CN112861023A - Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product - Google Patents
Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product Download PDFInfo
- Publication number
- CN112861023A CN112861023A CN202110145478.3A CN202110145478A CN112861023A CN 112861023 A CN112861023 A CN 112861023A CN 202110145478 A CN202110145478 A CN 202110145478A CN 112861023 A CN112861023 A CN 112861023A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- interest
- historical
- point
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 30
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The present disclosure provides a map information processing method, apparatus, device, storage medium, and program product, and relates to the field of artificial intelligence technologies such as intelligent search, deep learning, nlp (natural Language process). The specific implementation scheme is as follows: acquiring character information of at least one minimum unit input by a user; acquiring merging information according to the character information of the at least one minimum unit and the time-space related information of the user; calculating the similarity between the merged information and each piece of interest point information in the plurality of pieces of interest point information in the map according to the merged information; and determining at least one interest point in the interest points and the corresponding sequence of the interest points according to the similarity. The method and the device for recommending the interest points of the map related products can improve accuracy and efficiency of recommending the interest points of the map related products.
Description
Technical Field
The present disclosure relates to the technical field of computer technology, and in particular, to the technical field of artificial intelligence, such as intelligent search, deep learning, nlp (natural Language process), and the like.
Background
With the development of terminal technologies and computer technologies such as mobile terminals, maps are becoming one of the more indispensable tools in people's daily life. In the processes of travel route planning, taxi taking, positioning and the like, accurate and efficient information such as geographic positions, geographic routes and the like needs to be acquired by means of maps.
In a map, a user can generally search for a Point of Interest (POI) and a specific location of the POI, but since the number of the POI is huge within a certain range, the user is often required to input a complete POI name to obtain the POI. This results in poor user experience and inefficient querying.
Disclosure of Invention
The present disclosure provides a method, apparatus, device, storage medium, and program product for map information processing.
According to an aspect of the present disclosure, there is provided a map information processing method including:
acquiring character information of at least one minimum unit input by a user;
acquiring merging information according to the character information of at least one minimum unit and the time-space related information of the user;
according to the merged information, calculating the similarity between the merged information and each piece of interest point information in a plurality of pieces of interest point information in the map;
and determining at least one interest point in the interest points and the corresponding sequence of the at least one interest point according to the similarity.
According to another aspect of the present disclosure, there is provided a map information processing apparatus including:
the character information module is used for acquiring character information of at least one minimum unit input by a user;
the merging module is used for acquiring merging information according to the character information of at least one minimum unit and the time-space related information of the user;
the similarity module is used for calculating the similarity between the merged information and each piece of interest point information in the plurality of pieces of interest point information in the map according to the merged information;
and the recommendation module is used for determining at least one interest point in the interest points and the sequence corresponding to the at least one interest point according to the similarity.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method in any of the embodiments of the present disclosure.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method in any of the embodiments of the present disclosure.
According to the technology disclosed by the invention, the at least one interest point and the sequence corresponding to the at least one interest point can be determined according to the character information of the minimum unit input by the user and the time-space related information of the user, so that a quick response can be made when the user searches the interest points, the interest points which the user most probably wants to search at present are recommended to the user in the shortest time, the input and determination efficiency of the interest points is improved, and the use experience of the user is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of a map information processing method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a map information processing method according to another embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a map information processing method according to an example of the present disclosure;
FIG. 4 is a schematic diagram of information related to a model structure according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of the operation of a system according to an embodiment of the present disclosure;
FIG. 6 is a first schematic diagram of a map information processing apparatus according to an embodiment of the present disclosure;
FIG. 7 is a diagram of a second map information processing apparatus according to an embodiment of the present disclosure;
FIG. 8 is a third schematic diagram of a map information processing apparatus according to an embodiment of the present disclosure;
FIG. 9 is a fourth schematic diagram of a map information processing apparatus according to an embodiment of the present disclosure;
FIG. 10 is a fifth schematic diagram of a map information processing apparatus according to an embodiment of the present disclosure;
FIG. 11 is a sixth schematic view of a map information processing apparatus according to an embodiment of the present disclosure;
FIG. 12 is a seventh schematic diagram of a map information processing apparatus according to an embodiment of the present disclosure;
fig. 13 is a block diagram of an electronic device for implementing a map information processing method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The embodiment of the present disclosure first provides a map information processing method, as shown in fig. 1, including:
step S11: acquiring character information of at least one minimum unit input by a user;
step S12: acquiring merging information according to the character information of at least one minimum unit and the time-space related information of the user;
step S13: calculating the similarity between the merged information and the information of the plurality of interest points in the map according to the merged information;
step S14: and determining at least one interest point in the interest points and the corresponding sequence of the at least one interest point according to the similarity.
