Disclosure of Invention
The present disclosure is directed to an address recognition method and an address recognition device, which are used to overcome the problem of low delivery efficiency caused by irregular delivery address filling by a user at least to a certain extent.
According to a first aspect of an embodiment of the present disclosure, there is provided an address identifying method, including: searching a matching address corresponding to the user-defined address of the distribution task in an address database; if the matching address is not found, acquiring a location positioning coordinate when the distribution task is finished through a distribution terminal; and determining a standard address corresponding to the user-defined address according to the location positioning coordinates.
In an exemplary embodiment of the present disclosure, the searching the address database for the matching address corresponding to the user-defined address of the distribution task includes:
Searching a full text matching result of the user-defined address in the address database;
if the full text matching result is not found, searching a fuzzy matching result of the user-defined address;
and taking the full text matching result or the fuzzy matching result as the matching address.
In an exemplary embodiment of the present disclosure, the searching the fuzzy matching result of the user-defined address includes:
determining a plurality of fuzzy related words such as homonyms, word segmentation results, preset correction words and the like of the user-defined address;
and searching matching results of the fuzzy related words in the address database.
In an exemplary embodiment of the disclosure, the determining, according to the location positioning coordinates, a standard address corresponding to the user-defined address includes:
Acquiring a plurality of standard addresses in a preset range around the location positioning coordinates;
searching a first matching result of the user-defined address in the plurality of standard addresses;
if the first matching result is found, recording the first matching result in the address database as a standard address;
If the first matching result is not found, extracting keywords of the user-defined address;
searching a second matching result in the standard addresses according to the keywords;
And if the second matching result is found, recording the second matching result in the address database as a standard address of the user-defined address.
In an exemplary embodiment of the disclosure, the extracting the keyword of the user-defined address includes:
Searching a preset scene word in the user-defined address;
determining a combined word of the preset scene word and the modifier word in front of the preset scene word, and searching a third matching result of the combined word in the standard addresses;
And taking the third matching result as the user-defined address.
In an exemplary embodiment of the present disclosure, further comprising:
and recording the corresponding relation among the user-defined address, the standard address and the positioning coordinate of the standard address in the address database.
In an exemplary embodiment of the present disclosure, further comprising:
and if the matching address is found, sending the positioning coordinates of the matching address to the distribution personnel.
According to a second aspect of the embodiments of the present disclosure, there is provided an address identifying apparatus, including:
The address matching module is used for searching a matching address corresponding to the user-defined address of the distribution task in the address database;
the positioning acquisition module is used for acquiring the location positioning coordinates when the distribution task is finished through the distribution terminal if the matching address is not found;
And the address searching module is used for determining a standard address corresponding to the user-defined address according to the location positioning coordinates.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a memory; and a processor coupled to the memory, the processor configured to perform the method of any of the above based on instructions stored in the memory.
According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the address identifying method as set forth in any one of the above.
According to the embodiment of the disclosure, after the non-standard delivery address is received, the address is automatically learned according to the location coordinate information of the first time of the delivery personnel, normalized and mapped to the GPS coordinate and recorded in the address database, so that the similar non-standard address can be correctly resolved when appearing again, the recognition accuracy and recognition efficiency of the non-standard address are improved, and the problem of low delivery efficiency caused by the fact that the address is not standard and the delivery personnel walk by mistake is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are only schematic illustrations of the present disclosure, in which the same reference numerals denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
The following describes example embodiments of the present disclosure in detail with reference to the accompanying drawings.
Fig. 1 schematically illustrates a flowchart of an address recognition method in an exemplary embodiment of the present disclosure. Referring to fig. 1, the address recognition method 100 may include:
step S1, searching a matching address corresponding to a user-defined address of a distribution task in an address database;
Step S2, if the matching address is not found, acquiring the location positioning coordinate of the distribution task through a distribution terminal;
And step S3, determining a standard address corresponding to the user-defined address according to the location positioning coordinates.
According to the embodiment of the disclosure, after the nonstandard distribution is received, the address is automatically learned according to the location coordinate information of the first time of the distribution personnel, normalized and mapped to the GPS coordinate and recorded in the address database, so that the similar nonstandard address can be correctly analyzed when appearing again, the recognition accuracy and recognition efficiency of the nonstandard address are improved, and the problem of low distribution efficiency caused by the fact that the address is nonstandard and the distribution personnel walk by mistake is solved.
Next, each step of the address identifying method 100 will be described in detail.
In step S1, a matching address corresponding to the user-defined address of the delivery task is searched in an address database.
