CN116401443A - Point location recommendation method and device, electronic equipment and storage medium - Google Patents
Point location recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116401443A CN116401443A CN202310131482.3A CN202310131482A CN116401443A CN 116401443 A CN116401443 A CN 116401443A CN 202310131482 A CN202310131482 A CN 202310131482A CN 116401443 A CN116401443 A CN 116401443A
- Authority
- CN
- China
- Prior art keywords
- point
- travel
- user
- similarity
- information
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000011159 matrix material Substances 0.000 claims abstract description 101
- 239000013598 vector Substances 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 3
- MOVRNJGDXREIBM-UHFFFAOYSA-N aid-1 Chemical compound O=C1NC(=O)C(C)=CN1C1OC(COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C(NC(=O)C(C)=C2)=O)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C(NC(=O)C(C)=C2)=O)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C(NC(=O)C(C)=C2)=O)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)CO)C(O)C1 MOVRNJGDXREIBM-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a point position recommending method, a point position recommending device, electronic equipment and a storage medium, wherein the point position recommending method comprises the following steps: acquiring current snapshot image information of a user; comparing the user snap image with a plurality of file information of the reference file set to determine target file information corresponding to the user snap image; determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of travel points, and a travel frequency matrix is used for describing the frequency of the user at each travel point at different time, wherein the travel points comprise pre-calculated distance similarity and time similarity; and determining the target interest point based on the travel frequency matrix, and recommending the point according to the target interest point. Therefore, the interest point recommendation has obvious rationality, the interest demands of users corresponding to different time and different places can be solved, and the recommendation accuracy and recall rate are improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a point position recommending method, a point position recommending device, electronic equipment and a storage medium.
Background
At present, when different archive users arrive at certain places, point-of-interest point location recommendation can be performed based on specific place information of the archive users in historical time, but the conventional recommendation mode is usually based on geographic position information or is performed for different time information, so that the point-of-interest point recommendation has obvious objectivity, and the user interest requirements corresponding to different time and different places cannot be met, so that the recommendation accuracy is insufficient.
Disclosure of Invention
In a first aspect, the present invention provides a point location recommendation method, including:
acquiring current snapshot image information of a user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image;
comparing the user snap image with a plurality of file information of a reference file set to determine target file information corresponding to the user snap image;
determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of the user collected at a plurality of travel points, the travel frequency matrix is used for describing the frequency of the user at each travel point at different time, and the travel points comprise pre-calculated distance similarity and time similarity;
And determining a target interest point based on the travel frequency matrix, and recommending the point according to the target interest point.
Optionally, before the step of acquiring the current snapshot image information of the user, the method includes:
according to personnel image features corresponding to the images to be archived, which are captured by each travel point, determining a similarity set between the images to be archived;
and clustering the images to be archived based on the similarity set, archiving the images to be archived which meet the similarity threshold, and obtaining the reference archive set.
Optionally, the clustering the images to be archived based on the similarity set, archiving the images to be archived that meet a similarity threshold, and after obtaining the reference archive set, including:
determining position information corresponding to each travel point according to the reference file set, and calculating the distance between every two travel point;
and determining the distance similarity between the two travel points according to the distance between the two travel points.
Optionally, the clustering the images to be archived based on the similarity set, archiving the images to be archived that meet a similarity threshold, and after obtaining the reference archive set, further includes:
Determining the occurrence times of the user at the trip point location in each time period according to the reference file set;
constructing a travel frequency matrix according to the occurrence frequency, and carrying out normalization processing based on the travel frequency matrix to obtain a matrix vector corresponding to the travel frequency matrix;
and calculating based on the matrix vector, and determining the time similarity between every two travel points.
Optionally, the determining the corresponding travel frequency matrix according to the target archive information and the current point location information includes:
determining a historical visit point of the user according to the target archive information;
determining the point position recommendation range of the user according to the current point position information;
taking the historical visit points in the point recommending range as points to be recommended;
and determining a corresponding travel frequency matrix based on the captured image information of the user acquired at the point to be recommended.
Optionally, the determining the target point of interest based on the trip frequency matrix and recommending the target point of interest include:
determining the time similarity and the distance similarity corresponding to the travel point positions based on the travel point positions corresponding to the travel frequency matrix;
Calculating according to the time similarity and the distance similarity to obtain total similarity;
and determining a target point of interest according to the total similarity, and recommending according to the target point of interest.
