CN112232845B - Method and device for predicting user behavior preference based on user position - Google Patents
Method and device for predicting user behavior preference based on user position Download PDFInfo
- Publication number
- CN112232845B CN112232845B CN201910635221.9A CN201910635221A CN112232845B CN 112232845 B CN112232845 B CN 112232845B CN 201910635221 A CN201910635221 A CN 201910635221A CN 112232845 B CN112232845 B CN 112232845B
- Authority
- CN
- China
- Prior art keywords
- target
- data
- point
- interest
- user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012216 screening Methods 0.000 claims abstract description 28
- 230000006399 behavior Effects 0.000 claims description 92
- 238000004891 communication Methods 0.000 claims description 15
- 230000003542 behavioural effect Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 10
- 238000012937 correction Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000008094 contradictory effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 101100343585 Arabidopsis thaliana LNG1 gene Proteins 0.000 description 1
- 101100343586 Arabidopsis thaliana LNG2 gene Proteins 0.000 description 1
- 102100038204 Large neutral amino acids transporter small subunit 1 Human genes 0.000 description 1
- 102100038235 Large neutral amino acids transporter small subunit 2 Human genes 0.000 description 1
- 108091006232 SLC7A5 Proteins 0.000 description 1
- 108091006238 SLC7A8 Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Abstract
The invention discloses a method and a device for predicting user behavior preference based on user position, wherein the method comprises the following steps: acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data; acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data; and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data. The invention can combine the personal position data and the GIS data, is not limited to a specific vertical field, fully utilizes the GIS data to carry out diversified prediction, and gets rid of the dependence on a large-scale crowd data set.
Description
Technical Field
The invention relates to the technical field of user behavior preference prediction, in particular to a method and a device for predicting user behavior preference based on a user position.
Background
With the rapid development of information technology and mobile internet, personalized services are becoming a manifestation of lean services and are becoming more and more perceived by enterprises, so that more and more enterprises begin to try to acquire more information of clients through various approaches, conduct deeper research on the clients, try to predict future demands of the clients and infer identity characteristics of the clients. Prediction of behavioral preferences and identity features is a hotspot in research, especially today where data mining, machine learning, artificial intelligence, cloud computing are hot.
The existing personal behavior preference and identity feature prediction methods are mostly limited to prediction in a fixed vertical field, the predicted departure point is a scene created in a certain vertical field, the prediction of a certain requirement is made based on the scene, and all predictions firstly have a specific scene, such as an e-commerce, and online reading. In a specific implementation algorithm, taking collaborative recommendation as an example, because the prediction basis of the collaborative recommendation is a large-scale crowd data set, the problem of whether the crowd data set is high in quality exists. The high quality is not limited to the huge or not of the crowd data set, and additional requirements are required for different specific implementations, such as sparsity of data, the crowd base is large enough, but individuals generating behaviors are few, and most crowd data sets have the characteristic in reality, so sparsity is also a problem widely faced by the algorithms.
Disclosure of Invention
The present invention has been made in view of the above problems, and it is an object of the present invention to provide a method and apparatus for predicting user behavior preferences based on user location that overcomes or at least partially solves the above problems.
According to one aspect of the present invention, there is provided a method of predicting user behavior preferences based on user location, comprising:
Acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data;
acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data;
and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Optionally, the personal location data comprises: slicing position data corresponding to the plurality of time slices, respectively;
screening at least one key location point corresponding to the target user according to the residence time length and/or residence frequency corresponding to each location point contained in the personal location data comprises:
determining the stay time length of each position point contained in each piece of position data, and screening the position points with the stay time length larger than a preset time length threshold value as candidate position points in the piece of position data;
according to the occurrence times of each candidate position point in each piece of position data, determining the stay frequency of each candidate position point, and screening the candidate position points with stay frequency not smaller than a preset frequency threshold as key position points.
Optionally, predicting the user behavior preference of the target user according to the point of interest corresponding to the target GIS data includes:
when the interest points corresponding to the target GIS data are multiple, judging whether each interest point is matched with a preset prediction target;
and determining the interest point matched with the preset prediction target as a target interest point, and predicting the user behavior preference of the target user according to the target interest point.
Optionally, predicting the user behavior preference of the target user according to the point of interest corresponding to the target GIS data includes:
when the interest points corresponding to the target GIS data are multiple, calculating the distance between the interest points and the key position points;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, predicting the user behavior preference of the target user according to the point of interest corresponding to the target GIS data includes:
when the interest points corresponding to the target GIS data are multiple, judging whether the attribute of the interest points meets a preset resident attribute rule or not;
If yes, the interest point is determined to be a target interest point, and the user behavior preference of the target user is predicted according to the target interest point.
