CN111831867A - Address query method and device, electronic equipment and computer readable storage medium - Google Patents
Address query method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111831867A CN111831867A CN202010255863.9A CN202010255863A CN111831867A CN 111831867 A CN111831867 A CN 111831867A CN 202010255863 A CN202010255863 A CN 202010255863A CN 111831867 A CN111831867 A CN 111831867A
- Authority
- CN
- China
- Prior art keywords
- address
- category
- road
- query request
- address query
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000013145 classification model Methods 0.000 claims description 48
- 238000004590 computer program Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 description 10
- 230000004044 response Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 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
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- 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
- G06F16/906—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an address query method, an address query device, electronic equipment and a computer readable storage medium.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to an address query method, an address query device, an electronic device, and a computer-readable storage medium.
Background
At present, people's lives are not away from the inquiry of various POI (Point of interest) addresses, such as route search, etc., wherein different types of users may use different search vocabularies for searching, such as keyword search or road number search, etc., and how to quickly and accurately obtain a target location address for different search vocabularies is an urgent problem to be solved at present.
Disclosure of Invention
In view of this, embodiments of the present invention provide an address query method, an address query apparatus, an electronic device, and a computer-readable storage medium, so as to improve an address recall speed and reduce system computing resources.
In a first aspect, an embodiment of the present invention provides an address query method, where the method includes:
acquiring an address query request;
responding to the character string of the address query request to accord with the rule of the category of the door address road, and retrieving in a first database according to the address query request to obtain target positioning information, wherein the first database comprises door address road information and corresponding positioning information;
responding to the fact that the character string of the address query request does not accord with the rule of the category of the portal road, inputting the address query request into a pre-trained classification model for classification, and determining the category of the address query request;
and responding to the type of the address query request as a type of the portal road, and retrieving in a first database according to the address query request to acquire target positioning information.
Optionally, the method further includes:
and responding to the fact that the category of the address query request is a non-portal road category, and retrieving in a second database according to the address query request to obtain target positioning information, wherein the second database comprises keywords and corresponding positioning information.
Optionally, the rule of the category of the address road is determined according to the following steps:
obtaining a historical click log, wherein the historical click log comprises character strings of the types of the address roads clicked by the user in history;
determining the clicking frequency of the character strings of the road category of each address in the historical clicking log;
and determining the rule of the category of the address road according to the character string of the predetermined address road category with the highest click frequency.
Optionally, the classification model is trained according to the following steps:
acquiring sample data, wherein the sample data comprises a portal road category character string and a non-portal road category character string, and the sample data has category marking information;
inputting the sample data into the classification model for processing;
and adjusting parameters of the classification model according to the output of the classification model so as to train the classification model.
In a second aspect, an embodiment of the present invention provides an address query apparatus, where the apparatus includes:
a request acquisition unit configured to acquire an address query request;
the first retrieval unit is configured to respond to the fact that the character string of the address query request accords with the rule of the category of the portal road, and retrieve in a first database according to the address query request to obtain target positioning information, wherein the first database comprises portal road information and corresponding positioning information;
the category determination unit is configured to respond to the fact that the character string of the address query request does not accord with the rule of the category of the portal road, input the address query request into a pre-trained classification model for classification, and determine the category of the address query request;
and the second retrieval unit is configured to respond to the fact that the category of the address query request is the category of the gateway address road, and retrieve in the first database according to the address query request to obtain the target positioning information.
Optionally, the apparatus further comprises:
and the third retrieval unit is configured to respond to the fact that the category of the address query request is the non-portal road category, and retrieve in a second database according to the address query request to obtain target positioning information, wherein the second database comprises key words and corresponding positioning information.
Optionally, the apparatus further includes a rule determining unit, where the rule determining unit includes:
the system comprises a click log obtaining subunit, a click log obtaining subunit and a click log processing subunit, wherein the click log obtaining subunit is configured to obtain a historical click log which comprises character strings of the types of the portal roads clicked by the user in history;
the click frequency acquisition subunit is configured to determine click frequencies of character strings of various types of the address roads in the historical click logs;
and the rule determining subunit is configured to determine the rule of the address road category according to the character strings of the predetermined address road categories with the highest click frequency.