Optionally, the determining the target point of interest according to the total similarity and recommending the target point of interest according to the target point of interest include:
sequencing all travel points according to the total similarity, and determining a target travel point position of which the total similarity meets a preset condition;
and taking the interest point address corresponding to the target trip point as a target interest point, and recommending according to the target interest point.
In a second aspect, an embodiment of the present invention provides a point location recommendation apparatus, including:
the acquisition module is used for acquiring the current snapshot image information of the user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image;
the comparison module is used for comparing the user snap image with the plurality of file information of the reference file set to determine target file information corresponding to the user snap image;
The determining module is used for determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of the user collected at a plurality of travel points, the travel frequency matrix is used for describing the frequency of the user at each travel point at different time, and the travel points comprise pre-calculated distance similarity and time similarity;
and the recommending module is used for determining a target interest point in the travel frequency matrix based on the current time information and the current point information and recommending the point according to the target interest point.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the point location recommendation method described above when the processor executes the computer program.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of a point location recommendation method as described above.
The scheme of the invention at least comprises the following beneficial effects:
the point position recommending method provided by the invention comprises the steps of firstly, acquiring current snapshot image information of a user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image; comparing the user snap image with a plurality of file information of the reference file set to determine target file information corresponding to the user snap image; determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of travel points, and a travel frequency matrix is used for describing the frequency of the user at each travel point at different time, wherein the travel points comprise pre-calculated distance similarity and time similarity; and determining a target interest point in the trip frequency matrix based on the current time information and the current point information, and performing point location recommendation according to the target interest point. Therefore, the interest point recommendation has obvious rationality, the interest demands of users corresponding to different time and different places can be solved, and the recommendation accuracy and recall rate are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an overall flow diagram of a point location recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a point location recommendation method according to an embodiment of the present invention;
fig. 3 is a block diagram of a point location recommendation device according to an embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second, third and the like in the description and in the claims of the invention and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the term "include" and any variations thereof is intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The following embodiments of the present application will be described by way of example with reference to the accompanying drawings.
As shown in fig. 1, a specific embodiment of the present invention provides a point location recommendation method, including:
s10, acquiring current snapshot image information of a user, wherein the current snapshot image information comprises the user snapshot image, current time information corresponding to the user snapshot image and current point position information corresponding to the user snapshot image.
In this embodiment, the current snapshot image information of the user may be obtained through a camera according to the recommendation request of the user, or may be obtained through a camera when the user arrives at a certain snapshot location, where the personnel flow is large, such as a traffic intersection, a mall, a neighborhood, etc., so as to collect the snapshot image of the user in time; the user snap image may be a face image of the user, a human body image of the user, or the like, and it may be understood that the face image or the human body image of the user may be image data that has been archived in a history time, for example, archiving an image captured by the user in one month or 24 hours may determine archival data corresponding to the user, so that the archival data corresponding to the user may be determined when current snap image information of the user is obtained.
Specifically, before the obtaining the current snapshot image information of the user according to the recommendation request of the user, the method includes: according to the personnel image characteristics corresponding to the images to be archived, which are captured by each travel point, determining a similarity set between the images to be archived; clustering the images to be archived based on the similarity set, archiving the images to be archived which meet the similarity threshold, and obtaining a reference archive set.
In this embodiment, the to-be-archived images captured at each trip point may include face images or body images of different users, and the similarity set may be obtained by calculating the face images of the users, and when the user captured images at each trip point are obtained, the similarity calculation may be performed on the user captured images, for example, cosine similarity may be used to calculate similarity between every two to-be-archived images, that is, when the cosine value between every two to-be-archived images is closer to 1, the similarity between every two to-be-archived data is larger; it can be understood that after the similarity set between the images to be archived is calculated, the data to be archived is clustered into corresponding image stacks through the similarity set, then an image with better image quality is determined as an initial archive set for each image stack, and further the user snap images collected at the subsequent trip point positions can be archived according to the initial archive set, so that a reference archive set is obtained; for example, each point may be represented as a file in fig. 2, and after similarity calculation and clustering are performed on each file, a plurality of image stacks may be formed, so that archiving operation between different files is completed.
