WO2023226448A1 - 物流兴趣点信息生成方法、装置、设备和计算机可读介质 - Google Patents

物流兴趣点信息生成方法、装置、设备和计算机可读介质 Download PDF

Info

Publication number
WO2023226448A1
WO2023226448A1 PCT/CN2023/070934 CN2023070934W WO2023226448A1 WO 2023226448 A1 WO2023226448 A1 WO 2023226448A1 CN 2023070934 W CN2023070934 W CN 2023070934W WO 2023226448 A1 WO2023226448 A1 WO 2023226448A1
Authority
WO
WIPO (PCT)
Prior art keywords
logistics
interest
point
information
text
Prior art date
Application number
PCT/CN2023/070934
Other languages
English (en)
French (fr)
Inventor
李司钤
赫桂望
曹振琴
孙鑫鑫
路俊伟
Original Assignee
北京京东振世信息技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京京东振世信息技术有限公司 filed Critical 北京京东振世信息技术有限公司
Publication of WO2023226448A1 publication Critical patent/WO2023226448A1/zh

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0833—Tracking

Definitions

  • Embodiments of the present disclosure relate to the field of computer technology, and specifically to methods, devices, equipment and computer-readable media for generating logistics point of interest information.
  • Logistics point of interest information refers to the addresses and other related information of places where logistics distribution can be carried out in logistics scenarios (for example, residential buildings, business districts, schools, etc.).
  • logistics scenarios for example, residential buildings, business districts, schools, etc.
  • Some embodiments of the present disclosure provide logistics point of interest information generation methods, devices, equipment and computer-readable media to solve the technical problems mentioned in the background art section above.
  • some embodiments of the present disclosure provide a method for generating logistics point of interest information.
  • the method includes: obtaining logistics point of interest information to be marked, wherein the above-mentioned logistics point of interest information includes logistics point of interest text; according to the logistics characteristics Word information set, identify the logistics feature words included in the above-mentioned logistics point of interest text and the position of the above-mentioned logistics feature word in the above-mentioned logistics point of interest text, and obtain a set of logistics feature word identification information, wherein, in the above-mentioned logistics feature word identification information set, Logistics feature word identification information includes logistics feature words and location information.
  • Logistics feature word information in the above-mentioned logistics feature word information set includes logistics feature words; according to the logistics features included in each logistics feature word identification information in the above-mentioned logistics feature word identification information set Words and location information are used to generate labels corresponding to the above logistics point of interest information.
  • some embodiments of the present disclosure provide a device for generating logistics point of interest information.
  • the device includes: an acquisition unit configured to obtain logistics point of interest information to be marked, wherein the above-mentioned logistics point of interest information includes logistics point of interest.
  • the recognition unit is configured to identify the logistics feature words included in the above-mentioned logistics point of interest text and the position of the above-mentioned logistics feature word in the above-mentioned logistics point of interest text according to the logistics feature word information set, and obtain the logistics feature word identification information set, wherein, the logistics characteristic word identification information in the above-mentioned logistics characteristic word identification information set includes logistics characteristic words and location information, and the logistics characteristic word information in the above-mentioned logistics characteristic word information set includes logistics characteristic words; the generation unit is configured to be based on the above-mentioned logistics Each logistics feature word identification information in the feature word identification information set includes logistics feature words and location information, and generates labels corresponding to the above logistics point of interest information.
  • some embodiments of the present disclosure provide an electronic device, including: at least one processor; a storage device on which at least one program is stored, and when the at least one program is executed by at least one processor, at least one process
  • the device implements the method described in any implementation manner of the first aspect above.
  • some embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.
  • Figure 1 is a schematic diagram of an application scenario of the logistics point of interest information generation method according to some embodiments of the present disclosure
  • Figure 2 is a flow chart of some embodiments of a logistics point of interest information generation method according to the present disclosure
  • Figure 3 is a flow chart of other embodiments of a method for generating logistics point of interest information according to the present disclosure
  • Figure 4 is a schematic diagram of determining tags corresponding to logistics point of interest text in some embodiments of the logistics point of interest information generation method according to the present disclosure
  • Figure 5 is an overall schematic diagram of some embodiments of a logistics point of interest information generation method according to the present disclosure.
  • Figure 6 is a schematic structural diagram of some embodiments of the logistics point of interest information generation device of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.
  • Relevant methods for generating logistics point of interest information for example, determining the labels of logistics points of interest based on the logistics point of interest information, thereby determining the delivery timeliness of different logistics points of interest based on the labels, often have the following technical problems: Current annotation of logistics point of interest information The rate is often low, and the annotation information is often not accurate enough.
  • some embodiments of the present disclosure propose methods and devices for generating logistics point of interest information, which can improve the labeling rate and labeling accuracy of new, unlabeled logistics point of interest information.
  • Figure 1 is a schematic diagram of an application scenario of the logistics point of interest information generation method according to some embodiments of the present disclosure.
  • the computing device 101 can obtain the logistics point of interest information 102 to be marked.
  • the above-mentioned logistics point of interest information 102 includes logistics point of interest text 1021.
  • the computing device 101 can identify the logistics characteristic words included in the above-mentioned logistics point of interest text 1021 and the position of the above-mentioned logistics characteristic word in the above-mentioned logistics point of interest text 1021 according to the logistics characteristic word information set 103, and obtain the logistics characteristic word identification information set. 104.
  • the logistics characteristic word identification information in the logistics characteristic word identification information set 104 includes logistics characteristic words and location information
  • the logistics characteristic word information in the logistics characteristic word information set 103 includes logistics characteristic words.
  • the computing device 101 can generate the label 105 corresponding to the logistics point of interest information 102 based on the logistics characteristic words and location information included in each logistics characteristic word identification information in the logistics characteristic word identification information set 104 .
  • the above-mentioned computing device 101 may be hardware or software.
  • the computing device When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device.
  • the computing device When the computing device is embodied as software, it can be installed in the hardware device listed above. It may be implemented, for example, as multiple pieces of software or software modules used to provide distributed services, or as a single piece of software or software module. There are no specific limitations here.
  • the logistics point of interest information generation method includes the following steps:
  • Step 201 Obtain logistics point of interest information to be marked.
  • the execution subject of the logistics point of interest information generation method can obtain the logistics point of interest information to be marked through a wired connection or a wireless connection.
  • the above-mentioned logistics point of interest information includes logistics point of interest text.
  • the above-mentioned logistics point of interest text may be text representing an address in a logistics scene.
  • the logistics point of interest information to be marked may be the address information that the user inputs when placing an order and has not been marked in advance.
  • the logistics point of interest text included in the above logistics point of interest information may be “ ⁇ province ⁇ city ⁇ county ⁇ township”, “ ⁇ province ⁇ city ⁇ district ⁇ road and ⁇ 100 meters south of the road intersection”, “ ⁇ International Plaza ⁇ Apartment ⁇ Block ⁇ Floor ⁇ Avenue ⁇ District ⁇ City ⁇ ”.
  • Step 202 According to the logistics characteristic word information set, identify the logistics characteristic words included in the logistics point of interest text and the positions of the logistics characteristic words in the logistics point of interest text, and obtain a logistics characteristic word identification information set.
  • the logistics characteristic word identification information in the above logistics characteristic word identification information set may include logistics characteristic words and location information.
  • the logistics characteristic word information in the above logistics characteristic word information set may include logistics characteristic words.
  • the logistics feature words included in the logistics feature word information may be extracted in advance from the sample logistics point of interest text.
  • the above-mentioned execution subject can identify whether the above-mentioned logistics point of interest text includes words representing spatial attributes through a keyword extraction algorithm.
  • the above keyword extraction algorithm may include, but is not limited to, at least one of the following: a keyword extraction algorithm based on statistical features and a TextRank (text level) keyword extraction algorithm.
  • the above-mentioned words characterizing spatial attributes may include, but are not limited to, at least one of the following: east, west, south, north, front, back, left, right or center.
  • the spatial attribute words included in the above-mentioned logistics point of interest text can also be identified through a string matching algorithm according to the set of spatial attribute words, so as to determine whether the above-mentioned logistics point of interest text includes words representing spatial attributes.
  • the spatial attribute words included in the above spatial attribute word set may be words representing spatial attributes. For example, east, west, south, north, front, back, left, right, or center.
  • the above spatial attribute word set may be generated in advance.
  • the above-mentioned string matching algorithm may include but is not limited to at least one of the following: Naive Algorithm, Finite Automation algorithm, or brute force matching method.
  • the logistics point of interest text "100 meters south of the intersection of ⁇ Road and ⁇ Road in ⁇ District, ⁇ City, ⁇ province” includes the word “south” that represents the spatial attribute.
  • the above-mentioned execution subject can identify the logistics characteristic words included in the logistics point of interest text through the above-mentioned string matching algorithm according to the logistics characteristic word information set.
  • the starting index number or the ending index number of the identified logistics feature words in the above-mentioned logistics point of interest text is used as the location information of the logistics feature words.
  • the above-mentioned starting index number may be the index number at the position where the first character of the above-mentioned logistics feature word appears in the above-mentioned logistics point of interest text.
  • the above-mentioned termination index number may be the index number at the position where the last character of the above-mentioned logistics feature word appears in the above-mentioned logistics point of interest text.
