Method and apparatus for obtaining abbreviated name of point of interest on map
A plurality of abbreviated names are generated for evaluation based on a full name of a point-of-interest (POI) on a map. A plurality of address names comprising the full name of the POI or any of the abbreviated names to be evaluated are obtained from a predetermined area of the POI. A phrase status vector used to indicate a location status of the target phrase in each particular address name is calculated for a target phrase based on each address name, the target phrase including the full name of the POI or any of the abbreviated names to be evaluated. A similarity is calculated between a phrase status vector for the full name of the POI and a phrase status vector. A particular abbreviated name corresponding with a calculated similarity greater than a predetermined threshold is associated with the full name of the POI corresponding to the calculated similarity.
1. A computer-implemented method, comprising:
generating, for evaluation, a plurality of abbreviated names based on a full name of a point-of-interest (POI) on a map;
obtaining, from a predetermined area of the POI, a plurality of address names comprising the full name of the POI or any of the abbreviated names to be evaluated;
calculating a phrase status vector for a target phrase based on each address name of the plurality of address names, wherein the phrase status vector is used to indicate a location status of the target phrase in each particular address name, and the target phrase includes the full name of the POI or any of the abbreviated names to be evaluated;
calculating a similarity between a phrase status vector for the full name of the POI and a phrase status vector for any of the abbreviated names to be evaluated; and
associating a particular abbreviated name that corresponds with a calculated similarity greater than a predetermined threshold with the full name of the POI corresponding to the calculated similarity.
2. The computer-implemented method of claim 1 , wherein the generation comprises combining single words forming the full name of the POI into a plurality of arrangement sequences, wherein each particular arrangement sequence is an abbreviated name.
3. The computer-implemented method of claim 2 , further comprising removing, from the plurality of arrangement sequences, a single word and a noise phrase determined as an abbreviated name of a non-POI, wherein a remaining abbreviated name is the to-be-evaluated abbreviated name.
4. The computer-implemented method of claim 1 , wherein the calculation of the phrase status vector comprises obtaining a neighboring phrase of the target phrase from any of the plurality of address names.
5. The computer-implemented method of claim 4 , further comprising using a frequency that each neighboring phrase appears in the plurality of address names as a dimensional value for a vector dimension of the phrase status vector.
6. The computer-implemented method of claim 1 , wherein the calculation of the similarity is a cosine similarity calculation.
7. The computer-implemented method of claim 1 , wherein there is at least one to-be-evaluated abbreviated name corresponding to the calculated similarity greater than the predetermined threshold.
8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
generating, for evaluation, a plurality of abbreviated names based on a full name of a point-of-interest (POI) on a map;
obtaining, from a predetermined area of the POI, a plurality of address names comprising the full name of the POI or any of the abbreviated names to be evaluated;
calculating a phrase status vector for a target phrase based on each address name of the plurality of address names, wherein the phrase status vector is used to indicate a location status of the target phrase in each particular address name, and the target phrase includes the full name of the POI or any of the abbreviated names to be evaluated;
calculating a similarity between a phrase status vector for the full name of the POI and a phrase status vector for any of the abbreviated names to be evaluated; and
associating a particular abbreviated name that corresponds with a calculated similarity greater than a predetermined threshold with the full name of the POI corresponding to the calculated similarity.
9. The non-transitory, computer-readable medium of claim 8 , wherein the generation comprises one or more instructions to combine single words forming the full name of the POI into a plurality of arrangement sequences, wherein each particular arrangement sequence is an abbreviated name.
10. The non-transitory, computer-readable medium of claim 9 , further comprising one or more instructions to remove, from the plurality of arrangement sequences, a single word and a noise phrase determined as an abbreviated name of a non-POI, wherein a remaining abbreviated name is the to-be-evaluated abbreviated name.
11. The non-transitory, computer-readable medium of claim 8 , wherein the calculation of the phrase status vector comprises obtaining a neighboring phrase of the target phrase from any of the plurality of address names.
12. The non-transitory, computer-readable medium of claim 11 , further comprising one or more instructions to use a frequency that each neighboring phrase appears in the plurality of address names as a dimensional value for a vector dimension of the phrase status vector.
13. The non-transitory, computer-readable medium of claim 8 , wherein the calculation of the similarity is a cosine similarity calculation.
14. The non-transitory, computer-readable medium of claim 8 , wherein there is at least one to-be-evaluated abbreviated name corresponding to the calculated similarity greater than the predetermined threshold.
15. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
generating, for evaluation, a plurality of abbreviated names based on a full name of a point-of-interest (POI) on a map;
obtaining, from a predetermined area of the POI, a plurality of address names comprising the full name of the POI or any of the abbreviated names to be evaluated;
calculating a phrase status vector for a target phrase based on each address name of the plurality of address names, wherein the phrase status vector is used to indicate a location status of the target phrase in each particular address name, and the target phrase includes the full name of the POI or any of the abbreviated names to be evaluated;
calculating a similarity between a phrase status vector for the full name of the POI and a phrase status vector for any of the abbreviated names to be evaluated; and
associating a particular abbreviated name that corresponds with a calculated similarity greater than a predetermined threshold with the full name of the POI corresponding to the calculated similarity.
16. The computer-implemented system of claim 15 , wherein the generation comprises combining single words forming the full name of the POI into a plurality of arrangement sequences, wherein each particular arrangement sequence is an abbreviated name.
17. The computer-implemented system of claim 16 , further comprising one or more operations to remove, from the plurality of arrangement sequences, a single word and a noise phrase determined as an abbreviated name of a non-POI, wherein a remaining abbreviated name is the to-be-evaluated abbreviated name.
18. The computer-implemented system of claim 15 , wherein the calculation of the phrase status vector comprises one or more operations to:
obtain a neighboring phrase of the target phrase from any of the plurality of address names; and
use a frequency that each neighboring phrase appears in the plurality of address names as a dimensional value for a vector dimension of the phrase status vector.
19. The computer-implemented system of claim 15 , wherein the calculation of the similarity is a cosine similarity calculation.
20. The computer-implemented system of claim 15 , wherein there is at least one to-be-evaluated abbreviated name corresponding to the calculated similarity greater than the predetermined threshold.