In this embodiment, the at least one minimum unit of character information input by the user may be at least one of characters in a minimum unit included in characters, letters, or numbers.
For example, when the user inputs "two" by using the stroke input method, the user firstly inputs one bar "one", and then inputs another bar "one". Then the bar "one" can be the character of the smallest unit.
For another example, when the user inputs "hospital" by using the pinyin input method, the letter "y" is first input, and then the initial letter "y" or "i" in the pinyin of "doctor" may be continuously input, so that "y" and "i" may be characters of a minimum unit, respectively.
For another example, if the user inputs a chinese character by using the five-stroke input method, each time a five-stroke symbol is input, the input five-stroke symbol may be used as a character of a minimum unit.
In a possible implementation manner, the character information of at least one minimum unit input by the user is obtained, and the input operation of the user may be used as the standard.
For example, the user completes the click operation by clicking the character button, the character input by the current user can be obtained by detecting that the user completes one click operation, and the character information of at least one minimum unit is obtained according to the character input by the current user.
In one possible specific implementation, for example, when the user inputs the letter "y" by clicking a character button, the character information of at least one minimum unit currently input by the user is obtained to include "y".
For another example, the user inputs the letters "y" and "i" by clicking the character button, and the letters "y" and "i" are the two smallest units of character information input by the user.
As yet another example, the user enters strokes "left-falling" and "down" through the stroke input method, the strokes "left-falling" and "down" are the two smallest units of character information entered by the user.
As yet another example, the user enters strokes "left-falling" and "down" through the stroke input method, the strokes "left-falling" and "down" are the two smallest units of character information entered by the user. The user then deletes the strokes "down" through either the undo button or the delete button, the remaining strokes "left-falling" are the smallest units of character information entered by the user.
In this embodiment, the user's spatiotemporal related information may specifically include all information related to time or space in the user related information. The query result can be obtained according to historical query records of the user, and can also be obtained according to the current space-time information of the user.
In this embodiment, the spatiotemporal related information of the user may be related to the current location of the user and the search history of the user at the current location.
Acquiring merging information according to the character information of at least one minimum unit and the time-space related information of the user, wherein the acquiring of the merging information specifically comprises acquiring a character information vector input by the user according to the character information of at least one minimum unit; obtaining a space-time correlation vector according to the space-time correlation information of the user; and performing calculation operations such as splicing or adding on the character information vector and the space-time correlation vector to obtain a combined vector, and obtaining combined information according to the combined vector.
In a specific possible implementation manner, the merging information is obtained according to the merging vector, and the merging vector may be used as the merging information.
According to the merged information, calculating similarity between the merged information and the plurality of interest point information in the map, which may specifically include converting the merged information and each of the plurality of interest point information into information of the same dimension, and calculating similarity between the merged information and each of the plurality of interest point information.
In this embodiment, determining at least one of the interest points and an order of the at least one interest point according to the similarity may include: and selecting at least one previous interest point with the highest similarity to the combined information, and determining the sequence of the selected at least one interest point.
According to the character information of the minimum unit input by the user and the time-space related information of the user, the method and the device for searching the interest points can determine the at least one interest point and the sequence corresponding to the at least one interest point, so that when the user searches the interest points, a quick response can be made, the interest points which the user most probably wants to search currently are recommended to the user in the shortest time, the input and determination efficiency of the interest points is improved, and the use experience of the user is improved.
In one embodiment, the spatiotemporal related information includes historical point of interest information input by the user; before obtaining the combined information according to the character information of at least one minimum unit and the spatio-temporal related information of the user, the method further comprises the following steps:
and obtaining the time-space related information of the user according to the historical interest points.
In this embodiment, the historical interest points may be interest points in the user search history. It may also be that the user has searched for points of interest in the history over the last period of time.
In this embodiment, the obtaining of the spatiotemporal related information of the user according to the historical interest points may specifically include screening at least one interest point from the historical interest points according to a set screening rule, and obtaining the spatiotemporal related information of the user according to the screened at least one interest point.