Optionally, predicting the user behavior preference of the target user according to the point of interest corresponding to the target GIS data includes:
when the interest points corresponding to the target GIS data are multiple, judging whether inter-contradiction logic exists between the interest points;
if yes, screening target interest points according to the distances between the interest points and the key position points and the weights corresponding to the interest points, and predicting user behavior preference of the target user according to the target interest points.
Optionally, when the plurality of interest points corresponding to the target GIS data are plural, before determining whether the inter-contradiction logic exists between the interest points, further comprising:
and presetting weights corresponding to the interest points according to the people flow corresponding to the interest points and/or the distance between the interest points and the key position points.
According to one aspect of the present invention, there is provided an apparatus for predicting user behavior preferences based on user location, comprising:
the key position point screening module is suitable for acquiring personal position data corresponding to the target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data;
The GIS data and interest point acquisition module is suitable for acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data;
and the behavior preference prediction module is suitable for predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Optionally, the personal location data comprises: slicing position data corresponding to the plurality of time slices, respectively;
the keypoint screening module is adapted to:
determining the stay time length of each position point contained in each piece of position data, and screening the position points with the stay time length larger than a preset time length threshold value as candidate position points in the piece of position data;
according to the occurrence times of each candidate position point in each piece of position data, determining the stay frequency of each candidate position point, and screening the candidate position points with stay frequency not smaller than a preset frequency threshold as key position points.
Optionally, the behavioral preference prediction module is adapted to:
when the interest points corresponding to the target GIS data are multiple, judging whether each interest point is matched with a preset prediction target;
and determining the interest point matched with the preset prediction target as a target interest point, and predicting the user behavior preference of the target user according to the target interest point.
Optionally, the behavioral preference prediction module is adapted to:
when the interest points corresponding to the target GIS data are multiple, calculating the distance between the interest points and the key position points;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behavioral preference prediction module is adapted to:
when the interest points corresponding to the target GIS data are multiple, judging whether the attribute of the interest points meets a preset resident attribute rule or not;
if yes, the interest point is determined to be a target interest point, and the user behavior preference of the target user is predicted according to the target interest point.
Optionally, the behavioral preference prediction module is adapted to:
when the interest points corresponding to the target GIS data are multiple, judging whether inter-contradiction logic exists between the interest points;
if yes, screening target interest points according to the distances between the interest points and the key position points and the weights corresponding to the interest points, and predicting user behavior preference of the target user according to the target interest points.
Optionally, the behavioral preference prediction module is adapted to:
and presetting weights corresponding to the interest points according to the people flow corresponding to the interest points and/or the distance between the interest points and the key position points.
According to still another aspect of the present invention, there is provided an electronic apparatus including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the method for predicting the user behavior preference based on the user position.
According to still another aspect of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the above-described method of predicting user behavior preferences based on user location.
In summary, the invention discloses a method and a device for predicting user behavior preference based on user position. Firstly, personal position data corresponding to a target user is obtained, and at least one key position point corresponding to the target user is screened according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data. Then, target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data are acquired. And finally, predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data. The invention can combine the personal position data and the GIS data, fully utilize the GIS data to carry out diversified prediction, is not limited to a specific vertical field, and gets rid of the dependence on a large-scale crowd data set.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 illustrates a flow chart of a method of predicting user behavior preferences based on user location in accordance with a first embodiment;
FIG. 2 illustrates a flow chart of a method of predicting user behavior preferences based on user location in accordance with a second embodiment;
FIG. 3 shows a block diagram of an apparatus for predicting user behavior preferences based on user location in accordance with a third embodiment;
fig. 4 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention;
FIG. 5 illustrates a user location trajectory abstract diagram;
FIG. 6 illustrates a schematic representation of a coincident locus key location point refinement;
FIG. 7 shows a shortest distance matching schematic;
fig. 8 shows a flowchart of the mutual contradiction determination correction processing.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example 1
Fig. 1 shows a flowchart of a method of predicting user behavior preferences based on user location according to a first embodiment. As shown in fig. 1, the method comprises the steps of:
step S110: and acquiring personal position data corresponding to the target user, and screening at least one key position point corresponding to the target user according to the stay time and/or the stay frequency corresponding to each position point contained in the personal position data.
The personal position data corresponding to the target user refers to longitude and latitude data of each position point where the target user is located.
Specifically, whether the stay time corresponding to each position point contained in the personal position data is greater than a preset time threshold value or not and/or whether the stay frequency corresponding to each position point contained in the personal position data is greater than a preset frequency threshold value or not are judged. If yes, determining the position points contained in the personal position data as key position points corresponding to the target user. Wherein at least one of the number of key location points is described above.
Step S120: and acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data.