Optionally, the apparatus further includes a training unit, and the training unit includes:
the system comprises a sample acquisition subunit, a data acquisition unit and a data processing unit, wherein the sample acquisition subunit is configured to acquire sample data, the sample data comprises a portal road category character string and a non-portal road category character string, and the sample data has category marking information;
a processing subunit configured to input the sample data to the classification model for processing;
a training subunit configured to adjust parameters of the classification model according to an output of the classification model to train the classification model.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory is used to store one or more computer program instructions, where the one or more computer program instructions are executed by the processor to implement the method described above.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method as described above.
The embodiment of the invention searches in the first database according to the address query request to obtain the target positioning information when the character string of the address query request conforms to the rule of the category of the door address road, determines the category of the address query request through the classification model when the character string of the address query request does not conform to the category of the door address road, and searches in the first database according to the address query request to obtain the target positioning information when the category of the address query request is the category of the door address road, wherein the first database comprises the door address road information and the corresponding positioning information. Reducing system computing resources.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of an address query method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another address lookup method of an embodiment of the present invention;
FIG. 3 is a diagram illustrating an address recall in accordance with an embodiment of the present invention;
FIG. 4 is a diagram illustrating another address recall according to an embodiment of the present invention;
FIG. 5 is a diagram of an address lookup apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an electronic device of an embodiment of the invention.
Detailed Description
The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present invention.
Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.
Unless the context clearly requires otherwise, throughout the description, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
A common way to retrieve is to receive a keyword, such as a POI name, etc., input by a user to recall address information. In the field of address query, address information recall refers to retrieving according to keywords input by a user in query, acquiring corresponding address information, and returning or displaying the corresponding address information on a terminal equipment interface. The POI refers to a specific point of interest on the map, for example xx school, xx market and the like are all a POI location. However, some users may directly input a road number or a zip code to retrieve a specific location on a map, such as xx street xx, due to different habits. At present, no matter the keyword, the road number or the postal code input by the user is recalled at a specific position required by the user in the same recall mode, so that the retrieval speed is low, and system computing resources are wasted.
Fig. 1 is a flowchart of an address query method according to an embodiment of the present invention. As shown in fig. 1, the address query method according to the embodiment of the present invention includes the following steps:
step S110, an address query request is obtained. The address query request comprises key words, road doorplate information or postal codes and the like. Such as xx schools, xx Luxx numbers, etc.
Step S120, responding to the character string of the address query request meeting the rule of the category of the door address road, and retrieving in a first database according to the address query request to obtain target positioning information, wherein the first database comprises door address road information and corresponding positioning information. The target positioning information comprises longitude and latitude information of a POI address corresponding to the address query request. In this embodiment, the search vocabulary of the road category of the portal address has a certain rule, for example, the search vocabulary starts with a road category word and ends with a number, or includes a road category word and a number. In this embodiment, the first database includes the portal road information and the corresponding positioning information, for example, the corresponding relationship between the portal road information and the longitude and latitude of each POI address, so that when the address query request is the portal road category, the first database can be retrieved according to the address query request to obtain the longitude and latitude of the POI address corresponding to the address query request.
In an alternative implementation, the rule of the portal road category is determined according to the following steps:
a1, obtaining a historical click log, wherein the historical click log comprises character strings of the address road category of the historical click of the user. In the embodiment, in the address recall related log, when the user recalls the address by using the vocabulary of the portal road category, the adopted log is clicked.
A2, determining the click frequency of the character string of each address road category in the historical click log. It is easy to understand that in the historical click log, the more frequently clicked, the more consistent the character string of the portal road category is with the query habit of the user.