In a preferred embodiment, the reference archive sets may be aidN { aid1, aid2, aid 3..aidn }, and the snap images in each image archive set aidN may be denoted b n {b 1 ,b 2 ,b 3 ,..b n N×n calculation of the snap images collected at each travel point location to calculate the similarity between the snap images, so that the calculated similarity set may be sim ij {sim 12 ,sim 13 ....sim ij I, j represents data b i ，b j The method comprises the steps of carrying out a first treatment on the surface of the After the similarity set is compared with the first similarity threshold, the user snap images corresponding to the similarity set larger than the first similarity threshold are reserved, so that the initial archive set can be determined to be expressed as aidN { aid1, aid2, aid3. It will be appreciated that the first similarity threshold may be expressed as α sim When sim ij -α sim When the similarity is greater than 0, the corresponding user snap-shot image is reserved to form an initial file set, when the non-archiving image acquired by each subsequent trip point location needs to be archived, similarity comparison can be carried out according to the initial file set and the non-archiving image, then comparison is carried out through a second similarity threshold, and when the similarity is determined to be greater than the second similarity threshold, the user snap-shot image can be reserved in the corresponding initial file set to form a reference file set; it will be appreciated that the second similarity threshold may be expressed as beta ij The set of similarities determined after comparing the subsequently acquired unaddressed image with the initial set of archives may be represented as sim ij {sim 12 ,sim 13 ....sim ij Thus at sim ij -β ij Corresponding to > 0The snap shot images of the users can be archived in the corresponding archive data.
Further, the clustering of the images to be archived based on the similarity set, archiving the images to be archived that meet the similarity threshold, and after obtaining the reference archive set, includes: determining position information corresponding to each travel point position according to the reference file set, and calculating the distance between every two travel point positions; and determining the distance similarity between every two travel points according to the distance between every two travel points.
In this embodiment, each user snap image in the reference file set includes corresponding travel point location information and corresponding interest points, the travel point location information may include longitude and latitude, map coordinates, and the like, the interest points may be locations of scenic spots, schools, restaurants, and the like around the travel point location, and the distance similarity between the travel points is determined by the reference file set, when the distance between the travel points is larger, the distance similarity is smaller, and when the distance between the travel points is smaller, the distance similarity is larger; the distance similarity between the travel points can be determined by inversely proportional to the distance between the travel points, and the distance similarity is indicated to be smaller when the distance is larger and larger when the distance is smaller.
It will be appreciated that the distance similarity described above can be calculated using the following formula:
distiance(li,lj)＝R*arccos[sin(lat i )*sin(lat j )+cos(lat i )*cos(lat j )*cos(lat i -lon j )]；
wherein,,
representing two outletsDistance similarity between row points li and lj, distian (li, lj) represents the distance between two row points li and lj, lat i And lon i The longitude and latitude of the trip point position are represented, R is the earth radius, and R= 6378.137km; the distance between the two travel points can be determined by the formula, the distance between the two travel points can be the road traffic distance, and the corresponding distance similarity can be determined by the distance between the two travel points.
Further, the clustering of the images to be archived based on the similarity set, archiving the images to be archived that meet the similarity threshold, and after obtaining the reference archive set, further includes: determining the occurrence times of the user in the trip point location in each time period according to the reference file set; constructing a travel frequency matrix according to the occurrence frequency, and carrying out normalization processing based on the travel frequency matrix to obtain a matrix vector; and calculating based on the matrix vector, and determining the time similarity between every two travel points.
In this embodiment, the travel frequency matrix may be a two-dimensional table matrix, and is obtained by counting travel points of a user in different time periods, and after normalization processing is performed on the travel frequency matrix, a plurality of one-dimensional vector matrices are determined, so that the plurality of one-dimensional vector matrices can be represented by matrix vectors, and further cosine similarity calculation is performed based on the matrix vectors, so that time similarity between every two travel points can be determined.
It will be appreciated that the table matrix for the different time periods is shown below:
wherein, the user is at each trip point position carema n The table matrix corresponding to the occurrence times of different time periods is as follows:
it will be appreciated from the above table matrix that 24 hours may be divided into different time periods and then counted for the number of occurrences of a plurality of users in each travel point in each time period, e.g. t in the above table matrix 4 In the corresponding time period, the trip point position carema 1 The number of times of appearance of a plurality of corresponding users is 56, so that the user snap images acquired by the users in different time periods within 24 hours are determined, the corresponding number of appearance times is counted, and the normalization calculation is performed after the table matrix is determined, so that the matrix vector is determined.