In the embodiment, the time-space related information of the user is obtained according to the historical interest points, so that the interest points obtained through recommendation can accord with the habit of searching the interest points of the user, and the recommended interest points can accord with the expectation of the user better.
In one embodiment, the historical interest points include a first historical interest point, and as shown in fig. 2, obtaining the spatiotemporal related information of the user according to the historical interest points includes:
step S21: obtaining a first historical interest point according to the searching frequency of a user on at least one interest point within a set time range;
step S22: and acquiring the time-space related information of the user according to the first historical interest point.
In a possible implementation manner, obtaining a first historical interest point according to a search frequency of a user for at least one interest point within a set time range may specifically include: and taking the historical interest points of which the search times exceed a first search time threshold value within a set time range as first historical interest points.
In a possible implementation manner, the spatiotemporal related information of the user is obtained according to the first historical interest point, which may be to obtain a corresponding vector representation according to the type of the first historical interest point, and the vector representation corresponding to the first historical interest point is used as the spatiotemporal related information of the user.
In another possible implementation manner, the first historical interest point is obtained according to the search frequency of the user for the at least one interest point within the set time range, which may be determining the search history corresponding to the address where the user is currently located according to the address where the user is currently located, determining the search frequency of the at least one interest point within the set time range in the search history, and determining the first historical interest point according to the search frequency.
In the embodiment, the time-space related information of the user is obtained according to the search frequency, so that the recommended interest points are more in line with the search habits of the user.
In one embodiment, the historical interest points include a second historical interest point, and the obtaining of the spatiotemporal related information of the user according to the historical interest points comprises:
obtaining a set number of latest search interest points as second historical interest points;
and obtaining the time-space related information of the user according to the second historical interest point.
In this embodiment, a set number of recently searched interest points are obtained as the second historical interest points, for example, 1 to 10 interest points determined to be recently searched are determined.
In another possible implementation manner, the number of the obtained nearest search interest points can be determined according to the position change event of the user. For example, by using the positioning device, it is detected that the address of the user is switched from city a to city B three days ago, and then, within the range of city B, a smaller number of historical interest points can be obtained as the second historical interest point.
In another possible implementation manner, the set number of recent search interest points is obtained, and may be the set number of recent search interest points in the administrative area range where the user is located.
In the embodiment, a set number of recently searched interest points are obtained, and then the time-space related information of the user is obtained according to the recently searched interest points, so that the recommended interest points are more suitable for the current most possibly searched place of the user, and the user experience is improved.
In one embodiment, obtaining spatiotemporal relevant information of a user according to historical interest points comprises:
acquiring the type of historical interest points;
mapping the type to a tag code;
and obtaining the time-space related information of the user according to the label codes.
The types of historical points of interest may include transportation hubs, transportation facilities, entertainment venues, leisure venues, residential areas, medical venues, schools, administrative institutions, and the like.
The type of the historical interest point may be at least one of all preset interest point types. All the preset interest point types can be added and deleted along with the development of city construction pace.
The label codes corresponding to the types of the historical interest points can be obtained through a mapping model obtained through pre-training.
Obtaining the spatiotemporal related information of the user according to the tag coding may include: and obtaining a corresponding space-time vector according to the label coding, and taking the space-time vector as the space-time related information of the user.
In the case that the historical interest points include the first historical interest point and the second historical interest point in the foregoing embodiment, the number of the first historical interest point and the number of the second historical interest point may be the same or different, and are set according to actual needs.
In the embodiment, the spatiotemporal related information of the user is obtained according to the types of the historical interest points, so that the recommended interest points and the corresponding sequence are more in line with the habits and possible expectations of the user.
In one embodiment, the spatiotemporal correlation information is obtained from at least one of user current location information and user current time information.
In one possible implementation, the spatiotemporal correlation information is obtained based on the user's current location information.
In another possible implementation, the spatiotemporal correlation information is obtained from the user's current temporal information.
In one possible implementation, the spatiotemporal correlation information is obtained based on the user's current location information and the user's current time information.
Because the interest point searched by the user has a large time correlation with the position of the user and the time when the user searches, for example, the interest point searched by the user may be a home address and a work unit address during the morning work time period. As another example, during the holiday time period, the user may search for other points of interest than the home address and the non-work unit address. The spatio-temporal related information is obtained according to at least one of the current position information and the current time information of the user, the interest points can be recommended to the user more accurately according to the overall requirements of the user group, the time for the user to find the interest points expected to be searched is reduced, and the user experience is improved.