A3, determining the rule of the category of the address road according to the character strings of the predetermined types of the address road with the highest click frequency. Optionally, the character strings of the respective types of the address roads are sorted according to the click frequency, the character strings of the first N (N is greater than or equal to 1) types of the address roads are obtained, and the rule of the type of the address road is determined according to the composition mode of the character strings of the N types of the address roads. For example, if the character string of the portal road category with the highest click frequency is composed: in the form of road category keyword + number, the rule for determining the category of the address road is as follows: and if the acquired character string of the address query request conforms to the rule of 'road category keyword + number', the category of the address query request can be determined to be the category of the portal road. The road category keywords may be "road", "street", "lane", and the like.
Therefore, according to the embodiment, the historical click log is obtained to screen the character strings of the address road category of the required address, and the rule of the address road category is determined according to the character strings of the plurality of address road categories with high click frequency, so that the rule of the address road category can better accord with the query habit of the user, and further the retrieval efficiency can be improved.
Step S130, in response to the fact that the character string of the address query request does not accord with the rule of the category of the portal road, the address query request is input into a pre-trained classification model for classification so as to determine the category of the address query request. In an actual application scenario, when a user searches for an address, the adopted search keywords are various, and the predetermined rule of the category of the address road cannot cover the search keywords of all the categories of the address road, so that when the character string of the address query request does not conform to the rule of the category of the address road, the embodiment further determines the category of the address query request by adopting a pre-trained classification model, and therefore the embodiment can more accurately retrieve in the corresponding database according to the category of the address query request, and further improves the query efficiency.
In an alternative implementation, the classification model is trained according to the following steps:
and B1, acquiring sample data, wherein the sample data comprises a portal road category character string and a non-portal road category character string, and the sample data has category marking information.
And B2, inputting the sample data into the classification model for processing.
B3, adjusting the parameters of the classification model according to the output of the classification model to train the classification model.
Therefore, the classification model is trained according to the sample data with the class marking information, and the class of the address query request can be accurately determined.
Step S140, in response to the type of the address query request being the type of the address road, retrieving in the first database according to the address query request to obtain the target positioning information.
In an optional implementation manner, the address query method of this embodiment further includes: and responding to the fact that the category of the address query request is a non-portal road category, and retrieving in a second database according to the address query request to obtain target positioning information, wherein the second database comprises keywords and corresponding positioning information. The address query request of the non-portal road category comprises key word query of POI names and the like.
The method comprises the steps of searching in a first database according to an address query request to obtain target positioning information when a character string of the address query request conforms to a rule of a door address road category, determining the category of the address query request through a classification model when the character string of the address query request does not conform to the door address road category, searching in the first database according to the address query request to obtain target positioning information when the category of the address query request is the door address road category, wherein the first database comprises the door address road information and corresponding positioning information, firstly preliminarily determining the category of the address query request according to the rule of the door address road category, if the category cannot be determined, determining by adopting a classification model, searching in a corresponding database according to the category of the address query request to obtain the target positioning information, therefore, the address recall speed can be improved, and the system computing resources can be reduced.
Fig. 2 is a flowchart of another address query method according to an embodiment of the present invention. As shown in fig. 2, the address query method according to the embodiment of the present invention includes the following steps:
step S210, an address query request is obtained. The address query request comprises key words, road doorplate information or postal codes and the like. Such as xx schools, xx Luxx numbers, etc.
Step S220, determining whether the character string of the address query request conforms to the rule of the category of the address road, if so, performing step S250, and if not, performing step S230. In this embodiment, the search vocabulary of the road category of the portal address has a certain rule, for example, the search vocabulary starts with a road category word and ends with a number, or includes a road category word and a number. The method for determining the rule of the address road category is as described above, and this embodiment is not described again.
In step S230, if the character string of the address query request does not conform to the rule of the category of the address road, the address query request is input to the classification model for processing, so as to determine the category of the address query request. In an actual application scenario, when a user searches for an address, the adopted search keywords are various, and the predetermined rule of the category of the address road cannot cover the search keywords of all the categories of the address road, so that when the character string of the address query request does not conform to the rule of the category of the address road, the embodiment further determines the category of the address query request by adopting a pre-trained classification model, and therefore the embodiment can more accurately retrieve in the corresponding database according to the category of the address query request, and further improves the query efficiency.
