective time of the user may be preset, and the threshold may be 0 to 45 minutes, 45 to 90 minutes, or 90 to 150 minutes. The activity effective time may be from 1 hour before the start of the activity to 1.5 hours after the end of the activity. If the average time of the activities around the activity holding position in the activity effective time of the user is within 0-45 minutes, reducing the value of the weight value b of the surrounding environment dimension of the holding position, if the average time of the activities around the activity holding position in the activity effective time of the user is within 45-90 minutes, keeping the value of the weight value b of the surrounding environment dimension of the holding position unchanged, and if the average time of the activities around the activity holding position in the activity effective time of the user is within 45-90 minutes, keeping the value of the weight value b of the surrounding environment dimension of the activity holding position unchangedIf the average time of the activity is within 90-150 minutes, increasing the value of the weight value b of the surrounding environment dimension of the holding position, and generating a final characteristic attribute vector which can be marked as V3，i=（aL1，i，b1E1，i，cR1，i，dC1，i) Wherein b is1And b is the value after adjustment.
And the stranger social activity recommendation module 206 is configured to recommend relevant stranger social activities to the current user according to the final feature attribute vector.
After the final characteristic attribute vector is generated, a preset number of alternative stranger social activities can be screened out according to the interests and hobbies of the user, and a position attribute characteristic vector of each alternative stranger social activity is calculated, wherein the position attribute characteristic vector can also be a vector comprising the regional dimension of the holding position, the surrounding environment dimension of the holding position, the user activity space correlation dimension with the current user and the activity position concentration dimension with the current user, and each dimension can also be provided with a corresponding weight value. After the position attribute feature vector of each candidate stranger social activity is calculated, the vector distance between the position attribute feature vector and the final feature attribute vector of the current user is further calculated, the social activities of the candidate strangers are ranked according to the calculation result, the smaller the vector distance between the position attribute feature vector of the social activity of the candidate strangers and the final feature attribute vector of the current user is, the more the ranking is, the social activity of the candidate strangers is recommended to the current user according to the ranking result, and specifically, the ranked social activity of the top 5 candidate strangers can be pushed to the current user according to actual needs.
The stranger social activity recommendation system based on the location attribute in the embodiment of the application can achieve the technical effect similar to that of the method embodiment, and is not repeated here.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (6)
1. A stranger social activity recommendation method based on location attributes is characterized by comprising the following steps:
acquiring the handling position information of historical activities participated by a current user in a preset time period, the position track information of the current user in an activity effective time and the daily activity space information of the current user; wherein the location information of the historical event comprises: the method comprises the following steps of (1) hosting the type of an area where a position is located, wherein the area is divided into a downtown area, an urban and rural combined area and a suburban area; the information of the surrounding environment of the holding position, namely the number of the surrounding of the holding position and the related places of the event; the position track information of the current user in the activity effective time is the staying time of the current user in a preset range of the activity holding position;
generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information; the location attribute vector includes: the method comprises the following steps of (1) carrying out regional dimension of a position, carrying out peripheral environment dimension of the position, user activity space correlation dimension and activity position concentration degree dimension; taking the distance between the holding position and a preset reference point as a value of the regional dimension of the holding position, taking the number of places related to the activities around the holding position as a value of the surrounding environment dimension of the holding position, taking the distance between the holding position and the daily activity space of the current user as a value of the activity space correlation dimension of the user, and taking the average distance between the holding position and the holding position of the social activities which are participated by the user for a preset number of times as an activity position concentration dimension;
averaging the position attribute vectors to generate an average attribute vector of the current user;
distributing a weight value to each dimension of the average attribute vector to generate a characteristic attribute vector;
adjusting corresponding dimensions in the feature attribute vector according to the position track information to generate a final feature attribute vector;
and recommending related stranger social activities to the current user according to the final characteristic attribute vector.
2. The method of claim 1, wherein the adjusting the corresponding dimension in the feature attribute vector according to the position trajectory information to generate a final feature attribute vector comprises:
and adjusting the weight value of the surrounding environment dimension of the holding position in the characteristic attribute vector according to the average time of the current user staying in the preset range of the activity holding position within the activity effective time to generate a final characteristic attribute vector.