In one possible implementation, the spatiotemporal relevant information of the user may be obtained according to the first historical interest point, the second historical interest point, the current position information of the user and the current time information of the user.
In a possible implementation manner, a first coding manner may be adopted for coding according to the first historical interest point and the second historical interest point to obtain a first code; coding in a second coding mode according to the current position information and the current time information of the user to obtain a second code; and converting the first code and the second code into the same dimension, and then combining the first code and the second code to obtain the user time-space related information.
In one embodiment, acquiring at least one minimum unit of character information input by a user comprises:
acquiring a total character input by a user;
character information of at least one minimum unit included in a total character input by a user is acquired.
The total characters input by the user may include complete Chinese characters, numbers, letters and the like, and may also include partial strokes of the Chinese characters, the numbers and the letters. The total characters input by the user may also include partial strokes of foreign characters.
In the embodiment, the total characters input by the user are obtained, more useful suggestions can be obtained according to the information currently provided by the user, and therefore interest points more consistent with the expectation of the user are recommended for the user.
In one embodiment, each of the plurality of point of interest information is obtained by:
and obtaining the information of each interest point according to at least one of the longitude and latitude information, the address information and the name information of each interest point.
In this embodiment, the information of the multiple interest points may be information of a part of all interest points in the location range where the user is located.
In this embodiment, the longitude and latitude information of the point of interest may be longitude information and latitude information of the point of interest under the earth longitude and latitude standard.
The address information of the point of interest may be mailing address information, such as a certain number of units in a certain street in a certain area, and the like.
The interest point name may be a name representing the attribute and content of the interest point, such as a certain amusement park, a certain school, a certain park, a certain hospital, a certain cell, and the like.
Obtaining the information of each point of interest according to at least one of the longitude and latitude information, the address information and the name information of each point of interest, which may include obtaining the information of each point of interest according to the longitude information, the latitude information, the address information and the name information of each point of interest.
In one example of the present disclosure, a deep learning-based method may be employed to model the behavior of a user, and obtain spatiotemporal related information (hereinafter referred to as "user representation"), point of interest information (hereinafter referred to as "POI representation"), and at least one minimum unit of character information (hereinafter referred to as "sug information" (suggestion information)) of the user.
Wherein, the user representation obtaining mode is as follows: and constructing a long and short interest sequence of the historical clicks of the user according to the historical clicks, considering the long and short interests of the user, counting 3 high frequencies of the last month of the user as long-term interests, 7 recent clicks as short-term interest points, and mapping the 10 click POIs to corresponding tags as historical interest information of the user to represent the historical behaviors of the user.
User initiated requested spatiotemporal information is also particularly important for user spotting, the present example encodes and incorporates user spatiotemporal information into the user representation.
Simultaneously, the POI representation acquisition mode is as follows: and fusing the POI name, the address and the longitude and latitude together by adopting a similar coding mode to comprehensively represent the POI information.
The specific technical means adopted in the example are as follows:
the user representation is obtained by the steps shown in fig. 3:
step S31: a user point of interest representation is obtained.
Different users have different clicking behaviors, the length and the interest of the users are considered according to the positions and the time of the interest points clicked by the users, 3 high frequencies of the users in the last month are counted as long-term interest, 7 recent clicks are counted as short-term interest points, the 10 historical click POIs 401 (historical interest points) are mapped into corresponding tags, the 10 tags are subjected to embedding mapping, and finally the tags are coded and expressed as interest point representations of the users through a CNN (Convolutional Neural network).
Step S32: and acquiring the space-time information representation requested by the user.
When a user initiates a request, the user has coordinate information and time information of the corresponding initiation request except for a query prefix. The method aims to solve the problem of complex and various query prefixes (combining pinyin, Chinese character numbers and the like), statistics is carried out on the query prefixes of a user in a month by utilizing big data, word segmentation is adopted for the query to generate a corresponding word list, and the word list is used as a query and POI segmentation word list so that the complex query can be segmented. For example, a user inputs [ Beijing daxue ], divides the query into [ Beijing ] da ] and [ xue ] corresponding to four words according to the wordpace algorithm, and encodes the four words through CNN to generate a query vector.