  • the above-mentioned logistics feature word information set may be generated in advance.
  • the above logistics characteristic words may include but are not limited to at least one of the following: supermarket, community, building, square, hospital or apartment.
  • the logistics point of interest text " ⁇ International Plaza ⁇ Apartment ⁇ Block ⁇ Floor ⁇ Avenue ⁇ District ⁇ City” includes the logistics feature words “square” and "apartment”.
  • the first character “Guang” of "square” is the 17th character in the above logistics point of interest text.
  • the last character “field” of "square” is the 18th character in the above logistics point of interest text. Therefore, the starting index number and the ending index number of the above-mentioned logistics feature word "square” in the above-mentioned logistics point of interest text are 17 and 18 respectively.
  • the starting index number and the ending index number of the above-mentioned logistics feature word "apartment" in the above-mentioned logistics point of interest text are 21 and 22 respectively.
  • the starting index number can be used as the location information of the logistics feature word in the above logistics point of interest text.
  • the above logistics feature word identification information set can be ⁇ [square, 17], [apartment, 22] ⁇ .
  • the termination index number can also be used as the location information of the logistics feature word in the above-mentioned logistics point of interest text.
  • the above-mentioned logistics feature word identification information set can be ⁇ [square, 18], [apartment, 23] ⁇ .
  • the execution subject may input the logistics point of interest text into a pre-trained label classifier to obtain the label corresponding to the logistics point of interest text.
  • the above-mentioned label classifier may include but is not limited to at least one of the following: CNN (Convolutional Neural Networks, convolutional neural network) and RNN (Recurrent Neural Network, recurrent neural network).
  • the corresponding tags for logistics point of interest texts containing uncertain words such as spatial attribute words can be determined through the tag classifier.
  • the annotation rate of logistics point of interest text and logistics point of interest information is further improved.
  • Step 203 Generate labels corresponding to the logistics point of interest information based on the logistics characteristic words and location information included in each logistics characteristic word identification information in the logistics characteristic word identification information set.
  • the above-mentioned execution subject may respond to determining that the above-mentioned logistics characteristic word identification information set is not empty, and generate the above-mentioned logistics characteristic word identification information according to the logistics characteristic words and location information included in each logistics characteristic word identification information in the above-mentioned logistics characteristic word identification information set.
  • the label corresponding to the logistics point of interest information can be included:
  • the logistics feature words included in the logistics feature word recognition information with the largest starting index number or ending index number included in the above set of logistics feature word recognition information are used as target logistics feature words.
  • the above logistics feature word identification information set may be ⁇ [square, 17], [apartment, 22] ⁇ . 22 is the largest index number, and the target logistics feature word can be "apartment".
  • the second step is to find the labels corresponding to the above target logistics feature words in the pre-configured logistics point of interest label mapping table.
  • the above-mentioned logistics point of interest label mapping table includes label mapping pairs.
  • the label mapping pair includes labels and logistics feature words.
  • the labels and logistics feature words in the same label mapping pair have corresponding relationships.
  • the tags included in the tag mapping pair in which the logistics feature words included in the above-mentioned logistics point of interest tag mapping table and the above-mentioned target logistics feature word are the same can be used as tags corresponding to the above-mentioned logistics point of interest information.
  • the labels of logistics interest points can be divided into: residential areas, company buildings, business districts, Education, medical care, government social institutions, other life services and other addresses and place names, etc. And the labels of each logistics point of interest are mapped to each logistics feature word and the existing multi-scenario common point of interest label in advance, and the above-mentioned preconfigured logistics point of interest label mapping table is obtained.
  • each label mapping pair included in the above logistics point of interest label mapping table may be, but is not limited to, at least one of the following: (business residence - residential complex, apartment), (shopping service - other life services, supermarket).
  • the logistics feature word included in the above-mentioned logistics point of interest tag mapping table is the same tag mapping pair as the above-mentioned target logistics feature word "apartment" (business residence-residential community, apartment).
  • the label corresponding to the above logistics point of interest information may be "Business Residence-Residential Community-Apartment".
  • the above target logistics feature words can also be directly used as labels corresponding to the above logistics point of interest information.
  • the logistics feature word information in the above logistics feature word information set also includes a weight value.
  • the above weight value may be set in advance for the logistics feature words according to the importance of the logistics feature words in the logistics scene.
  • the above-mentioned execution subject generates a label corresponding to the above-mentioned logistics point of interest information based on the logistics characteristic words and location information included in each logistics characteristic word identification information in the above-mentioned logistics characteristic word identification information set, which may include the following steps:
  • the first step is to determine the logistics feature words of the above-mentioned logistics feature words based on the weight value corresponding to the logistics feature words included in each logistics feature word recognition information in the above-mentioned logistics feature word recognition information set and the location information included in the above-mentioned logistics feature word recognition information. Score value, obtain the score value set of logistics feature words.
  • the product value of the weight value corresponding to the above-mentioned logistics feature word in the above-mentioned logistics feature word identification information set and the starting index number or the ending index number represented by the above-mentioned location information can be determined as the logistics feature word score of the above-mentioned logistics feature word. value.
  • the logistics feature word corresponding to the largest logistics feature word score value in the above-mentioned logistics feature word score value set is determined as the label corresponding to the above-mentioned logistics point of interest information.
  • the logistics feature word corresponding to the largest logistics feature word score value in the above set of logistics feature word score values can also be determined as the target logistics feature word. Then, in the above-mentioned pre-configured logistics point of interest tag mapping table, search for the tag corresponding to the above-mentioned target logistics feature word.
  • the above-mentioned embodiments of the present disclosure have the following beneficial effects: through the logistics point of interest information generation methods of some embodiments of the present disclosure, the labeling rate and labeling accuracy of new, unlabeled logistics point of interest information can be improved.
  • the reason why the annotation rate of relevant logistics point of interest information is low and the annotation information is not accurate enough is that: currently, when annotating logistics point of interest information, the usual method is to use the crowdsourcing model to annotate logistics point of interest information. Label, when the user fills in the shipping address or shipping address when placing an order, let the user manually add a label to the shipping address or shipping address; or when the user enters the address information, add the existing address information that is similar to the address information entered by the user.
  • the label of the address information is used as the label of the address information input by the user.
  • whether the user manually adds a label to the receiving address or shipping address depends on the user's subjective will and subjective perception. Therefore, it is impossible to ensure that the user fills in the receiving address when placing an order.
  • the address or shipping address has a corresponding and accurate label; or when the user enters the address information, the address information similar to the address information entered by the user cannot be found, and in this case the label corresponding to the address information entered by the user cannot be determined.
  • the annotation rate of logistics interest point information is low and the annotation information is not accurate enough.
  • the logistics point of interest information generation method of some embodiments of the present disclosure realizes the annotation of logistics point of interest information by identifying logistics feature words in the logistics point of interest text.
  • the influence of human subjective factors in crowdsourcing mode is avoided and the accuracy of annotated information is improved.
  • the annotation rate of logistics point of interest information is improved.
  • the process 300 of the logistics point of interest information generation method includes the following steps:
  • Step 301 Obtain logistics point of interest information to be marked.
  • Step 302 According to the logistics feature word information set, identify the logistics feature words included in the logistics point of interest text and the position of the logistics feature word in the logistics point of interest text, and obtain a logistics feature word identification information set.
  • Step 303 Generate labels corresponding to the logistics point of interest information based on the logistics characteristic words and location information included in each logistics characteristic word identification information in the logistics characteristic word identification information set.
  • steps 301-303 and the technical effects brought by them can be referred to steps 201-203 in those embodiments corresponding to Figure 2, which will not be described again here.
  • Step 304 In response to determining that the logistics feature word identification information set is empty, identify whether the logistics point of interest text includes target area information.
  • the execution subject of the logistics point of interest information generation method may identify whether the target is included in the logistics point of interest text in response to determining that the above logistics feature word identification information set is empty.
  • the above target area information may be information characterizing villages, towns, communities, etc.
  • the above string matching algorithm can be used to identify whether the above logistics point of interest text contains the name of a village, town or community name database, so as to determine whether the above mentioned logistics point of interest text includes target area information.
  • the logistics point of interest text "XX City ⁇ City ⁇ County ⁇ Township” includes the village name "XX Township”.
  • Step 305 In response to identifying that the logistics point of interest text includes target area information, generate a label corresponding to the logistics point of interest information based on the identified target area information.
  • the execution subject may respond to identifying that the logistics point of interest text includes target area information, and replace the replacement bit information in the preset label template corresponding to the target area information with the identified target. Regional information, get the tag corresponding to the logistics point of interest information.
  • the above label template corresponding to the target area information may be "other place name address information-common place name-replacement bits”. Then the label corresponding to the above-mentioned logistics point of interest information may be "Other place name address information-common place name- ⁇ Township”.