It will be appreciated that in the normalization calculation by the above-described table matrix, the following formula may be used for calculation:
wherein,,
representing travel point position carema li The number of occurrences of all files, N, at time tj t Representing travel point position carema li All the times of occurrence, after calculating the one-dimensional vector matrix, the vector matrix can be expressed as +.>
Thus, the matrix vector can be expressed as +. >
After the matrix vector is determined, calculating the time similarity between every two travel points of the matrix vector through cosine similarity, and calculating by adopting the following formula:
When the time similarity is calculated, the travel point location corresponding to the current point location information may be expressed as a carema li Therefore, the travel point position cart corresponding to the current point position information li With each trip point position carema n The time similarity between the two can be calculated by the formula; in the calculation, the average value variance normalization calculation can be performed on the travel time and travel times corresponding to each travel point location, that is to say, the travel time and travel times in the travel time matrix are classified into the distribution with the average value of 0 and the variance of 1, that is, the obtained data average value is 0 and the variance of 1, so that the travel point location care corresponding to the current point location information can be obtained li Performing variance calculation on the corresponding travel times and travel time, and then calculating the carema according to the variance result and the normalization formula li The corresponding normalized value; it can be appreciated that the travel point position carema is obtained through calculation li After the corresponding normalized values, a plurality of normalized values can be used as travel point positions carima li Is represented by a matrix vector of (a), i.e. as described above
The time similarity between every two travel points can be determined by calculating the cosine similarity of the matrix vectors of all the travel points, and the time similarity can be expressed as the travel time and travel times between every two travel points, so that the time similarity between all the travel points can be determined by calculating the cosine similarity of the matrix vectors obtained by calculating every two travel points, and when a user arrives at a certain travel point in the follow-up point recommendation, the corresponding point can be recommended according to the time similarity between the travel point and each travel point, thereby improving the accuracy of point recommendation; for example, in calculating the temporal similarity, the trip point location includes A,B. C, D when the user half appears at the A point at 11 am, the A point can acquire the snapshot image information of the user at the A point, further can determine corresponding time information according to the snapshot image information of the A point, and matches and determines that the corresponding point information is the A point in the t4 time period, and can determine that the corresponding point information is the A point, therefore, when the time similarity is calculated, the corresponding travel times of the t4 time period and the A point can be normalized, so that a corresponding normalization value is obtained, and further, the time similarity between the A point and the B, C, D travel point in the t4 time period is calculated after the normalization value is expressed by a matrix vector.
S20, comparing the user snap image with a plurality of file information of the reference file set, and determining target file information corresponding to the user snap image.
In this embodiment, when a user appears in a certain trip point, the trip point may collect current snap image information of the user and perform similarity calculation with the above reference file set, so as to determine corresponding target file information in the reference file set, so that the corresponding trip frequency matrix may be determined by searching the target file information and the current snap image information, and further determine the corresponding recommended point.
S30, determining a corresponding travel time matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of travel points, and a travel frequency matrix is used for describing the frequency of the user at each travel point at different times, wherein the travel points comprise pre-calculated distance similarity and time similarity.
In this embodiment, when determining the target archive information, the historical visiting points that the user has arrived can be found according to the target archive information, and then the corresponding time similarity and distance similarity can be determined through the travel frequency matrix; it can be understood that the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image; therefore, the travel time matrix determined by the user in the history time can be obtained by determining the history visit points of the user.
Specifically, the determining the corresponding travel frequency matrix according to the target archive information and the current point location information includes: according to the target archive information, determining a historical visiting point position of the user; determining the point position recommendation range of the user according to the current point position information; taking the historical visit points in the point recommending range as points to be recommended; and determining a corresponding travel frequency matrix based on the captured image information of the user acquired at the point to be recommended.