The time-space related information of the user also comprises the current time of the user and the latitude and longitude of the place. In this example, a binary hash encoding is used for time and latitude and longitude, and the final space-time feature encoding may be a 01 vector with 38 dimensions.
Step S33: a user final vector representation is obtained. The user final vector representation 402 is composed of two parts of the results from steps S31 and S32, as shown in fig. 4, i.e., the user historical interest points and spatio-temporal information.
In this example, POI representation 403 may be obtained by: the POI side has basic information composition of the POI, as shown in fig. 4, the basic information includes a POI name (name), an address (addr) and an anchor point (goe). The method comprises the steps of adopting the same processing means as query to the poi name and address, firstly utilizing word segmentation of a word algorithm to generate the id of a corresponding word, then carrying out embedding mapping on the id, and finally carrying out coding on the id through CNN to generate the vector of the name and the address. For the longitude and latitude of the positioning point, the binary hash coding is also adopted here, and position information expressed as poi of a 01 vector with 30 dimensions is generated. The final representation of the POI, as shown in fig. 4, is a combination of codes generated from the POI name, address, and latitude and longitude described above.
In order to better acquire information of the poi and the user, a full connection layer FC (full connection) is added after the information, the user captures important information of the poi and the user, and a vector generated by the FC calculates similarity of the poi and the user through cosine function distance. In summary, the similarity includes personalized features of historical clicks, time and space, and the like of the user, and is a better feature for measuring the user and the search poi.
In summary, when a user inputs a sug search segment, similarity between the sug search segment and the poi can be obtained through personalized modeling of the user and accurate representation of the poi, and the problem that prefix query cannot be accurately sequenced due to complicated user input is solved.
In one example of the present application, as shown in fig. 5, a map information processing method includes acquiring a user representation 501 and a POI representation 502, which is represented as a plurality of point of interest information in a map in the foregoing embodiment. After a User initiates a request, obtaining a historical click sequence and characters in an input request (query), performing word segmentation operation on the characters in the request to obtain at least one character with a minimum unit, and inputting information after word segmentation and the obtained historical click sequence into a User model (User model), wherein the User model can be a convolutional neural network model to obtain a model output code.
Referring to fig. 5, after the user initiates the request, the current time and the location point (address) of the user are also obtained, and the binary hash coding mode is adopted to perform coding, so as to obtain the first hash code.
And finally, outputting the codes and the first Hash codes according to the user model to obtain a user semantic vector, wherein the user semantic vector is used for carrying out similarity comparison with a plurality of interest point information in the map.
Each interest point information in the plurality of interest point information is obtained in the following manner: segmenting the name and the address of the interest point, and inputting the segmentation into the POI model to obtain the POI model code; and encoding the latitude and longitude of the interest point (POI positioning point) by adopting a binary hash encoding mode to obtain a second hash code. And obtaining a POI semantic vector according to the POI model coding and the second hash coding.
And finally, calculating the similarity between the user semantic vector and the POI semantic vector of each interest point in the plurality of interest points according to the cos function to obtain the similarity between the user semantic vector and the POI semantic vector of each interest point. And selecting a plurality of interest points according to the similarity between the user semantic vector and the POI semantic vector of each interest point, and determining the sequence of the selected interest points.
An embodiment of the present disclosure further provides a map information processing apparatus, as shown in fig. 6, including:
the character information module 61 is used for acquiring at least one minimum unit of character information input by a user;
a merging module 62, configured to obtain merging information according to the character information of at least one minimum unit and the spatiotemporal related information of the user;
a similarity module 63, configured to calculate, according to the merged information, a similarity between the merged information and each piece of interest point information in the multiple pieces of interest point information in the map;
and a recommending module 64, configured to determine at least one of the interest points and an order corresponding to the at least one interest point according to the similarity.
In one embodiment, the spatiotemporal related information includes historical point of interest information input by the user; as shown in fig. 7, the apparatus further comprises:
and the spatiotemporal related information module 71 is used for obtaining spatiotemporal related information of the user according to the historical interest points.
In one embodiment, the historical points of interest include a first historical point of interest, and as shown in FIG. 8, the spatiotemporal correlation information module includes:
a first historical interest point unit 81, configured to obtain a first historical interest point according to a search frequency of a user on at least one interest point within a set time range;
and the first historical interest point processing unit 82 is used for obtaining the spatiotemporal related information of the user according to the first historical interest point.