The GIS data refers to data of a certain position point obtained from a geographic information system. Specifically, longitude and latitude data of the key position point are matched with longitude and latitude data in the GIS data, and the GIS data successfully matched with the longitude and latitude data is determined to be target GIS data corresponding to the key position point. Wherein, a certain GIS data contains at least one interest point. And determining interest points corresponding to the target GIS data according to the target GIS data corresponding to the key position points. The interest points refer to topography, administrative division, regional functions, business service areas and the like near a certain position point in the geographic information system. It should be noted that successful matching of the longitude and latitude data means that the errors of the longitude and latitude data of the key position point and the longitude and latitude data in the GIS data are within a preset error range.
Step S130: and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Specifically, the user behavior preference is presumed according to the type of the interest point corresponding to the target GIS data, the stay time length corresponding to the interest point and the stay time period. For example, the type of the interest point is cinema, the stay time corresponding to the interest point is 3 hours, the stay time is Saturday afternoon, the stay frequency is 4 times a month, and the target user can be presumed to be a movie fan, and is used to go to the cinema on the weekend to watch the movie. The user behavior preference is used for describing characteristics of user preference, occupation, identity and the like, and any content related to the user behavior can be used as the user behavior preference. For example, the user behavior preferences in the present invention specifically include: behavioral preferences and identity characteristics (e.g., profession, etc.).
In summary, the method combines the personal position data and the GIS data, makes full use of the GIS data to conduct diversified prediction, is not limited to a specific vertical field, and gets rid of dependence on a large-scale crowd data set.
Example two
Fig. 2 shows a flow chart of a method of predicting user behavior preferences based on user location according to a second embodiment. As shown in fig. 2, the method comprises the steps of:
Step S210: and acquiring personal position data corresponding to the target user, and screening at least one key position point corresponding to the target user according to the stay time and/or the stay frequency corresponding to each position point contained in the personal position data.
The personal position data corresponding to the target user refers to longitude and latitude data of each position point where the target user is located. The personal location data may come from a variety of sources including, but not limited to, global satellite positioning system (Global Positioning System, GPS), beidou satellite navigation system (BeiDou Navigation Satellite System, BDS), carrier base station positioning.
Specifically, the above-mentioned personal position data includes: and slice position data corresponding to the plurality of time slices, respectively. For example, the personal position data is position information of each position point where the target user is located within 10 days, the time slicing is preset to be 1 day, and the personal position data is divided into 10 pieces of sliced position data corresponding to the time slicing. For example, the date of day 1 is 2019, 2, 17, and 2019, 2, 17 corresponds to one piece of position data.
In the implementation, firstly, the stay time length of each position point contained in each piece of position data is determined, and the position points with the stay time length larger than a preset time length threshold value are screened as candidate position points in the piece of position data. For example, fig. 5 shows an abstract view of a user location track, and as shown in fig. 5, in the sliced location data corresponding to the year 2 and the month 17 of 2019, the preset time period threshold is 0.5 hour. The residence time of the position point A is 1 hour and 3.3 hours, the residence time of the position point B is 3 hours and 4 hours, the residence time of the position point C is 1.5 hours, and the residence time of the position point D is 1 hour. The dwell time of the position point A, B, C, D is longer than a preset time threshold, and the position point A, B, C, D is screened as a candidate position point in the slice position data. Further, determining a user position track under the time slicing corresponding to the slicing position data according to the candidate position points in the slicing position data.
And then, according to the occurrence times of each candidate position point in each piece of position data, determining the stay frequency of each candidate position point, and screening the candidate position points with the stay frequency not smaller than a preset frequency threshold as key position points. Wherein, at least one of the above-mentioned screened key position points. For example, the preset frequency threshold is the number of time slices, and in the position data of each slice corresponding to 10 time slices, the number of occurrences of the position point a is 10, the number of occurrences of the position point B is 10, the number of occurrences of the position point C is 9, and the number of occurrences of the position point D is 10. The dwell frequency of the location point A, B, D is not less than the preset frequency threshold for 10 times, and the location point A, B, D is screened as a key location point corresponding to the target user. Further, a user coincidence trajectory is determined from the key location points corresponding to the target user.
Step S220: and acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data.
The key location points corresponding to the target user determined in step S210 may be one or more. GIS data refers to data of a certain position point obtained from a geographic information system.
Specifically, longitude and latitude data of the key position point are matched with longitude and latitude data in the GIS data, and the GIS data successfully matched with the longitude and latitude data is determined to be target GIS data corresponding to the key position point. Wherein, a certain GIS data contains at least one interest point. And determining interest points corresponding to the target GIS data according to the target GIS data corresponding to the key position points. The interest points refer to topography, administrative division, regional functions, business service areas and the like near a certain position point in the geographic information system. It should be noted that successful matching of the longitude and latitude data means that the errors of the longitude and latitude data of the key position point and the longitude and latitude data in the GIS data are within a preset error range.
Step S230: and screening target interest points from a plurality of interest points corresponding to the target GIS data.