The historical visiting point represents a travel point where the user visits before the current time, the point recommendation range represents a point of interest range corresponding to the current point, similarity calculation can be performed on each file in the current snapshot image information and the reference file set, when the current snapshot image information can determine target file information with higher similarity in the reference file set, the historical visiting point where the user visits can be determined according to the target file information, optionally, the travel point has a corresponding point recommendation range, the point recommendation range can be divided according to the point of interest, such as schools, super-quotient, restaurants, hotels, scenic spots and the like, therefore, the point of interest can comprise learning, shopping, dining, lodging, playing and the like, the point recommendation range can be determined according to the current point information, the historical visiting point which is in the point recommendation range of the current point can be determined in the historical visiting point, and is used as a to-be-recommended point, and the travel frequency matrix corresponding to the user can be determined according to the snapshot image information of the user in the to-be-recommended point, and the travel frequency matrix corresponding to the user can be determined according to the frequency matrix; for example, the historical visiting point is A, B, C, D, the current point reached by the user is A, and the point recommendation range of the point A comprises B, C two points, so that the two points B, C can be determined as points to be recommended, the corresponding trip times are determined according to the snap shot image information acquired by the user at the two points B, C, and the trip times are counted in a trip time matrix to perform point recommendation.
And S40, determining a target point of interest based on the travel frequency matrix, and recommending according to the target point of interest.
In this embodiment, the target point of interest may be determined according to the above-mentioned time similarity and distance similarity, so that a corresponding travel point location may be determined according to the travel frequency matrix, the distance between the travel point location and the travel point location where the user is currently located may be relatively close, and the number of times of arrival in the user history time is relatively large, so that after calculation may be performed comprehensively through the distance similarity and the time similarity, the location of the travel point location may be determined, and the associated target point of interest may be determined through the travel point location.
In an optional embodiment, when determining the target point of interest through the distance similarity and the time similarity, the distance similarity and the time similarity may be screened first to determine the distance similarity and the time similarity of the maximum result, and then comprehensive calculation is performed according to the screened distance similarity and time similarity, so that the corresponding travel point location is determined according to the result of the comprehensive calculation.
Specifically, the determining the target point of interest based on the trip frequency matrix and recommending the target point of interest includes: determining the time similarity and the distance similarity corresponding to the travel point positions based on the travel point positions corresponding to the travel frequency matrix; calculating according to the time similarity and the distance similarity to obtain total similarity; and determining the target interest point according to the total similarity, and recommending according to the target interest point.
In this embodiment, the time similarity may be calculated according to the calculation formula of the time similarity, the distance similarity may be calculated according to the calculation formula of the distance similarity, after a travel time matrix determined according to current captured image information of a user, a travel point location corresponding to the current captured image information may be determined, the distance similarity is determined according to the travel point location and each travel point location, meanwhile, the time similarity is determined according to the travel time matrix, then the weighted sum is performed by using the distance similarity and the time similarity to obtain a total similarity, a target interest point location is determined by the total similarity, user interest requirements corresponding to different time and different places may be comprehensively considered, and accuracy of interest point location recommendation is improved.
It will be appreciated that in calculating the overall similarity described above, the following formula may be used for the calculation:
sim(li,lj)＝α*t_sim li,lj +(1-α)d_sim li,lj ，
t_sim li,lj : time similarity;
d_sim li,lj : distance similarity
Wherein, alpha is [0,1 ]]Represented as a weight value of the weight,
representing the distance similarity between two travel points li and lj, t_sim li,lj And the time similarity obtained by calculating the travel time matrix corresponding to the current snapshot image information is represented, sim (li, lj) is represented as total similarity, and the target interest point location is determined through the total similarity, so that comprehensive recommendation can be performed by combining information of different time periods, and the recommendation accuracy is higher.
Further, determining the target point of interest according to the total similarity, and recommending according to the target point of interest, including: sequencing the travel points according to the total similarity, and determining a target travel point with the total similarity meeting a preset condition; and taking the interest point address corresponding to the target trip point as the target interest point, and recommending according to the target interest point.
In this embodiment, after the total similarity is determined, the total similarity may be sorted according to the order from large to small according to the total similarity of each travel point, after sorting, the total similarity may be compared with the predetermined similarity, when the total similarity is greater than the predetermined similarity, the travel point corresponding to the total similarity may be regarded as the target travel point, and when the total similarity is less than the predetermined similarity, the travel point corresponding to the total similarity may be removed, so that when the recommendation is performed to the user, the recommendation may be performed according to the interest point address corresponding to the target travel point, thereby improving the accuracy of the recommendation of the interest point, and the user's options may be more diversified.
In an alternative embodiment, after sorting according to the total similarity of all the travel points from big to small, determining the travel point corresponding to the maximum total similarity as the target travel point, thereby determining the interest point address according to the target travel point corresponding to the maximum total similarity, further recommending to the user, and obviously improving the accuracy and recall rate of the interest point recommendation.