  • Step 306 In response to identifying that the logistics point of interest text does not include target area information, identify whether the logistics point of interest text includes road information.
  • the execution subject may identify whether the logistics point of interest text includes road information in response to identifying that the logistics point of interest text does not include target area information. Whether the logistics point of interest text includes the road name in the road name database can be identified through the string matching algorithm to determine whether the logistics point of interest text includes road information.
  • the logistics point of interest text may be " ⁇ Avenue, ⁇ City, ⁇ County, ⁇ province”. Then it can be identified that the above logistics point of interest text includes road information " ⁇ Avenue”.
  • Step 307 In response to identifying that the logistics point of interest text includes road information, generate a label corresponding to the logistics point of interest information based on the identified road information.
  • the execution subject may respond to identifying that the logistics point of interest text includes road information, and replace the information in the replacement bits in the preset label template corresponding to the road information with the identified road information, Obtain the label corresponding to the above logistics point of interest information.
  • the above label template corresponding to the target area information may be "other place name address information-transportation place name-replacement bit”. Then the label corresponding to the logistics point of interest information may be "Other place name address information-Transportation place name- ⁇ Avenue”.
  • the empty set of the above-mentioned logistics feature word identification information can mean that the above-mentioned logistics point of interest text does not include logistics feature words that can be directly identified, that is, the label corresponding to the above-mentioned logistics point of interest information cannot be determined through the method of logistics feature word identification.
  • the target area information or road information in the logistics point of interest text is mainly further identified to determine the label corresponding to the above logistics point of interest information.
  • Step 308 In response to identifying that the logistics point of interest text does not include road information, search for similar logistics point of interest text of the logistics point of interest text based on the coordinates of the logistics point of interest, and obtain a similar logistics point of interest text set.
  • the above-mentioned logistics point of interest information may also include coordinates of the logistics point of interest.
  • the above-mentioned execution subject may respond to identifying that the above-mentioned logistics point of interest text does not include road information, and according to the above-mentioned logistics point of interest coordinates, determine the logistics point of interest text included in the marked logistics point of interest information that meets the preset conditions as similar logistics. Point-of-interest text to obtain similar logistics point-of-interest text.
  • the coordinates of the above-mentioned stream interest points can be expressed in longitude and latitude.
  • the above-mentioned preset condition may be that the distance value between the coordinates of the logistics point of interest included in the marked logistics point of interest information and the coordinates of the above-mentioned logistics point of interest is less than the preset distance value.
  • the above marked logistics point of interest information includes the coordinates of the logistics point of interest.
  • the execution subject searches for similar logistics point of interest texts of the logistics point of interest text based on the coordinates of the logistics point of interest, and obtains a set of similar logistics point of interest texts, which may include the following steps:
  • the logistics point of interest text included in the marked logistics point of interest information that meets the preset conditions is determined as the candidate logistics point of interest text, and a candidate logistics point of interest text set is obtained.
  • the above-mentioned preset condition may be that the distance value between the coordinates of the logistics point of interest included in the marked logistics point of interest information and the coordinates of the above-mentioned logistics point of interest is less than the preset distance value.
  • the second step is to select the candidate logistics point of interest text whose similarity to the above mentioned logistics point of interest text is greater than the preset similarity threshold from the above candidate logistics point of interest text set as the similar logistics point of interest text, and obtain the similar logistics point of interest text.
  • Text collection a text similarity algorithm can be used to determine the text similarity between the above-mentioned logistics point of interest text and each candidate logistics point of interest text in the above-mentioned candidate logistics point of interest text set.
  • the above text similarity algorithm may include but is not limited to at least one of the following: cosine similarity algorithm, TF-IDF (term frequency-inverse document frequency, term frequency-inverse document frequency) algorithm, etc.
  • Step 309 Score the label corresponding to each similar logistics point of interest text in the similar logistics point of interest text set to obtain a label score set.
  • the execution subject may use the weight value of the tag corresponding to the similar logistics point of interest text as the tag score.
  • the execution subject may determine the numerical value of the similarity between the similar logistics point of interest text and the logistics point of interest text as the label score corresponding to the similar logistics point of interest text.
  • Step 310 Based on the similar logistics point of interest text set and the tag score set, determine whether there is a tag corresponding to the logistics point of interest text among the tags corresponding to each similar logistics point of interest text in the similar logistics point of interest text set.
  • the execution subject may determine, based on the similar logistics point of interest text set and the label score set, whether there is a tag corresponding to the logistics point of interest text in the similar logistics point of interest text set.
  • the label corresponding to the text may be determined, based on the similar logistics point of interest text set and the label score set, whether there is a tag corresponding to the logistics point of interest text in the similar logistics point of interest text set. The label corresponding to the text.
  • the above execution subject determines whether the tag corresponding to each similar logistics point of interest text in the above similar logistics point of interest text set is based on the above similar logistics point of interest text set and the above tag score set.
  • There is a label corresponding to the above logistics point of interest text which can include the following steps:
  • the label with the most corresponding similar logistics point of interest texts in the above similar logistics point of interest text set is determined as the first label.
  • the label corresponding to the largest label score in the above label score set is determined as the second label.
  • the third step in response to determining that the first label is the same as the second label, determine the first label as a label corresponding to the logistics point of interest text.
  • the tag corresponding to the most similar logistics point of interest texts in the above-mentioned similar logistics point of interest text set 401 may be determined as the first tag 402 .
  • the label corresponding to the largest label score in the above-mentioned label score set 403 is determined as the second label 404 .
  • the first label 402 is determined as a label corresponding to the logistics point of interest text 405 .
  • Tags can also include the following steps:
  • the logistics point of interest text when the logistics point of interest text does not include logistics feature words, target area information and road information, the logistics point of interest text can be determined through the marked logistics interest points near the logistics point of interest represented by the logistics point of interest text. corresponding label.
  • This processing method is in line with the first law of geography—spatial correlation, that is, the correlation between ground objects is related to distance. Generally speaking, the closer the distance, the greater the correlation between ground objects. The farther the distance, the greater the correlation between ground objects. The greater the dissimilarity.
  • Step 311 In response to determining that the tags corresponding to each similar logistics point of interest text in the similar logistics point of interest text set do not contain tags corresponding to the logistics point of interest text or the logistics point of interest text includes words that represent spatial attributes, the logistics point of interest text is The text is input into the pre-trained label classifier, and the labels corresponding to the logistics point of interest text are obtained.
  • the above execution subject may respond to determining that there is no tag corresponding to the above logistics point of interest text in the tag corresponding to each similar logistics point of interest text in the above similar logistics point of interest text set or the above mentioned logistics point of interest text includes For words that represent spatial attributes, input the above-mentioned logistics point of interest text into the pre-trained label classifier to obtain the label corresponding to the above-mentioned logistics point of interest text.
  • the above-mentioned label classifier may include but is not limited to at least one of the following: CNN (Convolutional Neural Networks, convolutional neural network) and RNN (Recurrent Neural Network, recurrent neural network).
  • the corresponding label can be determined through the label classifier.
  • the annotation rate of logistics point of interest text and logistics point of interest information is further improved.
  • FIG. 5 is an overall schematic diagram of some embodiments of a logistics point of interest information generation method according to the present disclosure.
  • feature word extraction processing can be performed on the logistics point of interest information. If the logistics point of interest information includes spatial attribute words, the logistics point of interest information can be directly input into the text classification model to obtain the output label. Otherwise, the label is determined based on the extracted logistics feature words. If the tag still cannot be determined, the tag corresponding to the logistics point of interest information is jointly determined through the points of interest surrounding the logistics point of interest. If the label corresponding to the logistics point of interest information cannot be determined through the interest points around the logistics point of interest, the logistics point of interest information is input into the text classification model to obtain the output label.
  • the process 300 of the logistics point of interest information generation method in some embodiments corresponding to Figure 3 embodies the problem of tags that cannot be determined through logistics feature word recognition.
  • the logistics point of interest text can be further processed.
  • the logistics point of interest text is progressively annotated layer by layer.
  • the annotation rate of logistics interest point information is further improved to a certain extent.
  • the present disclosure provides some embodiments of a logistics point of interest information generation device. These device embodiments correspond to those method embodiments shown in Figure 2.
  • the device can be applied in various electronic devices.
  • the logistics point of interest information generation device 600 of some embodiments includes: an acquisition unit 601, an identification unit 602 and a generation unit 603.
  • the acquisition unit 601 is configured to acquire logistics point of interest information to be marked, where the above logistics point of interest information includes logistics point of interest text.