Step S240, determining whether the category of the address query request is the category of the address road according to the output result of the classification model. If yes, go to step S250, otherwise go to step S260.
Step S250, retrieving in a first database according to the address query request to obtain the target location information, where the first database includes the address road information and the corresponding location information. The target positioning information comprises longitude and latitude information of a POI address corresponding to the address query request. In this embodiment, the first database includes the portal road information and the corresponding positioning information, for example, the corresponding relationship between the portal road information and the longitude and latitude of each POI address, so that when the address query request is the portal road category, the first database can be retrieved according to the address query request to obtain the longitude and latitude of the POI address corresponding to the address query request.
Step S260, when the type of the address query request is the non-portal road type, retrieving in a second database according to the address query request to obtain the target positioning information, where the second database includes the keyword and the corresponding positioning information. The address query request of the non-portal road category comprises key word query of POI names and the like.
The method comprises the steps of searching in a first database according to an address query request to obtain target positioning information when a character string of the address query request conforms to a rule of a door address road category, determining the category of the address query request through a classification model when the character string of the address query request does not conform to the door address road category, searching in the first database according to the address query request to obtain target positioning information when the category of the address query request is the door address road category, wherein the first database comprises the door address road information and corresponding positioning information, firstly preliminarily determining the category of the address query request according to the rule of the door address road category, if the category cannot be determined, determining by adopting a classification model, searching in a corresponding database according to the category of the address query request to obtain the target positioning information, therefore, the address recall speed can be improved, and the system computing resources can be reduced.
FIG. 3 is a diagram illustrating an address recall according to an embodiment of the present invention. In this embodiment, the rule of the address road category is taken as "road category keyword (road, street, etc.) + number". As shown in fig. 3, if the character string input by the user in the address query box is "xxx to 17", it is first determined whether the character string "xxx to 17" is in the category of the address road according to the rule of the address road, and if the road category keyword includes "to", it is determined that the character string "xxx to 17" conforms to the category of the address road, and the search is performed in the first database according to the character string "xxx to 17" to recall the corresponding target positioning information. Assuming that the road category keyword does not include "do", the category of the character string "xxx to 17" cannot be determined according to the road rule of the door address, and the character string "xxx to 17" is input to a pre-trained classification model for classification so as to determine the category of the character string "xxx to 17". And if the character string 'xxx plus 17' is determined to be the type of the door address road according to the classification model, searching in a first database according to the character string 'xxx plus 17' so as to recall the corresponding target positioning information. As shown in fig. 3, if the character string input in the address query box at the location O by the user is "xxx to 17", to perform the address query, after the above steps S210-S260 are performed, the corresponding target location information "xx university east gate/xxx to 17" is recalled and displayed on the terminal interface of the user.
FIG. 4 is a diagram illustrating another address recall in accordance with an embodiment of the present invention. As shown in fig. 4, if the character string input by the user in the address query box is "xx university east gate", it is preferred to determine whether the character string "xx university east gate" is a gate address road category according to a gate address road rule, and it is assumed that the predetermined rule of the gate address road category is: road category keywords (road, street, etc.) + number, the category of the character string "xx university east gate" cannot be determined according to the gate address road rule, and the character string "xx university east gate" is input to a classification model trained in advance to be classified, so that the category of the character string "xx university east gate" is determined. If it is determined that the character string "xx university east gate" is not the gate address road category according to the classification model, retrieving the corresponding target location information in the second database according to the character string "xx university east gate" to recall the corresponding target location information, as shown in fig. 4, if the character string input in the address query box at the location O by the user is "xx university east gate" for address query, after the above steps S210-S260 are performed, recalling the corresponding target location information "xx university east gate" to be displayed on the terminal interface of the user.
It should be understood that fig. 3 and fig. 4 are only exemplary diagrams of the present embodiment, and the present embodiment does not limit the display manner and the interface after the address recall.
Therefore, the embodiment can meet the retrieval requirements of various users, improves the user experience, and queries different databases according to different types of retrieval words so as to perform targeted retrieval according to the characteristics of various types of retrieval words, thereby improving the retrieval efficiency and reducing the system computing resources.