The point position recommending method provided by the invention comprises the steps of firstly, acquiring current snapshot image information of a user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image; comparing the user snap image with a plurality of file information of the reference file set to determine target file information corresponding to the user snap image; determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of travel points, and a travel frequency matrix is used for describing the frequency of the user at each travel point at different time, wherein the travel points comprise pre-calculated distance similarity and time similarity; and determining a target interest point in the trip frequency matrix based on the current time information and the current point information, and performing point location recommendation according to the target interest point. Therefore, the interest point recommendation has obvious rationality, the interest demands of users corresponding to different time and different places can be solved, and the recommendation accuracy and recall rate are improved.
It will be appreciated that in the specific embodiments of the present application, related data such as snapshot image information, archive information, etc. are referred to, and when the embodiments of the present application are applied to specific products or technologies, user permission or consent is required to be obtained, and the collection, use and processing of related data is required to comply with relevant laws and regulations and standards of relevant countries and regions.
As shown in fig. 3, an embodiment of the present invention provides a point location recommendation device 10, including:
the acquisition module 11 is configured to acquire current snapshot image information of a user, where the current snapshot image information includes a user snapshot image, current time information corresponding to the user snapshot image, and current point location information corresponding to the user snapshot image; the method comprises the steps of carrying out a first treatment on the surface of the
A comparison module 12, configured to compare the user snap-shot image with a plurality of file information of the reference file set, and determine target file information corresponding to the user snap-shot image;
the determining module 13 is used for determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of trip points, and a trip frequency matrix is used for describing the frequency of the user at each trip point at different times;
The recommendation module 14 is configured to determine a target point of interest based on the trip frequency matrix, and perform point location recommendation according to the target point of interest.
The point position recommending device 10 provided by the invention firstly acquires the current snap image information of a user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image; comparing the user snap image with a plurality of file information of the reference file set to determine target file information corresponding to the user snap image; determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of travel points, and a travel frequency matrix is used for describing the frequency of the user at each travel point at different time, wherein the travel points comprise pre-calculated distance similarity and time similarity; and determining a target interest point in the trip frequency matrix based on the current time information and the current point information, and performing point location recommendation according to the target interest point. Therefore, the interest point recommendation has obvious rationality, the interest demands of users corresponding to different time and different places can be solved, and the recommendation accuracy and recall rate are improved.
It should be noted that, the point location recommending device 10 provided in the embodiment of the present invention is a device corresponding to the point location recommending method, all embodiments of the point location recommending method are applicable to the point location recommending device 10, and the point location recommending device 10 has corresponding modules corresponding to the steps in the point location recommending method, so that the same or similar beneficial effects can be achieved, and in order to avoid excessive repetition, excessive redundant description is not performed on each module in the point location recommending device 2.
As shown in fig. 4, the embodiment of the present invention further provides an electronic device 20, including a memory 202, a processor 201, and a computer program stored in the memory 202 and executable on the processor 201, where the processor 201 implements the steps of the point location recommendation method described above when executing the computer program.
Specifically, the processor 201 is configured to call a computer program stored in the memory 202, and execute the following steps:
acquiring current snapshot image information of a user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image;
comparing the user snap image with a plurality of file information of the reference file set to determine target file information corresponding to the user snap image;
Determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of a user collected at a plurality of travel points, and a travel frequency matrix is used for describing the frequency of the user at each travel point at different time, wherein the travel points comprise pre-calculated distance similarity and time similarity;
and determining a target interest point in the trip frequency matrix based on the current time information and the current point information, and performing point location recommendation according to the target interest point.
Optionally, before the processor 201 executes to obtain the current snapshot image information of the user, the method includes:
according to the personnel image characteristics corresponding to the images to be archived, which are captured by each travel point, determining a similarity set between the images to be archived;
clustering the images to be archived based on the similarity set, archiving the images to be archived which meet the similarity threshold, and obtaining a reference archive set.
Optionally, the clustering of the images to be archived based on the similarity set performed by the processor 201, archiving the images to be archived that meet the similarity threshold, and after obtaining the reference archive set, includes:
Determining position information corresponding to each travel point position according to the reference file set, and calculating the distance between every two travel point positions;
and determining the distance similarity between every two travel points according to the distance between every two travel points.