3. The method of claim 2, wherein recommending relevant stranger social activities to the current user according to the final feature attribute vector comprises:
screening out a preset number of alternative stranger social activities according to the interest and hobbies of the user, calculating a position attribute feature vector of each alternative stranger social activity, calculating the distance between the feature vector and the final feature attribute vector, sequencing the alternative stranger social activities according to the calculation result, and recommending the alternative stranger social activities to the current user according to the sequencing result.
4. A stranger social activity recommendation system based on location attributes, comprising:
the information acquisition module is used for acquiring the handling position information of the historical activities participated by the current user in a preset time period, the position track information of the current user in the activity effective time and the daily activity space information of the current user; wherein the location information of the historical event comprises: the method comprises the following steps of (1) hosting the type of an area where a position is located, wherein the area is divided into a downtown area, an urban and rural combined area and a suburban area; the information of the surrounding environment of the holding position, namely the number of the surrounding of the holding position and the related places of the event; the position track information of the current user in the activity effective time is the staying time of the current user in a preset range of the activity holding position;
the position attribute vector generating module is used for generating a position attribute vector corresponding to each historical activity according to the holding position information and the daily activity space information; the location attribute vector includes: the method comprises the following steps of (1) carrying out regional dimension of a position, carrying out peripheral environment dimension of the position, user activity space correlation dimension and activity position concentration degree dimension; taking the distance between the holding position and a preset reference point as a value of the regional dimension of the holding position, taking the number of places related to the activities around the holding position as a value of the surrounding environment dimension of the holding position, taking the distance between the holding position and the daily activity space of the current user as a value of the activity space correlation dimension of the user, and taking the average distance between the holding position and the holding position of the social activities which are participated by the user for a preset number of times as an activity position concentration dimension;
the average attribute vector generation module is used for averaging the position attribute vectors to generate an average attribute vector of the current user;
the characteristic attribute vector generation module is used for distributing a weight value for each dimension of the average attribute vector to generate a characteristic attribute vector;
the final characteristic attribute vector generation module is used for adjusting corresponding dimensions in the characteristic attribute vectors according to the position track information to generate final characteristic attribute vectors;
and the stranger social activity recommending module is used for recommending relevant stranger social activities to the current user according to the final characteristic attribute vector.
5. The system of claim 4, wherein the final feature attribute vector generation module is specifically configured to:
and adjusting the weight value of the surrounding environment dimension of the holding position in the characteristic attribute vector according to the average time of the current user staying in the preset range of the activity holding position within the activity effective time to generate a final characteristic attribute vector.
6. The system of claim 5, wherein the stranger social activity recommendation module is specifically configured to:
screening out a preset number of alternative stranger social activities according to the interest and hobbies of the user, calculating a position attribute feature vector of each alternative stranger social activity, calculating the distance between the feature vector and the final feature attribute vector, sequencing the alternative stranger social activities according to the calculation result, and recommending the alternative stranger social activities to the current user according to the sequencing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811442178.6A CN109522491B (en) | 2018-11-29 | 2018-11-29 | Stranger social activity recommendation method and system based on location attribute |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811442178.6A CN109522491B (en) | 2018-11-29 | 2018-11-29 | Stranger social activity recommendation method and system based on location attribute |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109522491A CN109522491A (en) | 2019-03-26 |