Fig. 5 is a schematic diagram of an address query apparatus according to an embodiment of the present invention. As shown in fig. 5, the address querying device 5 of the present embodiment includes a request acquisition unit 51, a first retrieval unit 52, a category determination unit 53, and a second retrieval unit 54.
The request acquisition unit 51 is configured to acquire an address query request. The first retrieving unit 52 is configured to, in response to that the character string of the address query request conforms to the rule of the category of the portal road, retrieve in a first database according to the address query request to obtain the target location information, where the first database includes the portal road information and the corresponding location information. The category determination unit 53 is configured to, in response to the character string of the address query request not matching the portal road category, input the address query request into a classification model trained in advance for classification to determine the category of the address query request. The second retrieving unit 54 is configured to, in response to the category of the address query request being the category of the portal road, retrieve in the first database according to the address query request to obtain the target location information.
In an alternative implementation manner, the address query device 5 of the present embodiment further includes a third retrieval unit 55. The third retrieving unit 55 is configured to, in response to the category of the address query request being a non-portal road category, retrieve in a second database according to the address query request to obtain target positioning information, wherein the second database includes a keyword and corresponding positioning information.
In an optional implementation manner, the address query device 5 of the present embodiment further includes a rule determination unit 56. The rule determining unit 56 includes a click log obtaining subunit 561, a click frequency obtaining subunit 562, and a rule determining subunit 563. Wherein the click log obtaining subunit 561 is configured to obtain a history click log including a character string of the portal road category of the user's history click. The click frequency acquiring sub-unit 562 is configured to determine the click frequency of the character string of each address road category in the history click log. The rule determination subunit 563 is configured to determine the rule of the portal road class from the character strings of the predetermined portal road classes with the highest click frequency.
In an optional implementation manner, the address querying device 5 of the present embodiment further includes a training unit 57, where the training unit 57 includes a sample obtaining sub-unit 571, a processing sub-unit 572, and a training sub-unit 573. The sample acquiring subunit 571 is configured to acquire sample data, where the sample data includes the portal road category character string and the non-portal road category character string, and the sample data has category label information. The processing sub-unit 572 is configured to input the sample data to the classification model for processing. The training subunit 573 is configured to adjust parameters of the classification model according to the output of the classification model to train the classification model.
The embodiment of the invention searches in the first database according to the address query request to obtain the target positioning information when the character string of the address query request conforms to the rule of the category of the door address road, determines the category of the address query request through the classification model when the character string of the address query request does not conform to the category of the door address road, and searches in the first database according to the address query request to obtain the target positioning information when the category of the address query request is the category of the door address road, wherein the first database comprises the door address road information and the corresponding positioning information. Reducing system computing resources.
Fig. 6 is a schematic diagram of an electronic device of an embodiment of the invention. As shown in fig. 6, the electronic device shown in fig. 6 is a general address query device, which includes a general computer hardware structure, which includes at least a processor 61 and a memory 62. The processor 61 and the memory 62 are connected by a bus 63. The memory 62 is adapted to store instructions or programs executable by the processor 61. The processor 61 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 61 implements the processing of data and the control of other devices by executing instructions stored by the memory 62 to perform the method flows of embodiments of the present invention as described above. The bus 63 connects the above components together, and also connects the above components to a display controller 64 and a display device and an input/output (I/O) device 65. Input/output (I/O) devices 65 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, the input/output device 65 is connected to the system through an input/output (I/O) controller 66.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus (device) or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may employ a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations of methods, apparatus (devices) and computer program products according to embodiments of the application. It will be understood that each flow in the flow diagrams can be implemented by computer program instructions.
These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows.
These computer program instructions may also be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows.