Specifically, the target points of interest may be screened in at least one of four ways:
the first mode specifically comprises: when a plurality of interest points corresponding to certain target GIS data are provided, judging whether each interest point is matched with a preset prediction target, and determining the interest point matched with the preset prediction target as a target interest point. For example, the preset predictive goal is to infer the occupation, income, hobbies of the target user. After a plurality of interest points corresponding to a certain target GIS data are acquired, the interest points which are not associated with professions, incomes and hobbies are screened out, for example, the park type interest points are not associated with professions, incomes and hobbies, and the park type interest points can be screened out.
The second mode specifically comprises: when a plurality of interest points corresponding to certain target GIS data are provided, calculating the distance between the interest points and the key position points, judging whether the distance between the interest points and the key position points meets a preset distance matching rule, and determining the interest points meeting the preset distance matching rule as target interest points. In the implementation, when the latitude and longitude data of the key location point in step S220 cannot be completely matched with the latitude and longitude data in the GIS data, that is, the latitude and longitude data of the key location point and the latitude and longitude data in the GIS data have errors within a preset error range, the distance between the interest point corresponding to the target GIS data and the key location point is calculated. For example, the preset distance matching rule is to determine the interest point with the shortest distance from the key position point as the target interest point. Fig. 7 shows a schematic diagram of shortest distance matching, as shown in fig. 7, the distance between the interest point a, b, c, d, e and the key position point is calculated, the interest point with the shortest distance to the key position point is selected, and the interest point (i.e. the interest point a) with the shortest distance is identified as the target interest point.
The third mode specifically includes: judging whether the attribute of the interest point meets a preset resident attribute rule, and if the attribute of the interest point meets the preset resident attribute rule, determining the interest point as a target interest point, wherein the preset resident attribute rule specifically comprises: the stay time length corresponding to the interest point is larger than a preset resident time length threshold value, and the stay time period meets a preset resident time period range. In specific implementation, the preset residence time threshold is 7 hours, and the preset residence time period ranges from 8 pm to 8 pm. For example, the stay time corresponding to the restaurant type interest point a is 12 hours, the stay time is 9 in the morning to 9 in the evening, the restaurant type interest point a meets the preset resident attribute rule, the restaurant type interest point a is determined as the target interest point, and the target user can be presumed to work in the restaurant according to the restaurant type interest point a. It should be noted that, the specific meaning of the resident attribute rule is not limited in this embodiment, and those skilled in the art may determine the specific meaning of the resident attribute rule in other manners.
The fourth mode specifically includes: when a plurality of interest points corresponding to a certain target GIS data exist, judging whether the interest points are mutually contradicted or not, and if yes, screening the target interest points according to the distance between the interest points and the key position points and the weight corresponding to the interest points. When a plurality of interest points corresponding to certain target GIS data are provided, the weight corresponding to the interest points is preset. In implementation, for example, the type of the point of interest b is a high-income user, the type of the point of interest c is a low-income user, and the point of interest b and the point of interest c corresponding to a certain target GIS data are against logic. Comparing the distance between the interest point b and the key position point with the distance between the interest point c and the key position point, and eliminating the interest points with larger distances to eliminate the contradiction logic. If the distances between the interest point b and the interest point c and the key position point are the same, comparing the weights of the interest point b and the interest point c, and eliminating the interest points with lower weights to eliminate the contradictory logic. In addition, when the interest points corresponding to the different key position points are in the mutually contradictory logic, the process can be repeated, the interest points which are far away from the key position points and have lighter weights can be removed, and finally the mutually contradictory logic is eliminated. It should be noted that, the specific method of eliminating the mutual paradox logic is not limited in this embodiment, and those skilled in the art may adopt other methods to eliminate the mutual paradox logic between multiple interest points.
Step S240: and predicting the user behavior preference of the target user according to the target interest points.
Specifically, the user behavior preference is presumed according to the type of the target interest point, the stay time length corresponding to the target interest point and the stay time period. For example, the type of the target interest point is cinema, the stay time corresponding to the target interest point is 3 hours, the stay time period is Saturday afternoon, and the stay frequency is 4 times a month, so that the target user can be presumed to be a movie fan, and is used to go to the cinema on the weekend to watch the movie.
In summary, the method combines the personal position data and the GIS data, and predicts the user behavior preference of the target user from a plurality of dimensions such as the distance between the interest point and the key position point, the interest point weight, the stay time of the target user and the like. The method has the advantages that the crowd data set in a certain scene is not relied on as a prediction basis, the GIS data is fully utilized for diversified prediction, and the data quality problem of the crowd data set on a large scale is avoided.
The method of the invention is described in a specific example as follows:
step one: personal location data cleaning.