In one embodiment, the historical points of interest include a second historical point of interest, as shown in FIG. 9, the spatiotemporal correlation information module includes:
a second history interest point unit 91, configured to obtain a set number of latest search interest points as second history interest points;
and the second historical interest point processing unit 92 is configured to obtain spatiotemporal related information of the user according to the second historical interest point.
In one embodiment, as shown in FIG. 10, the spatiotemporal correlation information module includes:
a type unit 101, configured to obtain a type of a historical interest point;
an encoding unit 102, configured to map the type into a tag code;
and the encoding processing unit 103 is used for obtaining the spatiotemporal related information of the user according to the label encoding.
In one embodiment, the spatiotemporal correlation information is obtained from at least one of user current location information and user current time information.
In one embodiment, as shown in fig. 11, the character information module includes:
a total character unit 111 for acquiring a total character input by a user;
the decomposition unit 112 is configured to obtain character information of at least one minimum unit included in the total characters input by the user.
In one embodiment, as shown in fig. 12, each of the plurality of point of interest information is obtained by:
the interest point information module 121 is configured to obtain information of each interest point according to at least one of latitude and longitude information, address information, and name information of each interest point.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 13 shows a schematic block diagram of an example electronic device 130 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 13, the electronic apparatus 130 includes a computing unit 131 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)132 or a computer program loaded from a storage unit 138 into a Random Access Memory (RAM) 133. In the RAM 133, various programs and data necessary for the operation of the electronic apparatus 130 can also be stored. The calculation unit 131, the ROM 132, and the RAM 133 are connected to each other via a bus 134. An input/output (I/O) interface 135 is also connected to bus 134.
Various components in the electronic device 130 are connected to the I/O interface 135, including: an input unit 136 such as a keyboard, a mouse, or the like; an output unit 137 such as various types of displays, speakers, and the like; a storage unit 138 such as a magnetic disk, optical disk, or the like; and a communication unit 139 such as a network card, modem, wireless communication transceiver, etc. The communication unit 139 allows the electronic device 130 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 131 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 131 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 131 executes the respective methods and processes described above, such as the map information processing method. For example, in some embodiments, the map information processing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 138. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 130 via the ROM 132 and/or the communication unit 139. When the computer program is loaded into the RAM 133 and executed by the calculation unit 131, one or more steps of the map information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 131 may be configured to perform the map information processing method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (19)
1. A map information processing method includes:
acquiring character information of at least one minimum unit input by a user;
acquiring merging information according to the character information of the at least one minimum unit and the time-space related information of the user;
calculating the similarity between the merged information and each piece of interest point information in the plurality of pieces of interest point information in the map according to the merged information;
and determining at least one interest point in the interest points and the corresponding sequence of the interest points according to the similarity.
2. The method of claim 1, wherein before obtaining the combined information according to the at least one minimum unit of character information and the spatiotemporal related information of the user, further comprising:
and obtaining the time-space related information of the user according to the historical interest points.
3. The method of claim 2, wherein the historical points of interest comprise a first historical point of interest, and wherein obtaining spatiotemporal relevant information of the user from the historical points of interest comprises:
obtaining the first historical interest point according to the searching frequency of the user on the at least one interest point within a set time range;
and acquiring the time-space related information of the user according to the first historical interest point.
4. The method of claim 2, wherein the historical points of interest include a second historical point of interest, and wherein obtaining spatiotemporal relevant information of the user from the historical points of interest comprises:
obtaining a set number of latest search interest points as the second historical interest points;
and acquiring the time-space related information of the user according to the second historical interest point.
5. The method of claim 2, wherein the obtaining spatiotemporal relevant information of the user from historical points of interest comprises:
acquiring the type of the historical interest points;
mapping the type to a tag code;
and obtaining the time-space related information of the user according to the label codes.
6. The method of claim 1, wherein the spatiotemporal correlation information is obtained from at least one of user current location information and user current time information.
7. The method according to any one of claims 1-6, wherein the acquiring at least one minimum unit of character information input by a user comprises:
acquiring a total character input by a user;
and acquiring character information of at least one minimum unit included in the total characters input by the user.
8. The method of any of claims 1-6, wherein each of the plurality of point of interest information is obtained by:
and obtaining the information of each interest point according to at least one of the longitude and latitude information, the address information and the name information of each interest point.