Optionally, the clustering of the images to be archived based on the similarity set performed by the processor 201, archiving the images to be archived that meet the similarity threshold, and after obtaining the reference archive set, further includes:
determining the occurrence times of the user in the trip point location in each time period according to the reference file set;
constructing a travel frequency matrix according to the occurrence frequency, and carrying out normalization processing based on the travel frequency matrix to obtain a matrix vector corresponding to the travel frequency matrix;
and calculating based on the matrix vector, and determining the time similarity between every two travel points.
Optionally, the determining, by the processor 201, a corresponding trip number matrix according to the target archive information and the current point location information includes:
according to the target archive information, determining a historical visiting point position of the user;
determining the point position recommendation range of the user according to the current point position information;
taking the historical visit points in the point recommending range as points to be recommended;
And determining a corresponding travel frequency matrix based on the captured image information of the user acquired at the point to be recommended.
Optionally, determining the target point of interest based on the trip count matrix and recommending the target point of interest by the processor 201 includes:
determining the time similarity and the distance similarity corresponding to the travel point positions based on the travel point positions corresponding to the travel frequency matrix;
calculating according to the time similarity and the distance similarity to obtain total similarity;
and determining the target interest point according to the total similarity, and recommending according to the target interest point.
Optionally, the determining, by the processor 201, the target point of interest according to the total similarity, and recommending according to the target point of interest includes:
sequencing the travel points according to the total similarity, and determining a target travel point with the total similarity meeting a preset condition;
and taking the interest point address corresponding to the target trip point as the target interest point, and recommending according to the target interest point.
That is, in the embodiment of the present invention, the steps of the point location recommendation method are implemented when the processor 201 of the electronic device 20 executes the computer program, so that the point of interest recommendation has obvious rationality, the interest demands of users corresponding to different time and different places can be solved, and the accuracy and recall rate of recommendation are improved.
It should be noted that, since the steps of the point location recommendation method are implemented when the processor 201 of the electronic device 20 executes the computer program, all embodiments of the point location recommendation method are applicable to the electronic device 20, and the same or similar advantages can be achieved.
The computer readable storage medium provided in the embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, the computer program implements each process of the point location recommendation method or the application endpoint location recommendation method provided in the embodiment of the present invention, and the same technical effect can be achieved, so that repetition is avoided, and no further description is provided herein.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM) or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structural changes made by the specification and drawings of the present invention or direct/indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. A point location recommendation method, comprising:
acquiring current snapshot image information of a user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image;
Comparing the user snap image with a plurality of file information of a reference file set to determine target file information corresponding to the user snap image;
determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of the user collected at a plurality of travel points, the travel frequency matrix is used for describing the frequency of the user at each travel point at different time, and the travel points comprise pre-calculated distance similarity and time similarity;
and determining a target point of interest in the travel frequency matrix based on the current time information and the current point information, and performing point location recommendation according to the target point of interest.
2. The point recommendation method according to claim 1, wherein before the obtaining the current snap image information of the user, the method comprises:
according to personnel image features corresponding to the images to be archived, which are captured by each travel point, determining a similarity set between the images to be archived;
and clustering the images to be archived based on the similarity set, archiving the images to be archived which meet the similarity threshold, and obtaining the reference archive set.
3. The point recommendation method according to claim 2, wherein the clustering the images to be archived based on the similarity set and archiving the images to be archived that meet a similarity threshold value, after obtaining the reference archive set, includes:
determining position information corresponding to each travel point according to the reference file set, and calculating the distance between every two travel point;
and determining the distance similarity between the two travel points according to the distance between the two travel points.
4. The point recommendation method according to claim 2, wherein the clustering the images to be archived based on the similarity set, archiving the images to be archived that meet a similarity threshold, and after obtaining the reference archive set, further comprises:
determining the occurrence times of the user at the trip point location in each time period according to the reference file set;
constructing a travel frequency matrix according to the occurrence frequency, and carrying out normalization processing based on the travel frequency matrix to obtain a matrix vector corresponding to the travel frequency matrix;
and calculating based on the matrix vector, and determining the time similarity between every two travel points.
5. The point location recommendation method according to claim 1, wherein the determining the corresponding trip count matrix according to the target profile information and the current point location information includes:
determining a historical visit point of the user according to the target archive information;
determining the point position recommendation range of the user according to the current point position information;
taking the historical visit points in the point recommending range as points to be recommended;
and determining a corresponding travel frequency matrix based on the captured image information of the user acquired at the point to be recommended.