The position behavior of the same person in a period of time is integrated, the position behavior track of the person is sketched, the sketching of the position behavior track can be realized by combining a GIS system, the position behavior track can also be separated from the GIS system, the aim of sketching the person track at the stage is to extract effective information from massive personal position data, clear out data with lower information value in the position data, and extract key position data for use in the subsequent steps. While outlining the personal position behavior trace, processing the position data is added with time dimension data, such as the position of longitude LNG1 and latitude LAT1 appearing in 2019, 2 months, 17 days, 9:00, stay for 6.5 hours, the position of longitude LNG2 and latitude LAT2 appearing in 2019, 2 months, 25 days, 15:30, stay for 3 hours.
As shown in fig. 5, fig. 5 shows a user location track abstraction, taking as an example a location behavior track of a person observed periodically on a day, the person location data abstraction can be refined to several important fixed points. Other redundant location data should be cleaned up at the step of personal location data cleaning, for example, someone goes from home to company in the morning, and location change data on the way does not help the extraction of personal key location data, and the data has the characteristics of rapid change of geographic location and short stay time of a single location. After the redundant position data is cleaned, the core position point A, B, C, D is abstracted, the geographic coordinates of each core position and the time of changing from other key positions to the current position are recorded, the stay time of the target at the key position after continuous monitoring is continuously monitored, and finally the track is abstracted according to the data recorded in one day.
The daily position behavior data are monitored according to the method, the superposition degree is checked after the track data of a plurality of days are accumulated, the repeated key position points are further refined, as shown in fig. 6, and fig. 6 shows a schematic diagram for refining the key position points of the superposition track. For the trace points with fewer occurrence and lower overlapping degree, the trace points are removed and filtered, certain offset threshold error correction can be given in the removing process, so long as the trace points can be identified as overlapping in the error range, the overfitting phenomenon that the overlapping is calculated only by absolute position matching is avoided, and the threshold can be specifically analyzed and adjusted according to specific conditions. According to specific conditions, the accumulated duration of the key position information extraction and the track period can be flexibly adjusted.
Step two: and (5) cleaning GIS data.
GIS data cleaning mainly comprises three main tasks:
(1) filtering GIS data irrelevant to key positions.
The GIS data is filled with innumerable position points, each position point possibly corresponds to a plurality of POIs (points of interest), and the POIs are taken as entity objects in the GIS and are information which can be used for predicting behavior preference and identity characteristics in the GIS data. If POI information of a certain location point is queried from the GIS each time and then processed again, this results in inefficiency, so GIS data should be preprocessed, and only GIS data at the location point involved in the first step is considered. After the relevant GIS data are obtained, filtering the POIs at the position points according to the predicted targets, removing the POIs irrelevant to the predicted targets, and further reducing the data size, for example: if someone goes to a park where this action does not help the intended predicted target, then no POIs like "park" should appear in the processed GIS data.
(2) And (5) carrying out weight division on the situation that the same position has multiple POIs.
The same position may have multiple POI attributes, and a weight dividing method is needed to order the POI attributes reflected by the position and assign proper weights. One relatively straightforward way is to estimate the division weights by the traffic of the services provided by the POI, i.e. more traffic is used than less traffic, and therefore more weight is given.
(3) And extracting the behavior preference and identity characteristics behind the POI.
The goal of the prediction is to identify the behavioral preferences and identity characteristics of the individual for which we need to extract the meaning behind the POI. The conversion from POI information to behavior preference and identity features can be simply manually marked or refined from the related data of the POI by adopting a natural language processing method.
After the GIS data are cleaned and mined, the GIS data which are simplified, have weight distribution and are described by the behavior preference and the identity characteristics are obtained.
Step three: and merging the personal position data and the GIS data to judge and predict.
After the personal core track position data and the mined GIS data are obtained, the behavior preference and the identity characteristic prediction can be carried out by combining the personal core track position data and the mined GIS data, and after the preparation of the two steps, the prediction process is actually converted into a process of extracting the corresponding GIS data according to the core position track, and the core problem to be solved in the process is how to distribute the GIS data to the position under the condition that the position data cannot directly correspond to the interest point in the GIS data.
A simple and easy-to-use algorithm is to use distance calculation, take the feature of the interest point with the shortest distance to the target position in GIS data as the feature of the target position, and take the distance as the position weight to be brought into an output result so as to optimize the prediction result in a subsequent step, as shown in FIG. 7, and FIG. 7 shows a shortest distance matching schematic diagram.
Step four: and correcting the pre-output data.
The correction processing for the pre-output data can be classified into two types:
(1) resident (workplace, residence) logic correction processing.