  • the identification unit 602 is configured to identify the logistics characteristic words included in the above-mentioned logistics point of interest text and the position of the above-mentioned logistics characteristic word in the above-mentioned logistics point of interest text according to the logistics characteristic word information set, and obtain a logistics characteristic word identification information set, where , the logistics characteristic word identification information in the above logistics characteristic word identification information set includes logistics characteristic words and location information, and the logistics characteristic word information in the above logistics characteristic word information set includes logistics characteristic words.
  • the generating unit 603 is configured to generate a label corresponding to the above-mentioned logistics point of interest information based on the logistics characteristic words and location information included in each logistics characteristic word identification information in the above-mentioned logistics characteristic word identification information set.
  • the above-mentioned logistics point of interest information generation device further includes a first input unit configured to, in response to determining that the above-mentioned logistics point of interest text includes words characterizing spatial attributes, convert the above-mentioned logistics point of interest text into Input the pre-trained label classifier to obtain the labels corresponding to the above logistics point of interest text.
  • the above-mentioned logistics point of interest information generation device further includes a target area information identification unit and a first generation unit.
  • the target area information identification unit is configured to identify whether the logistics point of interest text includes target area information in response to determining that the logistics feature word identification information set is empty.
  • the first generating unit is configured to respond to identifying that the logistics point of interest text includes target area information, and generate a label corresponding to the logistics point of interest information based on the identified target area information.
  • the above-mentioned logistics point of interest information generation device further includes a road information identification unit and a second generation unit.
  • the road information identification unit is configured to identify whether the logistics point of interest text includes road information in response to identifying that the logistics point of interest text does not include target area information.
  • the second generation unit is configured to, in response to identifying that the logistics point of interest text includes road information, generate a label corresponding to the logistics point of interest information based on the identified road information.
  • the above-mentioned logistics point of interest information also includes coordinates of the logistics point of interest; and the above-mentioned logistics point of interest information generation device further includes: a search unit, a scoring unit and a label determination unit.
  • the search unit is configured to, in response to identifying that the above-mentioned logistics point of interest text does not include road information, search for similar logistics point of interest text of the above-mentioned logistics point of interest text according to the coordinates of the above-mentioned logistics point of interest, and obtain a set of similar logistics point of interest texts.
  • the scoring unit is configured to score the label corresponding to each similar logistics point of interest text in the above similar logistics point of interest text set to obtain a label score set.
  • the label determination unit is configured to determine, based on the above-mentioned similar logistics point-of-interest text set and the above-mentioned tag score set, whether there is a label corresponding to the above-mentioned logistics point-of-interest text in the tag corresponding to each similar logistics point-of-interest text in the above-mentioned similar logistics point-of-interest text set. Label.
  • the above-mentioned logistics point of interest information generation device further includes a second input unit configured to respond to determining that there are no tags corresponding to each similar logistics point of interest text in the above-mentioned similar logistics point of interest text set.
  • tags corresponding to the above-mentioned logistics point of interest text or the above-mentioned logistics point of interest text includes words representing spatial attributes.
  • the above-mentioned logistics point of interest text is input into the pre-trained label classifier to obtain the tag corresponding to the above-mentioned logistics point of interest text.
  • the above-mentioned search unit includes a candidate logistics point of interest text determination subunit and a selection subunit.
  • the candidate logistics point of interest text determination subunit is configured to determine the logistics point of interest text included in the marked logistics point of interest information that meets the preset conditions as the candidate logistics point of interest text, and obtain a candidate logistics point of interest text set,
  • the above-mentioned preset condition is that the distance value between the coordinates of the logistics point of interest included in the marked logistics point of interest information and the coordinates of the above-mentioned logistics point of interest is less than the preset distance value.
  • the selection subunit is configured to select, from the above candidate logistics point of interest text set, a candidate logistics point of interest text whose similarity to the above mentioned logistics point of interest text is greater than a preset similarity threshold as a similar logistics point of interest text, and obtain a similarity Logistics points of interest text collection.
  • the scoring unit is configured to determine the value of the similarity between the similar logistics point of interest text and the logistics point of interest text as the label score corresponding to the similar logistics point of interest text.
  • the above-mentioned tag determination unit is configured to determine the tag with the most corresponding similar logistics point-of-interest texts in the above-mentioned similar logistics point-of-interest text set as the first tag; and the above-mentioned tag score set The label corresponding to the largest label score is determined as the second label; in response to determining that the above-mentioned first label is the same as the above-mentioned second label, the above-mentioned first label is determined as the label corresponding to the above-mentioned logistics point of interest text.
  • the above-mentioned label determination unit is further configured to: in response to determining that the above-mentioned first label is not the same as the above-mentioned second label, determine each similar logistics point of interest in the above-mentioned similar logistics point of interest text set. There is no tag corresponding to the above logistics point of interest text among the tags corresponding to the text.
  • the logistics feature word information in the above logistics feature word information set also includes a weight value; and the above generation unit includes a logistics feature word score value determination subunit and a label determination subunit.
  • the logistics feature word score value determination sub-unit is configured to determine the weight value corresponding to the logistics feature word included in each logistics feature word identification information in the above-mentioned logistics feature word identification information set and the location information included in the above-mentioned logistics feature word identification information, The logistics feature word score values of the above logistics feature words are determined, and a set of logistics feature word score values is obtained.
  • the label determination subunit is configured to determine the logistics feature word corresponding to the largest logistics feature word score value in the above-mentioned logistics feature word score value set as the label corresponding to the above-mentioned logistics point of interest information.
  • the units recorded in the device 600 correspond to various steps in the method described with reference to FIG. 2 . Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 600 and the units included therein, and will not be described again here.
  • FIG. 7 a schematic structural diagram of an electronic device 700 suitable for implementing some embodiments of the present disclosure is shown.
  • the electronic device shown in FIG. 7 is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present disclosure.
  • the electronic device 700 may include a processing device (eg, central processing unit, graphics processor, etc.) 701 that may be loaded into a random access device according to a program stored in a read-only memory (ROM) 702 or from a storage device 708 .
  • the program in the memory (RAM) 703 executes various appropriate actions and processes.
  • various programs and data required for the operation of the electronic device 700 are also stored.
  • the processing device 701, ROM 702 and RAM 703 are connected to each other via a bus 704.
  • An input/output (I/O) interface 705 is also connected to bus 704.
  • the following devices may be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 707 such as a computer; and a communication device 709.
  • Communication device 709 may allow electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 7 illustrates an electronic device 700 having various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided. Each block shown in Figure 7 may represent one device, or may represent multiple devices as needed.
  • the processes described above with reference to the flowcharts may be implemented as a computer software program.
  • some embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communication device 709, or from storage device 708, or from ROM 702.
  • the processing device 701 the above-described functions defined in the methods of some embodiments of the present disclosure are performed.
  • the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having at least one conductor, a portable computer disk, a hard disk, random access memory (RAM), read only memory (ROM), erasable programmable memory Read memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and server can communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communications e.g., communications network
  • communications networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or developed in the future network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
  • the computer-readable medium carries one or more programs.
  • the electronic device obtains logistics interest point information to be marked, where the logistics interest point information includes logistics Point of interest text; according to the logistics feature word information set, identify the logistics feature words included in the above-mentioned logistics point of interest text and the position of the above-mentioned logistics feature word in the above-mentioned logistics point of interest text, and obtain a logistics feature word identification information set, wherein the above-mentioned logistics
  • the logistics feature word identification information in the feature word identification information set includes logistics feature words and location information.
  • the logistics feature word information in the above-mentioned logistics feature word information set includes logistics feature words; according to the above-mentioned logistics feature word identification information set, each logistics feature in the information set
  • the word recognition information includes logistics characteristic words and location information, and generates labels corresponding to the above logistics point of interest information.
  • Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof, Also included are conventional procedural programming languages—such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider). connected via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as an Internet service provider
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains at least one operable function for implementing the specified logical function.
  • Execute instructions may also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units described in some embodiments of the present disclosure may be implemented in software or hardware.
  • the described unit may also be provided in a processor.
  • a processor includes an acquisition unit, an identification unit and a generation unit.
  • the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the identification unit can also be described as "a unit that identifies logistics characteristic words and locations.”
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLD Complex Programmable Logical device