The delivery platform may use the address entered manually by the user instead of selected as the user-defined address.
Fig. 2 is a sub-flowchart of step S1.
Referring to fig. 2, in an exemplary embodiment of the present disclosure, step S1 may include:
Step S11, searching the full text matching result of the user-defined address in the address database;
step S12, if the full text matching result is not found, searching a fuzzy matching result of the user-defined address;
And S13, taking the full-text matching result or the fuzzy matching result as the matching address.
In the disclosed embodiments, an address database may be maintained for recording correspondence between non-standard addresses and standard addresses. When the user-defined address is identified, the full-text matching result existing in the address database can be searched first. The full-text matching result may be full-text matching of a non-standard address (for example, the address database already records the corresponding relation between the address and the standard address), or full-text matching of a standard address (for example, the address filled by the user accords with the standard of the standard address or mostly accords with the standard of the standard address). For example, the non-standard address may be opposite to the XX bank XX branch, if the correspondence between the non-standard address and the standard address is recorded in the address database, when the user-defined address is opposite to the XX bank XX branch, the full text matching result of the non-standard address may be found in the address database as the matching address of the user-defined address.
When the full text matching result cannot be queried, the fuzzy matching result can be further searched. In some embodiments, the fuzzy matching result of the user-defined address may be, for example, a plurality of fuzzy related words such as homonyms, word segmentation results, preset correction words of the user-defined address are determined first, and then the matching results of the fuzzy related words are searched in the address database.
Referring to the relevant fuzzy recognition technology, homonym results of the user-defined address can be determined first, for example, "Fucheng" can correspond to "Fucheng ways", "Fucheng" and the like. In confirming homonym results, a specification may be set, such as that homonym requires more strokes than the original word (strokes are more leading to user shorthand) to help refine recognition range. Next, a preset correction vocabulary for the user-defined address, etc. may be determined. For example, the preset correction word "airport" for "airport" may be automatically determined, and so on. The word stock of the preset correction word can be externally introduced, and can be gradually enriched according to the analysis of the address recognition result. In addition, the user-defined address can be segmented, homonym determination, preset correction vocabulary determination and the like are performed on the segmentation result, and further more fuzzy related vocabularies are determined. In the above embodiments, the method for determining homophones, preset correction words or segmentation words may be various, which is not particularly limited in this disclosure.
After the fuzzy related words are determined, the full text matching results of the fuzzy related words can be searched in an address database. If a matching result of fuzzy related words in the user-defined address is found in the process, the matching result is used as the matching result of the user-defined address; if multiple matching results are found, for example, for the word segmentation case, one word segment corresponds to multiple matching results, the matching results may be determined from the full text. For example, if a word has a matching result in both the fuzzy related terms "netherlands" and "henna", but the word appears "zheng", then it may be determined that the matching result corresponding to the previous word is "henna". The above is merely an example, and a person skilled in the art may set a unique determination manner for a plurality of matching results of fuzzy related vocabulary by himself.
Similarly, the fuzzy matching result can be a non-standard address or a standard address, and after the fuzzy matching result is found, the fuzzy matching result can be used as the matching address of the user-defined address.
In addition, fuzzy matching results may not be found. At this time, the process advances to step S2.
In step S2, if the matching address is not found, the location positioning coordinate at the end of the delivery task is obtained through the delivery terminal.
In the embodiment of the disclosure, the user-defined vocabulary which is not found to be the full-text matching result or the fuzzy matching result can be directly sent to the distribution personnel for manual identification to complete the distribution task. In the process, the completion condition of the delivery task can be tracked, and the location positioning coordinate of the delivery address of the delivery task is determined by clicking the geographic position of the delivery task by the delivery personnel, or the position of the delivery task when the delivery is completed is determined according to the speed characteristic of the positioning track of the delivery personnel (the stop time near one location exceeds a threshold value) and the comprehensive result of the geographic position of the delivery personnel when the delivery task is clicked.
And in step S3, determining a standard address corresponding to the user-defined address according to the location positioning coordinates.
Before determining the standard address, the regular expression can be used for deleting useless character strings from the user-defined address so as to improve the efficiency of address identification.
Fig. 3 is a sub-flowchart of step S3.
Referring to fig. 3, in an exemplary embodiment of the present disclosure, step S3 may include:
step S31, a plurality of standard addresses in a preset range around the location positioning coordinates are obtained;
Step S32, searching a first matching result of the user-defined address in the plurality of standard addresses;
Step S33, if the first matching result is found, recording the first matching result in the address database as a standard address;
step S34, if the first matching result is not found, extracting keywords of the user-defined address;
Step S35, searching a second matching result in the standard addresses according to the keywords;
Step S36, if the second matching result is found, the second matching result is recorded as the standard address of the user-defined address in the address database.