9. A map information processing apparatus comprising:
the character information module is used for acquiring character information of at least one minimum unit input by a user;
the merging module is used for obtaining merging information according to the character information of the at least one minimum unit and the time-space related information of the user;
the similarity module is used for calculating the similarity between the merged information and each piece of interest point information in the plurality of pieces of interest point information in the map according to the merged information;
and the recommending module is used for determining at least one interest point in the interest points and the sequence corresponding to the interest point according to the similarity.
10. The apparatus of claim 9, wherein the apparatus further comprises:
and the time-space related information module is used for obtaining the time-space related information of the user according to the historical interest points.
11. The apparatus of claim 10, wherein the historical points of interest comprise a first historical point of interest, the spatiotemporal correlation information module comprising:
the first historical interest point unit is used for obtaining the first historical interest point according to the searching frequency of the user on the at least one interest point within a set time range;
and the first historical interest point processing unit is used for obtaining the time-space related information of the user according to the first historical interest point.
12. The apparatus of claim 10, wherein the historical points of interest comprise a second historical point of interest, the spatiotemporal correlation information module comprising:
a second history interest point unit, configured to obtain a set number of latest search interest points as the second history interest points;
and the second historical interest point processing unit is used for obtaining the time-space related information of the user according to the second historical interest point.
13. The apparatus of claim 10, wherein the spatiotemporal correlation information module comprises:
the type unit is used for acquiring the type of the historical interest point;
an encoding unit for mapping the type to a tag code;
and the coding processing unit is used for obtaining the time-space related information of the user according to the label coding.
14. The apparatus of claim 10, wherein the spatiotemporal correlation information is obtained from at least one of user current location information and user current time information.
15. The apparatus of any one of claims 9-14, wherein the character information module comprises:
the total character unit is used for acquiring total characters input by a user;
and the decomposition unit is used for acquiring character information of at least one minimum unit included in the total characters input by the user.
16. The apparatus of any of claims 9-14, wherein each of the plurality of point of interest information is obtained by:
and the interest point information module is used for acquiring the information of each interest point according to at least one of the longitude and latitude information, the address information and the name information of each interest point.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-8.
19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110145478.3A CN112861023A (en) | 2021-02-02 | 2021-02-02 | Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110145478.3A CN112861023A (en) | 2021-02-02 | 2021-02-02 | Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112861023A true CN112861023A (en) | 2021-05-28 |
Family
ID=75986756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110145478.3A Pending CN112861023A (en) | 2021-02-02 | 2021-02-02 | Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861023A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113608628A (en) * | 2021-08-18 | 2021-11-05 | 中国第一汽车股份有限公司 | Interest point input method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
| CN104063383A (en) * | 2013-03-19 | 2014-09-24 | 北京三星通信技术研究有限公司 | Information recommendation method and device |
| CN104408168A (en) * | 2014-12-09 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Map searching method and regional tendency recognition method and device |
| US9282161B1 (en) * | 2012-10-26 | 2016-03-08 | Amazon Technologies, Inc. | Points of interest recommendations |
| CN107315750A (en) * | 2016-04-26 | 2017-11-03 | 斑马网络技术有限公司 | Electronic map figure layer display methods, device, terminal device and user interface system |
| CN110781413A (en) * | 2019-08-28 | 2020-02-11 | 腾讯大地通途（北京）科技有限公司 | Interest point determining method and device, storage medium and electronic equipment |
| CN110781415A (en) * | 2019-09-16 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Interest point recommendation method, device, equipment and medium |
| CN111241427A (en) * | 2020-01-06 | 2020-06-05 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and computer storage medium for query automatic completion |
| CN111538904A (en) * | 2020-04-27 | 2020-08-14 | 北京百度网讯科技有限公司 | Method and device for recommending interest points |
| CN111708876A (en) * | 2020-06-16 | 2020-09-25 | 北京百度网讯科技有限公司 | Method and device for generating information |
| CN111859060A (en) * | 2020-01-10 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Information query method and device, electronic equipment and readable storage medium |