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开的实施例公开了物流兴趣点信息生成方法、装置、设备和计算机可读介质。该方法的一具体实施方式包括：获取待标注的物流兴趣点信息；根据物流特征词信息集合，识别物流兴趣点文本中包括的物流特征词和物流特征词在物流兴趣点文本中的位置，得到物流特征词识别信息集合；根据物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成物流兴趣点信息所对应的标签。

Description

物流兴趣点信息生成方法、装置、设备和计算机可读介质
相关申请的交叉引用
本申请要求于申请日为2022年05月26日提交的，申请号为202210581210.9、发明名称为“物流兴趣点信息生成方法、装置、设备和计算机可读介质”的中国专利申请的优先权，其全部内容作为整体并入本申请中。
技术领域
本公开的实施例涉及计算机技术领域，具体涉及物流兴趣点信息生成方法、装置、设备和计算机可读介质。
背景技术
物流兴趣点信息，是指在物流场景中能够进行物流配送的地点(例如，楼宇住宅、商圈和学校等)的地址等相关信息。在实际应用中，需要根据物流兴趣点信息确定物流兴趣点的标签，从而根据标签确定不同的物流兴趣点的配送时效。例如，写字楼在周末可能不配送，小区工作日的白天不配送等。
发明内容
本公开的内容部分用于以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。本公开的内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的一些实施例提出了物流兴趣点信息生成方法、装置、设备和计算机可读介质，来解决以上背景技术部分提到的技术问题。
第一方面，本公开的一些实施例提供了一种物流兴趣点信息生成方法，该方法包括：获取待标注的物流兴趣点信息，其中，上述物流 兴趣点信息包括物流兴趣点文本；根据物流特征词信息集合，识别上述物流兴趣点文本中包括的物流特征词和上述物流特征词在上述物流兴趣点文本中的位置，得到物流特征词识别信息集合，其中，上述物流特征词识别信息集合中的物流特征词识别信息包括物流特征词和位置信息，上述物流特征词信息集合中的物流特征词信息包括物流特征词；根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息所对应的标签。
第二方面，本公开的一些实施例提供了一种物流兴趣点信息生成装置，装置包括：获取单元，被配置成获取待标注的物流兴趣点信息，其中，上述物流兴趣点信息包括物流兴趣点文本；识别单元，被配置成根据物流特征词信息集合，识别上述物流兴趣点文本中包括的物流特征词和上述物流特征词在上述物流兴趣点文本中的位置，得到物流特征词识别信息集合，其中，上述物流特征词识别信息集合中的物流特征词识别信息包括物流特征词和位置信息，上述物流特征词信息集合中的物流特征词信息包括物流特征词；生成单元，被配置成根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息所对应的标签。
第三方面，本公开的一些实施例提供了一种电子设备，包括：至少一个处理器；存储装置，其上存储有至少一个程序，当至少一个程序被至少一个处理器执行，使得至少一个处理器实现上述第一方面任一实现方式所描述的方法。
第四方面，本公开的一些实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现上述第一方面任一实现方式所描述的方法。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，元件和元素不一定按照比例绘制。
图1是本公开的一些实施例的物流兴趣点信息生成方法的一个应用场景的示意图；
图2是根据本公开的物流兴趣点信息生成方法的一些实施例的流程图；
图3是根据本公开的物流兴趣点信息生成方法的另一些实施例的流程图；
图4是根据本公开的物流兴趣点信息生成方法的一些实施例中的确定物流兴趣点文本对应的标签的示意图；
图5是根据本公开的物流兴趣点信息生成方法的一些实施例的整体示意图。
图6是本公开的物流兴趣点信息生成装置的一些实施例的结构示意图；
图7是适于用来实现本公开的一些实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出， 否则应该理解为“至少一个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
相关的物流兴趣点信息生成方法，例如，根据物流兴趣点信息确定物流兴趣点的标签，从而根据标签确定不同的物流兴趣点的配送时效等经常会存在如下技术问题：目前物流兴趣点信息的标注率往往较低，标注信息往往不够准确。
为了解决以上所阐述的问题，本公开的一些实施例提出了物流兴趣点信息生成方法及装置，可以提升新的、未标注的物流兴趣点信息的标注率和标注准确性。
下面将参考附图并结合实施例来详细说明本公开。
图1是本公开的一些实施例的物流兴趣点信息生成方法的一个应用场景的示意图。
在图1的应用场景中，首先，计算设备101可以获取待标注的物流兴趣点信息102。其中，上述物流兴趣点信息102包括物流兴趣点文本1021。然后，计算设备101可以根据物流特征词信息集合103，识别上述物流兴趣点文本1021中包括的物流特征词和上述物流特征词在上述物流兴趣点文本1021中的位置，得到物流特征词识别信息集合104。其中，上述物流特征词识别信息集合104中的物流特征词识别信息包括物流特征词和位置信息，上述物流特征词信息集合103中的物流特征词信息包括物流特征词。最后，计算设备101可以根据上述物流特征词识别信息集合104中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息102所对应的标签105。
需要说明的是，上述计算设备101可以是硬件，也可以是软件。当计算设备为硬件时，可以实现成多个服务器或终端设备组成的分布式集群，也可以实现成单个服务器或单个终端设备。当计算设备体现为软件时，可以安装在上述所列举的硬件设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件 或软件模块。在此不做具体限定。
应该理解，图1中的计算设备的数目仅仅是示意性的。根据实现需要，可以具有任意数目的计算设备。
继续参考图2，示出了根据本公开的物流兴趣点信息生成方法的一些实施例的流程200。该物流兴趣点信息生成方法，包括以下步骤：
步骤201，获取待标注的物流兴趣点信息。
在一些实施例中，物流兴趣点信息生成方法的执行主体(如图1所示的计算设备101)可以通过有线连接方式或者无线连接方式获取待标注的物流兴趣点信息。其中，上述物流兴趣点信息包括物流兴趣点文本。上述物流兴趣点文本可以是物流场景中表征地址的文本。待标注的物流兴趣点信息可以是用户在下单时输入的未预先进行标注的地址信息。
作为示例，上述物流兴趣点信息中包括的物流兴趣点文本可以是“××省×××市××县××乡”，“××省×××市××区××路与××路交叉口南100米”，“××市××区××大道×××号××国际广场××公寓×座×层”。
步骤202，根据物流特征词信息集合，识别物流兴趣点文本中包括的物流特征词和物流特征词在物流兴趣点文本中的位置，得到物流特征词识别信息集合。
在一些实施例中，上述物流特征词识别信息集合中的物流特征词识别信息可以包括物流特征词和位置信息。上述物流特征词信息集合中的物流特征词信息可以包括物流特征词。物流特征词信息中包括的物流特征词可以是预先从样本物流兴趣点文本中提取的。
上述执行主体可以通过关键词提取算法识别上述物流兴趣点文本是否包括表征空间属性的词语。上述关键词提取算法可以包括但不限于以下至少一种：基于统计特征的关键词抽取算法和TextRank(文本等级)关键词提取算法。上述表征空间属性的词语可以包括但不限于以下至少一项：东、西、南、北、前、后、左、右或中。
还可以根据空间属性词语集合，通过字符串匹配算法识别上述物 流兴趣点文本中包括的空间属性词语，以确定上述物流兴趣点文本是否包括表征空间属性的词语。上述空间属性词语集合中包括的空间属性词语可以是表征空间属性的词语。例如，东、西、南、北、前、后、左、右或中等。上述空间属性词语集合可以是预先生成的。上述字符串匹配算法可以包括但不限于以下至少一种：Naive Algorithm(朴素算法)、Finite Automation(有限自动机)算法、或蛮力匹配法。
作为示例，物流兴趣点文本“××省×××市××区××路与××路交叉口南100米”中包括了表征空间属性的词语“南”。物流兴趣点文本“××省×××市××县××乡”和“××市××区××大道×××号××国际广场××公寓×座×层”中不包括表征空间属性的词语。
上述执行主体可以根据物流特征词信息集合，通过上述字符串匹配算法识别物流兴趣点文本中包括的物流特征词。并将识别出的物流特征词在上述物流兴趣点文本中的起始索引号或终止索引号作为物流特征词的位置信息。其中，上述起始索引号可以是上述物流特征词的首个字符在上述物流兴趣点文本中出现的位置处的索引号。上述终止索引号可以是上述物流特征词的末位字符在上述物流兴趣点文本中出现的位置处的索引号。上述物流特征词信息集合可以是预先生成的。
作为示例，上述物流特征词可以包括但不限于以下至少一项：超市、小区、大厦、广场、医院或公寓。物流兴趣点文本“××市××区××大道×××号××国际广场××公寓×座×层”中包括物流特征词“广场”和“公寓”。“广场”的首个字符“广”是上述物流兴趣点文本中的第17个字符。“广场”的末位字符“场”是上述物流兴趣点文本中的第18个字符。因此，上述物流特征词“广场”在上述物流兴趣点文本中的起始索引号和终止索引号分别为17和18。同理，上述物流特征词“公寓”在上述物流兴趣点文本中的起始索引号和终止索引号分别为21和22。可以将起始索引号作为物流特征词在上述物流兴趣点文本中的位置信息。则上述物流特征词识别信息集合可以是{[广场，17]，[公寓，22]}。还可以将终止索引号作为物流特征词在上述物流兴趣点文本中的位置信息。则上述物流特征词识别信息集合可 以是{[广场，18]，[公寓，23]}。
可选的，上述执行主体可以响应于确定上述物流兴趣点文本中包括表征空间属性的词语，将上述物流兴趣点文本输入预先训练的标签分类器中，得到上述物流兴趣点文本所对应的标签。其中，上述标签分类器可以包括但不限于以下至少一项：CNN(Convolutional Neural Networks，卷积神经网络)和RNN(Recurrent Neural Network，循环神经网络)。
由此，可以将包含空间属性词语等不确定词语的物流兴趣点文本，通过标签分类器确定对应的标签。进一步提升了物流兴趣点文本和物流兴趣点信息的标注率。
步骤203，根据物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成物流兴趣点信息所对应的标签。
在一些实施例中，上述执行主体可以响应于确定上述物流特征词识别信息集合非空，根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息所对应的标签。其中，可以包括以下步骤：
第一步，将上述物流特征词识别信息集合中包括的起始索引号或终止索引号最大的物流特征词识别信息中包括的物流特征词作为目标物流特征词。