Step S3 may be implemented by invoking local or third party mapping software.
For example, the distribution location may be determined on the map software according to location positioning coordinates, and then a standard address within a preset range around the distribution location may be determined according to a record of the map software, where the preset range may be, for example, a circle centered on the distribution location. After the standard addresses are determined, the first matching result of the user-defined addresses is searched in the standard addresses, and the matching result can be a full-text matching result or a fuzzy matching result.
If the first matching result is found, it indicates that the user-defined address is a standard address, and only because the address database is not recorded, the matching result is not found in step S1. The first matching address can then be recorded as a new standard address in the address database.
If the first matching result is not found, the keywords in the user-defined address can be determined, and the second matching result of the keywords is found.
Fig. 4 is a sub-flowchart of step S34.
Referring to fig. 4, in an exemplary embodiment of the present disclosure, step S34 may include:
step S341, searching a preset scene word in a user-defined address;
step S342, determining a combination word of a preset scene word and a modifier word in front of the preset scene word, and searching a third matching result of the combination word in the plurality of standard addresses;
in step S343, the third matching result is used as the keyword of the user-defined address.
Firstly, whether the user-defined address contains the names of the types of places such as restaurants, meetings, buildings, centers and the like can be checked. If the name is contained, extracting a substring from the name to the previous character, and matching the substring with a standard address queried by map software; if the matching fails, extracting the substring from the previous position from the substring, and matching again until the matching is successful.
In some embodiments, if the user-defined address contains a plurality of location type names, a plurality of keywords may also be determined according to the method described above.
In step S35, after finding the keyword of the user-defined address, the second matching result may be determined in the plurality of standard addresses according to the descriptor before or after the keyword and the location positioning coordinates. For example, if the user-defined address is "opposite to XX building", and the found keyword is "XX building", then a second matching result (for example, "XX number") corresponding to the location positioning coordinate may be determined in the plurality of standard addresses according to the location positioning coordinate, the positional relationship of coordinates of the standard address represented by the keyword, and the direction word "opposite" described by the user, and the second matching result is recorded in the address database as the standard address of the user-defined address.
In some embodiments, the keyword of the user-defined address may not be found, or a second matching result cannot be determined from the keyword and the description in the plurality of standard addresses, where step S3 may include step S37: and submitting the user-defined address to a manual auditing database, and manually identifying and recording the standard address of the user-defined address in the address database.
In an exemplary embodiment of the present disclosure, the method 100 further includes recording in the address database the correspondence of the user-defined address, the standard address, and the location coordinates of the standard address. When the positioning coordinates of the standard address are recorded in the address database, if the matching address is found, the positioning coordinates of the matching address (standard address or non-standard address) can be sent to the distribution personnel. The goods receiving address is automatically converted into GPS coordinates to be provided for couriers, so that the goods delivery navigation and the goods combined delivery can be facilitated, and the delivery efficiency is improved.
According to the embodiment of the disclosure, the address database can be dynamically updated by automatically learning the user-defined address according to the first manual throwing information, so that the maintenance flow of the address database is simplified, and the identification accuracy and the identification efficiency of the user-defined address in the distribution task are improved.
The method 100 is described in detail below with respect to a specific application scenario.
On the e-commerce platform, if the address part is identified as the receiving address manually filled by the user after receiving the user order, the user-defined address can be matched with keywords such as a cell, an office building and the like stored in the address database in advance first:
If the address keyword is matched, directly returning the address keyword (cell name and the like) and corresponding GPS coordinates;
If the address key word is not matched, judging that the user-defined address is a non-standard address, namely a non-standard address for short, and attempting fuzzy matching;
if no matching result is found finally, the order is sent to the courier for the courier to manually identify the judgment destination. The motion track of the delivery task can be acquired, the tuo-put point is calculated according to the track position of the courier at the tuo-put time, and the tuo-put point is used as the real address of the nonstandard address.
Then, the GPS coordinates of the current order casting point are input into the map API, and the returned address character string is obtained. If the returned address character string is the non-standard address, directly matching and storing the non-standard address and the real address character string into an address dictionary; if the returned address character string is not the nonstandard address, inquiring the names of all shops, office buildings and other places in a preset range (for example, 2 km) nearby from the map API, and then matching the keyword extraction result of the nonstandard address character string to finally determine the real address (comprising GPS positioning information) of the place represented by the user-defined address on the map.