6. The point location recommendation method according to claim 1, wherein determining a target point of interest based on the trip count matrix and recommending the target point of interest includes:
based on the travel point positions corresponding to the travel times matrix, determining the time similarity and the distance similarity corresponding to the travel point positions;
calculating according to the time similarity and the distance similarity to obtain total similarity;
and determining a target point of interest according to the total similarity, and recommending according to the target point of interest.
7. The method of point recommendation according to claim 6, wherein determining a target point of interest according to the total similarity and recommending according to the target point of interest comprises:
sequencing all travel points according to the total similarity, and determining a target travel point position of which the total similarity meets a preset condition;
and taking the interest point address corresponding to the target trip point as a target interest point, and recommending according to the target interest point.
8. A point location recommendation device, comprising:
the acquisition module is used for acquiring the current snapshot image information of the user; the current snapshot image information comprises a user snapshot image, current time information corresponding to the user snapshot image and current point location information corresponding to the user snapshot image;
the comparison module is used for comparing the user snap image with the plurality of file information of the reference file set to determine target file information corresponding to the user snap image;
the determining module is used for determining a corresponding travel frequency matrix according to the target archive information and the current point location information; the target archive information comprises snapshot image information of the user collected at a plurality of travel points, the travel frequency matrix is used for describing the frequency of the user at each travel point at different time, and the travel points comprise pre-calculated distance similarity and time similarity;
And the recommending module is used for determining a target interest point in the travel frequency matrix based on the current time information and the current point information and recommending the point according to the target interest point.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the spot recommendation method according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the point location recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310131482.3A CN116401443A (en) | 2023-02-03 | 2023-02-03 | Point location recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310131482.3A CN116401443A (en) | 2023-02-03 | 2023-02-03 | Point location recommendation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116401443A true CN116401443A (en) | 2023-07-07 |
Family
ID=87011229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310131482.3A Pending CN116401443A (en) | 2023-02-03 | 2023-02-03 | Point location recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116401443A (en) |
-
2023
- 2023-02-03 CN CN202310131482.3A patent/CN116401443A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920174B (en) | Book borrowing method and device, electronic equipment and storage medium | |
| CN113196331B (en) | Application service providing device and method using satellite image | |
| CN108446281A (en) | Determine the method, apparatus and storage medium of user's cohesion | |
| CN110110669A (en) | A kind of wisdom scenic spot tourist's localization method and system based on face recognition technology | |
| CN111954175B (en) | Method for judging visiting of interest point and related device | |
| CN108363783B (en) | The binding method and device of MAC Address and identity information | |
| CN112770265B (en) | Pedestrian identity information acquisition method, system, server and storage medium | |
| CN112214677B (en) | Point of interest recommendation method and device, electronic equipment and storage medium | |
| JP2008243130A (en) | Population estimation device and program | |
| CN111400550A (en) | Target motion trajectory construction method and device and computer storage medium | |
| CN111380530A (en) | Navigation method and related product | |
| CN115410104A (en) | Data processing system for acquiring image acquisition points of aircraft | |
| CN111242723B (en) | User child and child condition judgment method, server and computer readable storage medium | |
| CN115565154A (en) | Feasible region prediction method, device, system and storage medium | |
| CN114078277A (en) | One-person-one-file face clustering method and device, computer equipment and storage medium | |
| CN111065044B (en) | Big data based data association analysis method and device and computer storage medium | |
| CN113962326A (en) | Clustering method, device, equipment and computer storage medium | |
| CN110262863B (en) | Method and device for displaying terminal main interface | |
| CN112651366B (en) | Passenger flow number processing method and device, electronic equipment and storage medium | |
| Ghazal et al. | Mobile-based archival and retrieval of missing objects using image matching | |
| CN115272025A (en) | Method, device and storage medium for determining population distribution thermodynamic data | |
| CN114547386A (en) | Positioning method and device based on Wi-Fi signal and electronic equipment | |
| CN116401443A (en) | Point location recommendation method and device, electronic equipment and storage medium | |
| CN112218046A (en) | Object monitoring method and device | |
| CN108985898B (en) | Site scoring method and device and computer readable storage medium |
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 |