作为示例，上述物流特征词识别信息集合可以是{[广场，17]，[公寓，22]}。22是最大的索引号，则目标物流特征词可以为“公寓”。
第二步，在预先配置的物流兴趣点标签映射表中，查找上述目标物流特征词对应的标签。其中，上述物流兴趣点标签映射表包括标签映射对。标签映射对包括标签和物流特征词。同一个标签映射对中的标签和物流特征词具有对应关系。可以将上述物流兴趣点标签映射表中包括的物流特征词和上述目标物流特征词相同的标签映射对中包括的标签作为上述物流兴趣点信息所对应的标签。
可以结合实际物流场景，从物流兴趣点揽收派送的不同需求、履约时效的不同要求以及物流兴趣点的真实属性等方面，将物流兴趣点 的标签划分为：住宅小区、公司楼宇、商圈、教育、医疗、政府社会机构、其他生活服务和其他地址地名等。并预先将各个物流兴趣点的标签映射至各个物流特征词和现有的多场景通用的兴趣点标签上，得到上述预先配置的物流兴趣点标签映射表。
作为示例，上述物流兴趣点标签映射表中包括的各个标签映射对可以但不限于以下至少一项：(商务住宅-住宅小区，公寓)，(购物服务-其他生活服务，超市)。上述物流兴趣点标签映射表中包括的物流特征词和上述目标物流特征词“公寓”相同的标签映射对是(商务住宅-住宅小区，公寓)。则上述物流兴趣点信息所对应的标签可以是“商务住宅-住宅小区-公寓”。
可选的，也可以直接将上述目标物流特征词作为上述物流兴趣点信息所对应的标签。
在一些实施例的一些可选的实现方式中，上述物流特征词信息集合中的物流特征词信息还包括权重值。上述权重值可以是预先根据物流特征词在物流场景中的重要程度为物流特征词设置的。上述执行主体根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息所对应的标签，可以包括以下步骤：
第一步，根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词对应的权重值和上述物流特征词识别信息包括的位置信息，确定上述物流特征词的物流特征词评分值，得到物流特征词评分值集合。其中，可以将上述物流特征词在上述物流特征词识别信息集合中对应的权重值与上述位置信息所表征的起始索引号或终止索引号的乘积值确定为上述物流特征词的物流特征词评分值。
第二步，将上述物流特征词评分值集合中最大的物流特征词评分值对应的物流特征词确定为上述物流兴趣点信息所对应的标签。
可选的，还可以将上述物流特征词评分值集合中最大的物流特征词评分值对应的物流特征词确定为目标物流特征词。然后，在上述预先配置的物流兴趣点标签映射表中，查找上述目标物流特征词对应的标签。
本公开的上述各个实施例具有如下有益效果：通过本公开的一些实施例的物流兴趣点信息生成方法，可以提升新的、未标注的物流兴趣点信息的标注率和标注准确性。具体来说，造成相关物流兴趣点信息的标注率较低，标注信息不够准确的原因在于：目前，在对物流兴趣点信息进行标注时，通常采用的方式为通过众包模式对物流兴趣点信息进行标注，在用户下单填写收货地址或寄货地址时，让用户手动为收货地址或寄货地址添加标签；或者在用户输入地址信息时，将已有的与用户输入的地址信息相似的地址信息的标签作为用户输入的地址信息的标签。但通过众包模式对物流兴趣点信息进行标注时，用户是否手动为收货地址或寄货地址添加标签取决于用户的主观意愿与主观认知，因此，无法确保用户下单时填写的收货地址或寄货地址均有对应的且准确的标签；或者在用户输入地址信息时，无法找到与用户输入的地址信息相似的地址信息，此时便无法确定用户输入的地址信息所对应的标签。进而，导致物流兴趣点信息的标注率较低，标注信息不够准确。基于此，本公开的一些实施例的物流兴趣点信息生成方法，通过识别物流兴趣点文本中的物流特征词实现对物流兴趣点信息的标注。从而，避免了众包模式下人为主观因素的影响，提升了标注信息的准确性。同时，可以实现为新获取的物流兴趣点信息进行标注。从而，提升物流兴趣点信息的标注率。
参考图3，其示出了物流兴趣点信息生成方法的另一些实施例的流程300。该物流兴趣点信息生成方法的流程300，包括以下步骤：
步骤301，获取待标注的物流兴趣点信息。
步骤302，根据物流特征词信息集合，识别物流兴趣点文本中包括的物流特征词和物流特征词在物流兴趣点文本中的位置，得到物流特征词识别信息集合。
步骤303，根据物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成物流兴趣点信息所对应的标签。
在一些实施例中，步骤301-303的具体实现方式及所带来的技术 效果可以参考图2对应的那些实施例中的步骤201-203，在此不再赘述。
步骤304，响应于确定物流特征词识别信息集合为空，识别物流兴趣点文本中是否包括目标区域信息。
在一些实施例中，物流兴趣点信息生成方法的执行主体(如图1所示的计算设备101)可以响应于确定上述物流特征词识别信息集合为空，识别上述物流兴趣点文本中是否包括目标区域信息。其中，上述目标区域信息可以是表征村庄、乡镇或社区等的信息。可以通过上述字符串匹配算法识别上述物流兴趣点文本中是否包村庄、乡镇或社区名称库中的名称，以确定上述物流兴趣点文本中是否包括目标区域信息。
作为示例，物流兴趣点文本“××省×××市××县××乡”中包括乡村名称“××乡”。
步骤305，响应于识别出物流兴趣点文本中包括目标区域信息，根据所识别出的目标区域信息，生成物流兴趣点信息所对应的标签。
在一些实施例中，上述执行主体可以响应于识别出上述物流兴趣点文本中包括目标区域信息，将预设的与目标区域信息对应的标签模板中的替换位的信息替换为所识别出的目标区域信息，得到物流兴趣点信息所对应的标签。
作为示例，上述与目标区域信息对应的标签模板可以是“其他地名地址信息-普通地名-替换位”。则上述物流兴趣点信息所对应的标签可以是“其他地名地址信息-普通地名-××乡”。
步骤306，响应于识别出物流兴趣点文本中不包括目标区域信息，识别物流兴趣点文本中是否包括道路信息。
在一些实施例中，上述执行主体可以响应于识别出上述物流兴趣点文本中不包括目标区域信息，识别上述物流兴趣点文本中是否包括道路信息。可以通过上述字符串匹配算法识别上述物流兴趣点文本中是否包道路名称库中的道路名称以确定上述物流兴趣点文本中是否包括道路信息。
作为示例，物流兴趣点文本可以是“××省×××市××县×× 大道”。则可以识别出上述物流兴趣点文本中包括道路信息“××大道”。
步骤307，响应于识别出物流兴趣点文本中包括道路信息，根据所识别出的道路信息，生成物流兴趣点信息所对应的标签。
在一些实施例中，上述执行主体可以响应于识别出上述物流兴趣点文本中包括道路信息，将预设的与道路信息对应的标签模板中的替换位的信息替换为所识别出的道路信息，得到上述物流兴趣点信息所对应的标签。
作为示例，上述与目标区域信息对应的标签模板可以是“其他地名地址信息-交通地名-替换位”。则物流兴趣点信息所对应的标签可以是“其他地名地址信息-交通地名-××大道”。
上述物流特征词识别信息集合为空可以表示上述物流兴趣点文本中不包括可以直接识别出的物流特征词，即通过物流特征词识别的方法无法确定上述物流兴趣点信息对应的标签。此时，主要进一步识别物流兴趣点文本中的目标区域信息或道路信息来确定上述物流兴趣点信息对应的标签。
步骤308，响应于识别出物流兴趣点文本中不包括道路信息，根据物流兴趣点坐标，查找物流兴趣点文本的相似物流兴趣点文本，得到相似物流兴趣点文本集合。
在一些实施例中，上述物流兴趣点信息还可以包括物流兴趣点坐标。上述执行主体可以响应于识别出上述物流兴趣点文本中不包括道路信息，根据上述物流兴趣点坐标，将满足预设条件的已标注的物流兴趣点信息中包括的物流兴趣点文本确定为相似物流兴趣点文本，得到相似物流兴趣点文本。其中，上述流兴趣点坐标可以用经纬度表示。上述预设条件可以是已标注的物流兴趣点信息中包括的物流兴趣点坐标与上述物流兴趣点坐标之间的距离值小于预设距离值。上述已标注的物流兴趣点信息包括物流兴趣点坐标。
在一些实施例的一些可选的实现方式中，上述执行主体根据上述物流兴趣点坐标，查找上述物流兴趣点文本的相似物流兴趣点文本，得到相似物流兴趣点文本集合，可以包括以下步骤：
第一步，将满足预设条件的已标注的物流兴趣点信息中包括的物流兴趣点文本确定为候选物流兴趣点文本，得到候选物流兴趣点文本集合。其中，上述预设条件可以是已标注的物流兴趣点信息中包括的物流兴趣点坐标与上述物流兴趣点坐标之间的距离值小于预设距离值。
第二步，从上述候选物流兴趣点文本集合中选择出与上述物流兴趣点文本之间的相似度大于预设相似度阈值的候选物流兴趣点文本作为相似物流兴趣点文本，得到相似物流兴趣点文本集合。其中，可以利用文本相似度算法确定上述物流兴趣点文本与上述候选物流兴趣点文本集合中每个候选物流兴趣点文本之间的文本相似度。上述文本相似度算法可以包括但不限于以下至少一项：余弦相似度算法、TF-IDF(term frequency-inverse document frequency，词频-逆文档频率)算法等。
步骤309，对相似物流兴趣点文本集合中每个相似物流兴趣点文本对应的标签打分，得到标签得分集合。
在一些实施例中，上述执行主体可以将上述相似物流兴趣点文本对应的标签的权重值作为标签得分。
在一些实施例的一些可选的实现方式中，上述执行主体可以将上述相似物流兴趣点文本与上述物流兴趣点文本之间的相似度的数值确定为上述相似物流兴趣点文本对应的标签得分。
步骤310，根据相似物流兴趣点文本集合和标签得分集合，确定相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与物流兴趣点文本对应的标签。
在一些实施例中，上述执行主体可以根据上述相似物流兴趣点文本集合和上述标签得分集合，确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与上述物流兴趣点文本对应的标签。
在一些实施例的一些可选的实现方式中，上述执行主体根据上述相似物流兴趣点文本集合和上述标签得分集合，确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与上 述物流兴趣点文本对应的标签，可以包括以下步骤：
第一步，将在上述相似物流兴趣点文本集合中对应的相似物流兴趣点文本最多的标签确定为第一标签。
第二步，将上述标签得分集合中最大的标签得分对应的标签确定为第二标签。
第三步，响应于确定上述第一标签与上述第二标签相同，将上述第一标签确定为与上述物流兴趣点文本对应的标签。
作为示例，参考图4，首先，可以将在上述相似物流兴趣点文本集合401中对应的相似物流兴趣点文本最多的标签确定为第一标签402。然后，将上述标签得分集合403中最大的标签得分对应的标签确定为第二标签404。最后，响应于确定上述第一标签402与上述第二标签404相同，将上述第一标签402确定为与上述物流兴趣点文本405对应的标签。
可选的，上述执行主体根据上述相似物流兴趣点文本集合和上述标签得分集合，确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与上述物流兴趣点文本对应的标签，还可以包括以下步骤：
响应于确定上述第一标签与上述第二标签不相同，确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与上述物流兴趣点文本对应的标签。