And then, deleting useless character strings of the nonstandard addresses by using the regular expression to simplify, and recording the simplified nonstandard addresses in an address database corresponding to GPS coordinates of the true addresses, so as to complete an automatic matching process of the user-defined addresses and a process of adding new addresses to the address database.
The embodiment of the disclosure can automatically correct and match the non-standard address with the standard address in the address library. If the matching is successful, the standard address and GPS coordinates of the distribution task are directly returned to the distribution personnel, so that the navigation is convenient; if the non-standard address cannot be matched with the true position, the destination position learning can be performed by determining the position of the proper delivery by combining the delivery track of the delivery personnel, and the non-standard address is correspondingly recorded in a standard address library. Therefore, when the irregular address or the user-defined address similar to the irregular address is encountered again, the correct address can be quickly matched in the address database, and the time for searching the address of the distribution personnel is saved. Through continuous automatic learning, the address database can be continuously expanded, so that the first address matching rate is continuously improved, and the distribution efficiency is further improved.
Corresponding to the above method embodiments, the present disclosure also provides an address identifying apparatus, which may be used to perform the above method embodiments.
Fig. 5 schematically illustrates a block diagram of an address recognition device in an exemplary embodiment of the present disclosure.
Referring to fig. 5, the address recognition apparatus 500 may include:
The address matching module 502 is configured to search the address database for a matching address corresponding to the user-defined address of the delivery task;
The positioning obtaining module 504 is configured to obtain, by the delivery terminal, the location positioning coordinate when the delivery task ends if the matching address is not found;
The address searching module 506 is configured to determine a standard address corresponding to the user-defined address according to the location positioning coordinate.
In one exemplary embodiment of the present disclosure, the address matching module 502 is configured to:
Searching a full text matching result of the user-defined address in the address database;
if the full text matching result is not found, searching a fuzzy matching result of the user-defined address;
and taking the full text matching result or the fuzzy matching result as the matching address.
In an exemplary embodiment of the present disclosure, the searching the fuzzy matching result of the user-defined address includes:
determining a plurality of fuzzy related words such as homonyms, word segmentation results, preset correction words and the like of the user-defined address;
and searching matching results of the fuzzy related words in the address database.
In one exemplary embodiment of the present disclosure, the address lookup module 506 is configured to:
Acquiring a plurality of standard addresses in a preset range around the location positioning coordinates;
searching a first matching result of the user-defined address in the plurality of standard addresses;
if the first matching result is found, recording the first matching result in the address database as a standard address;
If the first matching result is not found, extracting keywords of the user-defined address;
searching a second matching result in the standard addresses according to the keywords;
And if the second matching result is found, recording the second matching result in the address database as a standard address of the user-defined address.
In an exemplary embodiment of the disclosure, the extracting the keyword of the user-defined address includes:
Searching a preset scene word in the user-defined address;
determining a combined word of the preset scene word and the modifier word in front of the preset scene word, and searching a third matching result of the combined word in the standard addresses;
and taking the third matching result as a keyword of the user-defined address.
In an exemplary embodiment of the present disclosure, further comprising:
The address recording module 508 is configured to record the correspondence between the user-defined address, the standard address, and the location coordinates of the standard address in the address database.
In an exemplary embodiment of the present disclosure, the address matching module 502 is further configured to send the location coordinates of the matching address to the distribution personnel if the matching address is found.
Since the functions of the apparatus 500 are described in detail in the corresponding method embodiments, the disclosure is not repeated herein.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 6. The electronic device 600 shown in fig. 6 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 6, the electronic device 600 is in the form of a general purpose computing device. Components of electronic device 600 may include, but are not limited to: the at least one processing unit 610, the at least one memory unit 620, and a bus 630 that connects the various system components, including the memory unit 620 and the processing unit 610.
Wherein the storage unit stores program code that is executable by the processing unit 610 such that the processing unit 610 performs steps according to various exemplary embodiments of the present invention described in the above-described "exemplary methods" section of the present specification. For example, the processing unit 610 may perform step S1 as shown in fig. 1: searching a matching address corresponding to the user-defined address of the distribution task in an address database; step S2: if the matching address is not found, acquiring a location positioning coordinate when the distribution task is finished through a distribution terminal; step S3: and determining a standard address corresponding to the user-defined address according to the location positioning coordinates.
The storage unit 620 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 6201 and/or cache memory unit 6202, and may further include Read Only Memory (ROM) 6203.