| CN109522491B true CN109522491B (en) | 2020-07-31 |
Family
ID=65794343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811442178.6A Active CN109522491B (en) | 2018-11-29 | 2018-11-29 | Stranger social activity recommendation method and system based on location attribute |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109522491B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241415B (en) * | 2019-12-28 | 2023-07-21 | 四川文理学院 | Recommendation method integrating multi-factor social activities |
| CN112307357A (en) * | 2020-10-30 | 2021-02-02 | 上海连尚网络科技有限公司 | Social method and device for strangers |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838834A (en) * | 2014-02-25 | 2014-06-04 | 北京智谷睿拓技术服务有限公司 | Mentioning recommending method, information processing method and system |
| CN103942310A (en) * | 2014-04-18 | 2014-07-23 | 厦门雅迅网络股份有限公司 | User behavior similarity mining method based on space-time mode |
| CN106776928A (en) * | 2016-12-01 | 2017-05-31 | 重庆大学 | Recommend method in position based on internal memory Computational frame, fusion social environment and space-time data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354196B (en) * | 2014-08-19 | 2019-06-21 | 北京羽扇智信息科技有限公司 | Information-pushing method and information push-delivery apparatus |
| CN104765873B (en) * | 2015-04-24 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | User's similarity determines method and apparatus |
| KR102535044B1 (en) * | 2015-12-08 | 2023-05-23 | 삼성전자주식회사 | Terminal, server and method for suggesting event thereof |
| CN105912702A (en) * | 2016-04-26 | 2016-08-31 | 南京酷派软件技术有限公司 | Position recommendation method and system |
| EP3401811A1 (en) * | 2016-05-18 | 2018-11-14 | Rovi Guides, Inc. | Recommending media content based on the trajectory of the user |
-
2018
- 2018-11-29 CN CN201811442178.6A patent/CN109522491B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838834A (en) * | 2014-02-25 | 2014-06-04 | 北京智谷睿拓技术服务有限公司 | Mentioning recommending method, information processing method and system |
| CN103942310A (en) * | 2014-04-18 | 2014-07-23 | 厦门雅迅网络股份有限公司 | User behavior similarity mining method based on space-time mode |
| CN106776928A (en) * | 2016-12-01 | 2017-05-31 | 重庆大学 | Recommend method in position based on internal memory Computational frame, fusion social environment and space-time data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109522491A (en) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11272020B2 (en) | Social network for mapping gradations to target intent | |
| US11005955B2 (en) | Social network for monitoring user activity | |
| US9918319B2 (en) | System and process for location-based information retrieval | |
| US8108414B2 (en) | Dynamic location-based social networking | |
| Cramer et al. | Performing a check-in: emerging practices, norms and'conflicts' in location-sharing using foursquare | |
| Hampton et al. | The social life of wireless urban spaces: Internet use, social networks, and the public realm | |
| US8892130B2 (en) | System for enabling interactive socialization of users at a location or geographic radius thereof | |
| US20120259791A1 (en) | System and method for social networking | |
| US20090248607A1 (en) | Method to determine a subgroup of users | |
| US20110004501A1 (en) | Methods and Apparatus for Automatically Generating Social Events | |
| JP2003523565A (en) | An Internet system that connects client travelers to geographically relevant data | |
| KR102122389B1 (en) | System and method for providing contents service based on location information | |
| WO2009070138A1 (en) | Dynamic geosocial networking | |
| CN109522491B (en) | Stranger social activity recommendation method and system based on location attribute | |
| CN109670107B (en) | Stranger social activity recommendation method and system based on big interest data | |
| Van Haperen et al. | Mediated interaction rituals: a geography of everyday life and contention in Black Lives Matter | |
| Schmidt et al. | Offline World: the internet as Social Infrastructure among the unconnected in Quasi-rural Illinois | |
| US20130185323A1 (en) | Social network service | |
| Schoon | Dragging young people down the drain: the mobile phone, gossip mobile website Outoilet and the creation of a mobile ghetto | |
| CN109241202A (en) | A kind of stranger's social activity user matching method and system based on cluster | |
| Zalega | Consumption cocooning in consumer behaviour of polish seniors (Report from Own Research) | |
| KR101806454B1 (en) | Helper matching system based on location's information | |
| US20180285930A1 (en) | Service System To Determine Journeys Based On Companion Relationship | |
| JP7178063B1 (en) | Information processing device, information processing method and information processing program | |
| Setiawan et al. | Characteristic of Edelweiss Park Agrotourism Visitorsm in the Covid-19 Pandemic Time |
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 |