According to the track data, predicting the personal residence (workplace, residence) from the angles of time and space, and judging whether a certain key position on the personal track is a usual residence or not from the pre-output data by combining a plurality of factors such as the stay time of the positions, the occurrence time of the positions, the offset between the positions, the environment reflected by the positions on the GIS and the like. For such data, the data will be processed in such a way that the resident properties are stronger than any other properties. For example: individuals often appear at two points a and B, identified as a workplace and a residence, respectively, with point a being a restaurant, then for location a the attribute of the workplace should be prioritized, the predicted objective has the trait of "restaurant practitioners" and should not be identified as "like this restaurant", and similarly if there is an advanced residential cell near point B, there is a movie theater, location B should be prioritized for the attribute of the residence, match the advanced residential cell, identify as "high-income people" and should not be identified as "movie lovers", even though the "movie lovers" are weighted more than the "high-income people" in the pre-output data of the previous step.
(2) Paradox logic correction processing.
After the identity feature is determined, whether the behavior preferences and the characteristics are mutually contradicted or not is checked, and if the behavior preferences and the characteristics are mutually contradicted, correction processing is needed. The simplest way is to remove violation decisions where the likelihood is lower, thereby eliminating paradox logic. However, when two behavior preferences contradict identity feature decisions, a position with lower weight (lower matching degree and longer distance) in the pre-output data is preferentially selected for modification, the position is modified into the behavior preference with lower weight at one level in GIS data, the identity feature attribute (the next level POI) is checked again, and if the mutual paradox exists, the behavior is repeated again until paradox logic is not existed.
The extreme case is that after all new behavior preference and identity characteristic attribute are iterated, the mutual paradox is found to exist, at the moment, an attempt can be made to modify a position with higher position weight in the pre-output data, the behavior is repeated, if the problem of mutual paradox cannot be solved after the attempt, rejection processing is carried out on the position characteristic data with lower position weight, and the mutual paradox logic is eliminated. And obtaining final judging data after finishing the correction processing. The specific implementation is shown in fig. 8, and fig. 8 shows a flowchart of the mutual contradiction determination correction processing. The position track A is a certain key position point, and the position track B is a certain key position point. First, the distance between the POI interest point corresponding to the position track a and the position track a is compared with the distance between the POI interest point corresponding to the position track B and the position track B. The distance between the POI interest point corresponding to the position track A and the position track A is short, namely the position weight of the POI interest point corresponding to the position track A is low, and the POI interest point corresponding to the position track A is modified to eliminate the contradictory logic. And then comparing weights of the POI interest points corresponding to the position track A, sequentially modifying the weights of the POI interest points from low to high, and finally eliminating the contradictory logic.
It follows that predictions of personal behavioral preferences and identity characteristics are not made based on a crowd data set in a certain scenario, but by characteristics that are reflected in the GIS system based on predicted goals. The method has the starting point that the prediction is performed by the personal behavior, the judgment and the prediction of the behavior preference and the identity characteristic are performed by combining GIS data, the crowd data set in a certain scene is not relied on as a prediction basis, the prediction is not entangled in the details of a specific field, and the diversified prediction is performed at a higher level. Because GIS data is not limited in a specific vertical field, the invention enables behavior preference prediction to get rid of the limitation that a specific scene is required to be relied on conventionally, and meanwhile, the invention avoids the problems of data scale and data quality of the existing method because the problems that a huge crowd data set is required as a basis or the data set is too sparse and the like are not existed. In general, compared with the traditional method, the method gets rid of the constraint of taking the crowd data set as a prediction basis, and has the characteristic of diversification in the prediction direction.
Example III
Fig. 3 is a block diagram showing an apparatus for predicting user behavior preference based on user location according to a third embodiment, the apparatus comprising:
The key location point screening module 31 is adapted to acquire personal location data corresponding to the target user, and screen at least one key location point corresponding to the target user according to the residence time and/or residence frequency corresponding to each location point included in the personal location data;
the GIS data and interest point acquisition module 32 is adapted to acquire target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data;
the behavior preference prediction module 33 is adapted to predict user behavior preferences of the target user based on the points of interest corresponding to the target GIS data.
Optionally, the personal location data comprises: slicing position data corresponding to the plurality of time slices, respectively;
the keypoint screening module 31 is adapted to:
determining the stay time length of each position point contained in each piece of position data, and screening the position points with the stay time length larger than a preset time length threshold value as candidate position points in the piece of position data;
according to the occurrence times of each candidate position point in each piece of position data, determining the stay frequency of each candidate position point, and screening the candidate position points with stay frequency not smaller than a preset frequency threshold as key position points.
Alternatively, the behavior preference prediction module 33 is adapted to:
when the interest points corresponding to the target GIS data are multiple, judging whether each interest point is matched with a preset prediction target;
and determining the interest point matched with the preset prediction target as a target interest point, and predicting the user behavior preference of the target user according to the target interest point.
Alternatively, the behavior preference prediction module 33 is adapted to:
when the interest points corresponding to the target GIS data are multiple, calculating the distance between the interest points and the key position points;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Alternatively, the behavior preference prediction module 33 is adapted to:
when the interest points corresponding to the target GIS data are multiple, judging whether the attribute of the interest points meets a preset resident attribute rule or not;
if yes, the interest point is determined to be a target interest point, and the user behavior preference of the target user is predicted according to the target interest point.