由此，可以在物流兴趣点文本中不包括物流特征词、目标区域信息和道路信息时，通过该物流兴趣点文本所表征的物流兴趣点附近的已标注的物流兴趣点确定该物流兴趣点文本对应的标签。这种处理方式符合地理学第一定律—空间相关性，即地物之间的相关性与距离有关，一般来说，距离越近，地物间相关性越大，距离越远，地物间相异性越大。
步骤311，响应于确定相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与物流兴趣点文本对应的标签或者物流兴趣点文本中包括表征空间属性的词语，将物流兴趣点文本输入预先训练的标签分类器中，得到物流兴趣点文本所对应的标签。
在一些实施例中，上述执行主体可以响应于确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与上述物流兴趣点文本对应的标签或者上述物流兴趣点文本中包括表征空间属性的词语，将上述物流兴趣点文本输入预先训练的标签分类器中，得到上述物流兴趣点文本所对应的标签。其中，上述标签分类器可以包括但不限于以下至少一项：CNN(Convolutional Neural Networks，卷积神经网络)和RNN(Recurrent Neural Network，循环神经网络)。
由此，可以对于经过之前的步骤仍未确定对应标签的物流兴趣点文本，通过标签分类器确定对应的标签。进一步提升了物流兴趣点文本和物流兴趣点信息的标注率。
且可以参考图5，图5是根据本公开的物流兴趣点信息生成方法的一些实施例的整体示意图。在图5中，首先可以对物流兴趣点信息进行特征词提取处理，若物流兴趣点信息中包括空间属性词语，则可以将物流兴趣点信息直接输入文本分类模型，以得到输出的标签。否则，根据提取出的物流特征词确定标签。若仍无法确定标签，则通过物流兴趣点周边的兴趣点来共同确定物流兴趣点信息对应的标签。若通过物流兴趣点周边的兴趣点仍无法确定物流兴趣点信息对应的标签，则将物流兴趣点信息输入文本分类模型，以得到输出的标签。
从图3中可以看出，与图2对应的一些实施例的描述相比，图3对应的一些实施例中的物流兴趣点信息生成方法的流程300体现了对于无法通过物流特征词识别确定标签的物流兴趣点文本的能进一步处理。通过识别目标区域信息和道路信息、临近的物流兴趣点的物流兴趣点文本以及标签分类器，层层递进的对物流兴趣点文本进行标注。从而，在一定程度上进一步的提高了物流兴趣点信息的标注率。
参考图6，作为对上述各图所示方法的实现，本公开提供了一种物流兴趣点信息生成装置的一些实施例，这些装置实施例与图2所示的那些方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图6所示，一些实施例的物流兴趣点信息生成装置600包括：获取单元601，识别单元602和生成单元603。其中，获取单元601， 被配置成获取待标注的物流兴趣点信息，其中，上述物流兴趣点信息包括物流兴趣点文本。识别单元602，被配置成根据物流特征词信息集合，识别上述物流兴趣点文本中包括的物流特征词和上述物流特征词在上述物流兴趣点文本中的位置，得到物流特征词识别信息集合，其中，上述物流特征词识别信息集合中的物流特征词识别信息包括物流特征词和位置信息，上述物流特征词信息集合中的物流特征词信息包括物流特征词。生成单元603，被配置成根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息所对应的标签。
在一些实施例的可选实现方式中，上述物流兴趣点信息生成装置还包括第一输入单元，被配置成响应于确定上述物流兴趣点文本中包括表征空间属性的词语，将上述物流兴趣点文本输入预先训练的标签分类器中，得到上述物流兴趣点文本所对应的标签。
在一些实施例的可选实现方式中，上述物流兴趣点信息生成装置还包括目标区域信息识别单元和第一生成单元。其中，目标区域信息识别单元，被配置成响应于确定上述物流特征词识别信息集合为空，识别上述物流兴趣点文本中是否包括目标区域信息。第一生成单元，被配置成响应于识别出上述物流兴趣点文本中包括目标区域信息，根据所识别出的目标区域信息，生成上述物流兴趣点信息所对应的标签。
在一些实施例的可选实现方式中，上述物流兴趣点信息生成装置还包括道路信息识别单元和第二生成单元。其中，道路信息识别单元，被配置成响应于识别出上述物流兴趣点文本中不包括目标区域信息，识别上述物流兴趣点文本中是否包括道路信息。第二生成单元，被配置成响应于识别出上述物流兴趣点文本中包括道路信息，根据所识别出的道路信息，生成上述物流兴趣点信息所对应的标签。
在一些实施例的可选实现方式中，上述物流兴趣点信息还包括物流兴趣点坐标；以及上述物流兴趣点信息生成装置还包括：查找单元，打分单元和标签确定单元。其中，查找单元，被配置成响应于识别出上述物流兴趣点文本中不包括道路信息，根据上述物流兴趣点坐标，查找上述物流兴趣点文本的相似物流兴趣点文本，得到相似物流兴趣 点文本集合。打分单元，被配置成对上述相似物流兴趣点文本集合中每个相似物流兴趣点文本对应的标签打分，得到标签得分集合。标签确定单元，被配置成根据上述相似物流兴趣点文本集合和上述标签得分集合，确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与上述物流兴趣点文本对应的标签。
在一些实施例的可选实现方式中，上述物流兴趣点信息生成装置还包括第二输入单元，被配置成响应于确定上述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与上述物流兴趣点文本对应的标签或者上述物流兴趣点文本中包括表征空间属性的词语，将上述物流兴趣点文本输入预先训练的标签分类器中，得到上述物流兴趣点文本所对应的标签。
在一些实施例的可选实现方式中，上述查找单元包括候选物流兴趣点文本确定子单元和选择子单元。其中，候选物流兴趣点文本确定子单元，被配置成将满足预设条件的已标注的物流兴趣点信息中包括的物流兴趣点文本确定为候选物流兴趣点文本，得到候选物流兴趣点文本集合，其中，上述预设条件是已标注的物流兴趣点信息中包括的物流兴趣点坐标与上述物流兴趣点坐标之间的距离值小于预设距离值。选择子单元，被配置成从上述候选物流兴趣点文本集合中选择出与上述物流兴趣点文本之间的相似度大于预设相似度阈值的候选物流兴趣点文本作为相似物流兴趣点文本，得到相似物流兴趣点文本集合。
在一些实施例的可选实现方式中，上述打分单元，被配置成将上述相似物流兴趣点文本与上述物流兴趣点文本之间的相似度的数值确定为上述相似物流兴趣点文本对应的标签得分。
在一些实施例的可选实现方式中，上述标签确定单元，被配置成将在上述相似物流兴趣点文本集合中对应的相似物流兴趣点文本最多的标签确定为第一标签；将上述标签得分集合中最大的标签得分对应的标签确定为第二标签；响应于确定上述第一标签与上述第二标签相同，将上述第一标签确定为与上述物流兴趣点文本对应的标签。
在一些实施例的可选实现方式中，上述标签确定单元，被更配置成：响应于确定上述第一标签与上述第二标签不相同，确定上述相似 物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与上述物流兴趣点文本对应的标签。
在一些实施例的可选实现方式中，上述物流特征词信息集合中的物流特征词信息还包括权重值；以及上述生成单元包括物流特征词评分值确定子单元和标签确定子单元。其中，物流特征词评分值确定子单元被配置成根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词对应的权重值和上述物流特征词识别信息包括的位置信息，确定上述物流特征词的物流特征词评分值，得到物流特征词评分值集合。标签确定子单元，被配置成将上述物流特征词评分值集合中最大的物流特征词评分值对应的物流特征词确定为上述物流兴趣点信息所对应的标签。
可以理解的是，该装置600中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置600及其中包含的单元，在此不再赘述。
下面参考图7，其示出了适于用来实现本公开的一些实施例的电子设备700的结构示意图。图7示出的电子设备仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，其可以根据存储在只读存储器(ROM)702中的程序或者从存储装置708加载到随机访问存储器(RAM)703中的程序而执行各种适当的动作和处理。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。
通常，以下装置可以连接至I/O接口705：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置706；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置707；以及通信装置709。通信装置709可以允许电子设备700与其他设备 进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图7中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的一些实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的一些实施例中，该计算机程序可以通过通信装置709从网络上被下载和安装，或者从存储装置708被安装，或者从ROM 702被安装。在该计算机程序被处理装置701执行时，执行本公开的一些实施例的方法中限定的上述功能。
需要说明的是，本公开的一些实施例中记载的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的一些实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的一些实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以 用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取待标注的物流兴趣点信息，其中，上述物流兴趣点信息包括物流兴趣点文本；根据物流特征词信息集合，识别上述物流兴趣点文本中包括的物流特征词和上述物流特征词在上述物流兴趣点文本中的位置，得到物流特征词识别信息集合，其中，上述物流特征词识别信息集合中的物流特征词识别信息包括物流特征词和位置信息，上述物流特征词信息集合中的物流特征词信息包括物流特征词；根据上述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成上述物流兴趣点信息所对应的标签。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的一些实施例的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含至少一个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的一些实施例中的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元，识别单元和生成单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，识别单元还可以被描述为“识别物流特征词和位置的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。