Another embodiment of the invention is directed to a non-transitory storage medium storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An address query method, the method comprising:
acquiring an address query request;
responding to the character string of the address query request to accord with the rule of the category of the door address road, and retrieving in a first database according to the address query request to obtain target positioning information, wherein the first database comprises door address road information and corresponding positioning information;
responding to the fact that the character string of the address query request does not accord with the rule of the category of the portal road, inputting the address query request into a pre-trained classification model for classification, and determining the category of the address query request;
and responding to the type of the address query request as a type of the portal road, and retrieving in a first database according to the address query request to acquire target positioning information.
2. The method of claim 1, further comprising:
and responding to the fact that the category of the address query request is a non-portal road category, and retrieving in a second database according to the address query request to obtain target positioning information, wherein the second database comprises keywords and corresponding positioning information.
3. The method of claim 1, wherein the rules for the category of portal road are determined according to the following steps:
obtaining a historical click log, wherein the historical click log comprises character strings of the types of the address roads clicked by the user in history;
determining the clicking frequency of the character strings of the road category of each address in the historical clicking log;
and determining the rule of the category of the address road according to the character string of the predetermined address road category with the highest click frequency.
4. The method of claim 1, wherein the classification model is trained according to the following steps:
acquiring sample data, wherein the sample data comprises a portal road category character string and a non-portal road category character string, and the sample data has category marking information;
inputting the sample data into the classification model for processing;
and adjusting parameters of the classification model according to the output of the classification model so as to train the classification model.
5. An address lookup apparatus, comprising:
a request acquisition unit configured to acquire an address query request;
the first retrieval unit is configured to respond to the fact that the character string of the address query request accords with the rule of the category of the portal road, and retrieve in a first database according to the address query request to obtain target positioning information, wherein the first database comprises portal road information and corresponding positioning information;
the category determination unit is configured to respond to the fact that the character string of the address query request does not accord with the rule of the category of the portal road, input the address query request into a pre-trained classification model for classification, and determine the category of the address query request;
and the second retrieval unit is configured to respond to the fact that the category of the address query request is the category of the gateway address road, and retrieve in the first database according to the address query request to obtain the target positioning information.
6. The apparatus of claim 5, further comprising:
and the third retrieval unit is configured to respond to the fact that the category of the address query request is the non-portal road category, and retrieve in a second database according to the address query request to obtain target positioning information, wherein the second database comprises key words and corresponding positioning information.
7. The apparatus of claim 5, further comprising a rule determination unit, the rule determination unit comprising:
the system comprises a click log obtaining subunit, a click log obtaining subunit and a click log processing subunit, wherein the click log obtaining subunit is configured to obtain a historical click log which comprises character strings of the types of the portal roads clicked by the user in history;
the click frequency acquisition subunit is configured to determine click frequencies of character strings of various types of the address roads in the historical click logs;
and the rule determining subunit is configured to determine the rule of the address road category according to the character strings of the predetermined address road categories with the highest click frequency.
8. The apparatus of claim 5, further comprising a training unit, the training unit comprising:
the system comprises a sample acquisition subunit, a data acquisition unit and a data processing unit, wherein the sample acquisition subunit is configured to acquire sample data, the sample data comprises a portal road category character string and a non-portal road category character string, and the sample data has category marking information;
a processing subunit configured to input the sample data to the classification model for processing;
a training subunit configured to adjust parameters of the classification model according to an output of the classification model to train the classification model.
9. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-4.