Alternatively, the behavior preference prediction module 33 is adapted to:
when the interest points corresponding to the target GIS data are multiple, judging whether inter-contradiction logic exists between the interest points;
If yes, screening target interest points according to the distances between the interest points and the key position points and the weights corresponding to the interest points, and predicting user behavior preference of the target user according to the target interest points.
Alternatively, the behavior preference prediction module 33 is adapted to:
and presetting weights corresponding to the interest points according to the people flow corresponding to the interest points and/or the distance between the interest points and the key position points.
Embodiments of the present application provide a non-volatile computer storage medium having stored thereon at least one executable instruction for performing a method of predicting user behavior preferences based on user location in any of the method embodiments described above.
Fig. 4 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention, and the specific embodiment of the present invention is not limited to the specific implementation of the electronic device.
As shown in fig. 4, the electronic device may include: a processor 402, a communication interface (Communications Interface) 404, a memory 406, and a communication bus 408.
Wherein:
processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.
A communication interface 404 for communicating with network elements of other devices, such as clients or other servers.
The processor 402 is configured to execute the program 410, and may specifically perform relevant steps in the above-described fault location method embodiment based on a multi-level network node.
In particular, program 410 may include program code including computer-operating instructions.
The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the electronic device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 406 for storing programs 410. Memory 406 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 410 may be specifically operative to cause processor 402 to perform the operations in the method embodiments described above.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a system according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or system program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
Claims (5)
1. A method of predicting user behavior preferences based on user location, comprising:
acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data;
Acquiring target GIS data corresponding to the at least one key position point and interest points corresponding to the target GIS data;
predicting user behavior preference of the target user according to the interest points corresponding to the target GIS data;
wherein, the predicting the user behavior preference of the target user according to the interest point corresponding to the target GIS data includes:
when a plurality of interest points corresponding to the target GIS data are provided, extracting behavior preference and identity characteristics behind each interest point, and judging whether each interest point is matched with a preset prediction target; wherein the behavioral preferences and identity characteristics include profession, income, and hobbies; the preset prediction targets are used for predicting occupation, income and hobbies of target users;
determining an interest point matched with a preset prediction target as a target interest point, and predicting user behavior preference of the target user according to the target interest point; wherein the user behavior preferences are behavior preferences and identity features including profession, income and hobbies.
2. The method of claim 1, wherein the personal location data comprises: slicing position data corresponding to the plurality of time slices, respectively;
The screening at least one key location point corresponding to the target user according to the residence time length and/or residence frequency corresponding to each location point contained in the personal location data includes:
determining the stay time length of each position point contained in each piece of position data, and screening the position points with the stay time length larger than a preset time length threshold value as candidate position points in the piece of position data;
according to the occurrence times of each candidate position point in each piece of position data, determining the stay frequency of each candidate position point, and screening the candidate position points with stay frequency not smaller than a preset frequency threshold as the key position points.
3. An apparatus for predicting user behavior preferences based on user location, comprising:
the key position point screening module is suitable for acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data;
the GIS data and interest point acquisition module is suitable for acquiring target GIS data corresponding to the at least one key position point and interest points corresponding to the target GIS data;
The behavior preference prediction module is suitable for predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data;
the behavioral preference prediction module is further adapted to:
when a plurality of interest points corresponding to the target GIS data are provided, extracting behavior preference and identity characteristics behind each interest point, and judging whether each interest point is matched with a preset prediction target; wherein the behavioral preferences and identity characteristics include profession, income, and hobbies; the preset prediction targets are used for predicting occupation, income and hobbies of target users;
determining an interest point matched with a preset prediction target as a target interest point, and predicting user behavior preference of the target user according to the target interest point; wherein the user behavior preferences are behavior preferences and identity features including profession, income and hobbies.
4. An electronic device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to a method of predicting user behavior preferences based on user location as recited in claim 1 or 2.
5. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of predicting user behavior preferences based on user location as recited in claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635221.9A CN112232845B (en) | 2019-07-15 | 2019-07-15 | Method and device for predicting user behavior preference based on user position |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635221.9A CN112232845B (en) | 2019-07-15 | 2019-07-15 | Method and device for predicting user behavior preference based on user position |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112232845A CN112232845A (en) | 2021-01-15 |
| CN112232845B true CN112232845B (en) | 2023-12-19 |
Family
ID=74111085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910635221.9A Active CN112232845B (en) | 2019-07-15 | 2019-07-15 | Method and device for predicting user behavior preference based on user position |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112232845B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740347A (en) * | 2016-01-25 | 2016-07-06 | 四川长虹电器股份有限公司 | GPS based user information acquisition and behavior analysis method |
| CN106844376A (en) * | 2015-12-03 | 2017-06-13 | 高德软件有限公司 | Recommend the method and device of point of interest |
| CN107515949A (en) * | 2017-09-14 | 2017-12-26 | 云南大学 | User's space-time method for measuring similarity in interest point prediction and recommendation |
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN109460509A (en) * | 2018-10-12 | 2019-03-12 | 平安科技（深圳）有限公司 | User interest point appraisal procedure, device, computer equipment and storage medium |
| CN109635070A (en) * | 2019-01-18 | 2019-04-16 | 上海图趣信息科技有限公司 | A kind of method and its data-updating method based on movement track building user interest portrait |
| CN109635190A (en) * | 2018-11-28 | 2019-04-16 | 四川亨通网智科技有限公司 | User characteristics method for digging based on position and behavior Conjoint Analysis |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104102638B (en) * | 2013-04-02 | 2017-06-20 | 北京百度网讯科技有限公司 | Method for pushing, system and device based on positional information |
| US9651392B2 (en) * | 2014-01-22 | 2017-05-16 | Mapquest, Inc. | Methods and systems for providing dynamic point of interest information and trip planning |
| US9869562B2 (en) * | 2016-02-22 | 2018-01-16 | Bayerische Motoren Werke Aktiengesellschaft | Method and system for contextually recommending a place of interest to a user and smart check-in |
-
2019
- 2019-07-15 CN CN201910635221.9A patent/CN112232845B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844376A (en) * | 2015-12-03 | 2017-06-13 | 高德软件有限公司 | Recommend the method and device of point of interest |
| CN105740347A (en) * | 2016-01-25 | 2016-07-06 | 四川长虹电器股份有限公司 | GPS based user information acquisition and behavior analysis method |
| CN107515949A (en) * | 2017-09-14 | 2017-12-26 | 云南大学 | User's space-time method for measuring similarity in interest point prediction and recommendation |
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN109460509A (en) * | 2018-10-12 | 2019-03-12 | 平安科技（深圳）有限公司 | User interest point appraisal procedure, device, computer equipment and storage medium |
| CN109635190A (en) * | 2018-11-28 | 2019-04-16 | 四川亨通网智科技有限公司 | User characteristics method for digging based on position and behavior Conjoint Analysis |
| CN109635070A (en) * | 2019-01-18 | 2019-04-16 | 上海图趣信息科技有限公司 | A kind of method and its data-updating method based on movement track building user interest portrait |
Non-Patent Citations (2)
| Title |
|---|
| "基于GPS数据的用户轨迹挖掘与预测研究";徐以彬;《中国优秀硕士学位论文全文数据库基础科学辑》(第3期);A008-88 * |
| "基于智能手机的个体出行模式识别研究";周洋;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第4期);C034-914 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112232845A (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107885796B (en) | Information recommendation method, device and equipment | |
| CN107291888B (en) | Machine learning statistical model-based living recommendation system method near living hotel | |
| Chen et al. | Constructing and comparing user mobility profiles | |
| WO2016196999A1 (en) | Personally impactful changes to events of users | |
| WO2016176470A1 (en) | Unusualness of events based on user routine models | |
| KR20170001546A (en) | Method and device for determining an address for a new point of interest | |
| CN110888866B (en) | Data expansion method and device, data processing equipment and storage medium | |
| WO2017040852A1 (en) | Modeling of geospatial location over time | |
| JP2018077821A (en) | Method, program, server device, and processor for generating predictive model of category of venue visited by user | |
| WO2016197857A1 (en) | Position information providing method and device | |
| CN108536695B (en) | Aggregation method and device of geographic position information points | |
| CN112214677A (en) | Interest point recommendation method and device, electronic equipment and storage medium | |
| CN110262863B (en) | Method and device for displaying terminal main interface | |
| CN107767155B (en) | Method and system for evaluating user portrait data | |
| CN109918048B (en) | Target object extraction method, device and system and computer readable storage medium | |
| CN115017400A (en) | Application APP recommendation method and electronic equipment | |
| CN113742580A (en) | Target type data recall method and device, electronic equipment and storage medium | |
| JP2017091435A (en) | Stay place prediction device | |
| CN112232845B (en) | Method and device for predicting user behavior preference based on user position | |
| JP5637073B2 (en) | Information processing apparatus, information processing method, and program | |
| CN112256957A (en) | Information sorting method and device, electronic equipment and storage medium | |
| CN111831892A (en) | Information recommendation method, information recommendation device, server and storage medium | |
| CN108122123B (en) | Method and device for expanding potential users | |
| US11050834B1 (en) | Method for automatically assigning visits to partially observable location data streams | |
| US20200143269A1 (en) | Method and Apparatus for Determining a Travel Destination from User Generated Content |
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 |