Claims (14)

  1. 一种物流兴趣点信息生成方法，包括：
    获取待标注的物流兴趣点信息，其中，所述物流兴趣点信息包括物流兴趣点文本；
    根据物流特征词信息集合，识别所述物流兴趣点文本中包括的物流特征词和所述物流特征词在所述物流兴趣点文本中的位置，得到物流特征词识别信息集合，其中，所述物流特征词识别信息集合中的物流特征词识别信息包括物流特征词和位置信息，所述物流特征词信息集合中的物流特征词信息包括物流特征词；
    根据所述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成所述物流兴趣点信息所对应的标签。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    响应于确定所述物流兴趣点文本中包括表征空间属性的词语，将所述物流兴趣点文本输入预先训练的标签分类器中，得到所述物流兴趣点文本所对应的标签。
  3. 根据权利要求1或2所述的方法，其中，所述方法还包括：
    响应于确定所述物流特征词识别信息集合为空，识别所述物流兴趣点文本中是否包括目标区域信息；
    响应于识别出所述物流兴趣点文本中包括目标区域信息，根据所识别出的目标区域信息，生成所述物流兴趣点信息所对应的标签。
  4. 根据权利要求3所述的方法，其中，所述方法还包括：
    响应于识别出所述物流兴趣点文本中不包括目标区域信息，识别所述物流兴趣点文本中是否包括道路信息；
    响应于识别出所述物流兴趣点文本中包括道路信息，根据所识别出的道路信息，生成所述物流兴趣点信息所对应的标签。
  5. 根据权利要求4所述的方法，其中，所述物流兴趣点信息还包括物流兴趣点坐标；以及
    所述方法还包括：
    响应于识别出所述物流兴趣点文本中不包括道路信息，根据所述物流兴趣点坐标，查找所述物流兴趣点文本的相似物流兴趣点文本，得到相似物流兴趣点文本集合；
    对所述相似物流兴趣点文本集合中每个相似物流兴趣点文本对应的标签打分，得到标签得分集合；
    根据所述相似物流兴趣点文本集合和所述标签得分集合，确定所述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与所述物流兴趣点文本对应的标签。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：
    响应于确定所述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与所述物流兴趣点文本对应的标签，将所述物流兴趣点文本输入预先训练的标签分类器中，得到所述物流兴趣点文本所对应的标签。
  7. 根据权利要求5或6所述的方法，其中，所述根据所述物流兴趣点坐标，查找所述物流兴趣点文本的相似物流兴趣点文本，得到相似物流兴趣点文本集合，包括：
    将满足预设条件的已标注的物流兴趣点信息中包括的物流兴趣点文本确定为候选物流兴趣点文本，得到候选物流兴趣点文本集合，其中，所述预设条件是已标注的物流兴趣点信息中包括的物流兴趣点坐标与所述物流兴趣点坐标之间的距离值小于预设距离值；
    从所述候选物流兴趣点文本集合中选择出与所述物流兴趣点文本之间的相似度大于预设相似度阈值的候选物流兴趣点文本作为相似物流兴趣点文本，得到相似物流兴趣点文本集合。
  8. 根据权利要求7所述的方法，其中，所述对所述相似物流兴趣 点文本集合中每个相似物流兴趣点文本对应的标签打分，得到标签得分集合，包括：
    将所述相似物流兴趣点文本与所述物流兴趣点文本之间的相似度的数值确定为所述相似物流兴趣点文本对应的标签得分。
  9. 根据权利要求5-8之一所述的方法，其中，所述根据所述相似物流兴趣点文本集合和所述标签得分集合，确定所述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与所述物流兴趣点文本对应的标签，包括：
    将在所述相似物流兴趣点文本集合中对应的相似物流兴趣点文本最多的标签确定为第一标签；
    将所述标签得分集合中最大的标签得分对应的标签确定为第二标签；
    响应于确定所述第一标签与所述第二标签相同，将所述第一标签确定为与所述物流兴趣点文本对应的标签。
  10. 根据权利要求9所述的方法，其中，所述根据所述相似物流兴趣点文本集合和所述标签得分集合，确定所述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中是否存在与所述物流兴趣点文本对应的标签，还包括：
    响应于确定所述第一标签与所述第二标签不相同，确定所述相似物流兴趣点文本集合中各个相似物流兴趣点文本对应的标签中不存在与所述物流兴趣点文本对应的标签。
  11. 根据权利要求1-10之一所述的方法，其中，所述物流特征词信息集合中的物流特征词信息还包括权重值；以及
    所述根据所述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成所述物流兴趣点信息所对应的标签，包括：
    根据所述物流特征词识别信息集合中每个物流特征词识别信息包 括的物流特征词对应的权重值和所述物流特征词识别信息包括的位置信息，确定所述物流特征词的物流特征词评分值，得到物流特征词评分值集合；
    将所述物流特征词评分值集合中最大的物流特征词评分值对应的物流特征词确定为所述物流兴趣点信息所对应的标签。
  12. 一种物流兴趣点信息生成装置，包括：
    获取单元，被配置成获取待标注的物流兴趣点信息，其中，所述物流兴趣点信息包括物流兴趣点文本；
    识别单元，被配置成根据物流特征词信息集合，识别所述物流兴趣点文本中包括的物流特征词和所述物流特征词在所述物流兴趣点文本中的位置，得到物流特征词识别信息集合，其中，所述物流特征词识别信息集合中的物流特征词识别信息包括物流特征词和位置信息，所述物流特征词信息集合中的物流特征词信息包括物流特征词；
    生成单元，被配置成根据所述物流特征词识别信息集合中每个物流特征词识别信息包括的物流特征词和位置信息，生成所述物流兴趣点信息所对应的标签。
  13. 一种电子设备，包括：
    至少一个处理器；
    存储装置，其上存储有至少一个程序，
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-11中任一所述的方法。
  14. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-11中任一所述的方法。
PCT/CN2023/070934 2022-05-26 2023-01-06 物流兴趣点信息生成方法、装置、设备和计算机可读介质 WO2023226448A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210581210.9A CN114925680A (zh) 2022-05-26 2022-05-26 物流兴趣点信息生成方法、装置、设备和计算机可读介质
CN202210581210.9 2022-05-26

Publications (1)

Publication Number Publication Date
WO2023226448A1 true WO2023226448A1 (zh) 2023-11-30

Family

ID=82810320

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/070934 WO2023226448A1 (zh) 2022-05-26 2023-01-06 物流兴趣点信息生成方法、装置、设备和计算机可读介质

Country Status (2)

Country Link
CN (1) CN114925680A (zh)
WO (1) WO2023226448A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114925680A (zh) * 2022-05-26 2022-08-19 北京京东振世信息技术有限公司 物流兴趣点信息生成方法、装置、设备和计算机可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110674423A (zh) * 2019-09-23 2020-01-10 拉扎斯网络科技（上海）有限公司 一种地址定位的方法、装置、可读存储介质和电子设备
US20200081908A1 (en) * 2018-09-10 2020-03-12 Baidu Online Network Technology (Beijing) Co., Ltd. Internet text mining-based method and apparatus for judging validity of point of interest
CN112507221A (zh) * 2020-03-25 2021-03-16 沈树新 物流信息推荐方法及物流配送系统
CN113806627A (zh) * 2021-03-12 2021-12-17 京东科技控股股份有限公司 兴趣点的类型识别方法、装置、计算机设备及存储介质
CN114925680A (zh) * 2022-05-26 2022-08-19 北京京东振世信息技术有限公司 物流兴趣点信息生成方法、装置、设备和计算机可读介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110832476A (zh) * 2017-07-24 2020-02-21 北京嘀嘀无限科技发展有限公司 用于为按需服务提供信息的系统和方法
CN108491387B (zh) * 2018-03-20 2022-04-22 百度在线网络技术（北京）有限公司 用于输出信息的方法和装置
CN112380849B (zh) * 2020-11-20 2024-05-28 北京百度网讯科技有限公司 生成兴趣点提取模型和提取兴趣点的方法和装置
CN112487120A (zh) * 2020-11-30 2021-03-12 上海寻梦信息技术有限公司 收件地址归类方法、装置、设备以及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200081908A1 (en) * 2018-09-10 2020-03-12 Baidu Online Network Technology (Beijing) Co., Ltd. Internet text mining-based method and apparatus for judging validity of point of interest
CN110674423A (zh) * 2019-09-23 2020-01-10 拉扎斯网络科技（上海）有限公司 一种地址定位的方法、装置、可读存储介质和电子设备
CN112507221A (zh) * 2020-03-25 2021-03-16 沈树新 物流信息推荐方法及物流配送系统
CN113806627A (zh) * 2021-03-12 2021-12-17 京东科技控股股份有限公司 兴趣点的类型识别方法、装置、计算机设备及存储介质
CN114925680A (zh) * 2022-05-26 2022-08-19 北京京东振世信息技术有限公司 物流兴趣点信息生成方法、装置、设备和计算机可读介质

Also Published As

Publication number Publication date
CN114925680A (zh) 2022-08-19

Similar Documents

Publication Publication Date Title
US20200326197A1 (en) Method, apparatus, computer device and storage medium for determining poi alias
WO2020156389A1 (zh) 信息推送方法和装置
JP4950508B2 (ja) 施設情報管理システム、施設情報管理装置、施設情報管理方法および施設情報管理プログラム
CN109508361B (zh) 用于输出信息的方法和装置
US20230049839A1 (en) Question Answering Method for Query Information, and Related Apparatus
WO2021259205A1 (zh) 一种文本序列生成方法、装置、设备和介质
WO2023103653A1 (zh) 键值匹配方法、装置、可读介质及电子设备
CN117290561B (zh) 业务状态信息反馈方法、装置、设备和计算机可读介质
CN113254716B (zh) 视频片段检索方法、装置、电子设备和可读存储介质
WO2023226448A1 (zh) 物流兴趣点信息生成方法、装置、设备和计算机可读介质
CN112699656B (zh) 一种广告标题重写方法、装置、设备及储存介质
US20210004406A1 (en) Method and apparatus for storing media files and for retrieving media files
CN110765280A (zh) 地址识别方法和装置
CN111403011B (zh) 挂号科室推送方法、装置、系统、电子设备及存储介质
CN110990651B (zh) 地址数据处理方法、装置、电子设备及计算机可读介质
WO2023016111A1 (zh) 键值匹配方法、装置、可读介质及电子设备
CN114708545A (zh) 基于图像的对象侦测方法、装置、设备和存储介质
CN112861474B (zh) 一种信息标注方法、装置、设备及计算机可读存储介质
WO2023226819A1 (zh) 数据匹配方法、装置、可读介质及电子设备
US9691106B2 (en) Location based friend finding
CN110020150B (zh) 信息推荐方法及装置
CN110895587A (zh) 用于确定目标用户的方法和装置
CN113722580A (zh) 地址信息处理方法、装置、电子设备和计算机可读介质
CN117171433A (zh) 物流信息的获取方法和装置
WO2022100401A1 (zh) 基于图像识别的价格信息处理方法、装置、设备和介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23810525

Country of ref document: EP

Kind code of ref document: A1