10. A computer-readable storage medium on which computer program instructions are stored, which computer program instructions, when executed by a processor, are to implement the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010255863.9A CN111831867A (en) | 2020-04-02 | 2020-04-02 | Address query method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010255863.9A CN111831867A (en) | 2020-04-02 | 2020-04-02 | Address query method and device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111831867A true CN111831867A (en) | 2020-10-27 |
Family
ID=72913564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010255863.9A Pending CN111831867A (en) | 2020-04-02 | 2020-04-02 | Address query method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111831867A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115017425A (en) * | 2022-07-19 | 2022-09-06 | 深圳依时货拉拉科技有限公司 | Location search method, location search device, electronic device, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070016556A1 (en) * | 2005-07-13 | 2007-01-18 | Ann Seong W | Destination searching system and method |
| CN203204618U (en) * | 2013-03-02 | 2013-09-18 | 成都精彩宏途科技信息有限公司 | Police standard address database system based on collecting and processing of mobile intelligent terminal |
| CN103744854A (en) * | 2013-11-15 | 2014-04-23 | 北京正图数创信息技术有限公司 | Address data matching mining platform based on big data storage and mining technology |
| US20140324852A1 (en) * | 2013-04-30 | 2014-10-30 | Wal-Mart Stores, Inc. | Classifying Queries To Generate Category Mappings |
| CN107958406A (en) * | 2017-11-30 | 2018-04-24 | 北京小度信息科技有限公司 | Inquire about acquisition methods, device and the terminal of data |
-
2020
- 2020-04-02 CN CN202010255863.9A patent/CN111831867A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070016556A1 (en) * | 2005-07-13 | 2007-01-18 | Ann Seong W | Destination searching system and method |
| CN203204618U (en) * | 2013-03-02 | 2013-09-18 | 成都精彩宏途科技信息有限公司 | Police standard address database system based on collecting and processing of mobile intelligent terminal |
| US20140324852A1 (en) * | 2013-04-30 | 2014-10-30 | Wal-Mart Stores, Inc. | Classifying Queries To Generate Category Mappings |
| CN103744854A (en) * | 2013-11-15 | 2014-04-23 | 北京正图数创信息技术有限公司 | Address data matching mining platform based on big data storage and mining technology |
| CN107958406A (en) * | 2017-11-30 | 2018-04-24 | 北京小度信息科技有限公司 | Inquire about acquisition methods, device and the terminal of data |
Non-Patent Citations (2)
| Title |
|---|
| 于焕菊;齐清文;李云岭;: "街道的城市地址编码模型与实验", 地球信息科学学报, no. 02 * |
| 林筝;: "集成全景地图的街道地名服务建设方法", 测绘通报, no. 04 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115017425A (en) * | 2022-07-19 | 2022-09-06 | 深圳依时货拉拉科技有限公司 | Location search method, location search device, electronic device, and storage medium |
| CN115017425B (en) * | 2022-07-19 | 2022-11-04 | 深圳依时货拉拉科技有限公司 | Location search method, location search device, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4850845B2 (en) | Method, system and memory device | |
| KR100814667B1 (en) | Systems and methods for clustering search results | |
| Bennett et al. | Inferring and using location metadata to personalize web search | |
| WO2017024884A1 (en) | Search intention identification method and device | |
| US9164987B2 (en) | Translating a search query into multiple languages | |
| JP4633803B2 (en) | Ambiguous geographic reference classification | |
| US8380693B1 (en) | System and method for automatically identifying classified websites | |
| US20110173177A1 (en) | Sightful cache: efficient invalidation for search engine caching | |
| CN109032381B (en) | Input method and device based on context, storage medium and terminal | |
| US8510262B2 (en) | Promoting websites based on location | |
| JP6053131B2 (en) | Information processing apparatus, information processing method, and program | |
| CN109948154B (en) | Character acquisition and relationship recommendation system and method based on mailbox names | |
| CN111831867A (en) | Address query method and device, electronic equipment and computer readable storage medium | |
| CN111177585A (en) | Map POI feedback method and device | |
| JP2016038667A (en) | Information provision device, information provision method and information provision program | |
| CN111723296B (en) | Search processing method and device and computer equipment | |
| KR101120040B1 (en) | Apparatus for recommending related query and method thereof | |
| WO2008129339A1 (en) | Method for location identification in web pages and location-based ranking of internet search results | |
| CN107423298B (en) | Searching method and device | |
| CN107784061B (en) | Method and system for determining image-based content style and machine-readable medium | |
| JP5559725B2 (en) | Information retrieval service providing method using web page divided into a plurality of information blocks | |
| JP4778284B2 (en) | Local search system and local search processing method | |
| JP4778285B2 (en) | Map center point suitability information generation system and map center point suitability information generation method | |
| CN108733848A (en) | A kind of method and system of search knowledge | |
| JPH1139327A (en) | Method and device for automatically restoring link information |
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 |