| CN111859174A (en) * | 2019-12-03 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining recommended boarding point |
| CN111859168A (en) * | 2019-05-24 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining interest points |
| CN112069415A (en) * | 2020-08-13 | 2020-12-11 | 中国海洋大学 | Interest point recommendation method based on heterogeneous attribute network characterization learning |
-
2021
- 2021-02-02 CN CN202110145478.3A patent/CN112861023A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9282161B1 (en) * | 2012-10-26 | 2016-03-08 | Amazon Technologies, Inc. | Points of interest recommendations |
| CN104063383A (en) * | 2013-03-19 | 2014-09-24 | 北京三星通信技术研究有限公司 | Information recommendation method and device |
| CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
| CN104408168A (en) * | 2014-12-09 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Map searching method and regional tendency recognition method and device |
| CN107315750A (en) * | 2016-04-26 | 2017-11-03 | 斑马网络技术有限公司 | Electronic map figure layer display methods, device, terminal device and user interface system |
| CN111859168A (en) * | 2019-05-24 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining interest points |
| CN110781413A (en) * | 2019-08-28 | 2020-02-11 | 腾讯大地通途（北京）科技有限公司 | Interest point determining method and device, storage medium and electronic equipment |
| CN110781415A (en) * | 2019-09-16 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Interest point recommendation method, device, equipment and medium |
| CN111859174A (en) * | 2019-12-03 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining recommended boarding point |
| CN111241427A (en) * | 2020-01-06 | 2020-06-05 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and computer storage medium for query automatic completion |
| CN111859060A (en) * | 2020-01-10 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Information query method and device, electronic equipment and readable storage medium |
| CN111538904A (en) * | 2020-04-27 | 2020-08-14 | 北京百度网讯科技有限公司 | Method and device for recommending interest points |
| CN111708876A (en) * | 2020-06-16 | 2020-09-25 | 北京百度网讯科技有限公司 | Method and device for generating information |
| CN112069415A (en) * | 2020-08-13 | 2020-12-11 | 中国海洋大学 | Interest point recommendation method based on heterogeneous attribute network characterization learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113608628A (en) * | 2021-08-18 | 2021-11-05 | 中国第一汽车股份有限公司 | Interest point input method, device, equipment and storage medium |
| WO2023020529A1 (en) * | 2021-08-18 | 2023-02-23 | 中国第一汽车股份有限公司 | Method and apparatus for inputting point-of-interest, and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200326197A1 (en) | Method, apparatus, computer device and storage medium for determining poi alias | |
| US11630560B2 (en) | Map information display method and apparatus, electronic device, and computer storage medium | |
| CN110926486B (en) | Route determining method, device, equipment and computer storage medium | |
| CN108304423A (en) | A kind of information identifying method and device | |
| CN110688449A (en) | Address text processing method, device, equipment and medium based on deep learning | |
| CN112612957A (en) | Interest point recommendation method, interest point recommendation model training method and device | |
| CN111382212B (en) | Associated address acquisition method and device, electronic equipment and storage medium | |
| US20230049839A1 (en) | Question Answering Method for Query Information, and Related Apparatus | |
| JP2023530795A (en) | Geolocation zone encoding method, method for establishing encoding model, and apparatus | |
| KR102601545B1 (en) | Geographic position point ranking method, ranking model training method and corresponding device | |
| CN111666461B (en) | Method, apparatus, device and computer storage medium for retrieving geographic location | |
| CN113641805A (en) | Acquisition method of structured question-answering model, question-answering method and corresponding device | |
| CN112632379A (en) | Route recommendation method and device, electronic equipment and storage medium | |
| CN112861023A (en) | Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product | |
| CN112818072A (en) | Tourism knowledge map updating method, system, equipment and storage medium | |
| CN113360791B (en) | Interest point query method and device of electronic map, road side equipment and vehicle | |
| CN114820960B (en) | Method, device, equipment and medium for constructing map | |
| CN111782748B (en) | Map retrieval method, information point POI semantic vector calculation method and device | |
| CN112966192A (en) | Region address naming method and device, electronic equipment and readable storage medium | |
| CN112507223A (en) | Data processing method and device, electronic equipment and readable storage medium | |
| CN111797183A (en) | Method and device for mining road attribute of information point and electronic equipment | |
| CN112035751A (en) | Information recommendation method, device, equipment and storage medium | |
| CN113449754A (en) | Method, device, equipment and medium for training and displaying matching model of label | |
| CN114861062B (en) | Information filtering method and device | |
| CN114036414A (en) | Method and device for processing interest points, electronic equipment, medium and program product |
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 |