鑒於上述問題，提出了本發明實施例以便提供一種克服上述問題或者至少部分地解決上述問題的一種物流對象配送資訊的獲取方法、一種物流對象配送資訊的獲取裝置和一種物流對象配送資訊的獲取系統。
為了解決上述問題，本發明實施例公開了一種物流對象配送資訊的獲取方法，包括：
接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊；
依據所述通信連接資訊與所述接收方終端建立通信；
在通信過程中接收所述接收方終端的通信資訊；
依據所述通信資訊確定所述物流對象的配送資訊；
將所述配送資訊發送至所述配送方終端。
可選地，所述通信資訊為語音資訊，所述依據所述通信資訊確定所述物流對象的配送資訊的步驟包括：
將所述語音資訊轉換為文件資訊；
對所述文件資訊進行語義分析，得到所述物流對象的配送資訊。
可選地，所述對所述文件資訊進行語義分析，得到所述物流對象的配送資訊的步驟包括：
對所述文件資訊進行斷句處理，得到至少一個語句；
對所述至少一個語句進行分詞，得到各個語句的分詞集合；
對所述分詞集合進行過濾，得到各個語句的至少一個關鍵詞；
依據所述關鍵詞在預置的關鍵詞-語義資訊庫中進行匹配，得到各個語句的核心意圖；
依據各個語句的核心意圖確定所述物流對象的配送資訊。
可選地，所述依據各個語句的核心意圖確定所述物流對象的配送資訊的步驟包括：
對各個語句的核心意圖進行分類，得到與配送資訊相關的核心意圖分類；
依據預置的意圖等級權重表，獲取所述核心意圖分類中每個核心意圖的權重；
依據所述核心意圖分類中每個核心意圖的權重進行意圖仲裁確定目標意圖；
依據預置的意圖-配送資訊對照表，獲取所述目標意圖對應的配送資訊。
可選地，所述對所述分詞集合進行過濾，得到各個語句的至少一個關鍵詞的步驟包括：
依據預置詞性表對所述分詞集合進行詞性過濾；
及/或，
依據預置詞頻表對所述分詞集合進行詞頻過濾；
及/或，
依據預置停用詞詞表對所述分詞集合進行停用詞過濾。
可選地，所述方法還包括：
依據所述配送資訊，獲取與所述配送資訊對應的反應文件資訊；
將所述反應文件資訊轉換為反應語音；
將所述反應語音發送至所述接收方終端。
可選地，在所述依據所述通信連接資訊與所述接收方終端建立通信的步驟之前，還包括：
獲取接收方的歷史行為資料；
依據所述歷史行為資料確定是否與所述接收方終端建立通信。
可選地，所述歷史行為資料封包括接收方地理位置資訊、接收方歷史收件行為資料、接收方肖像、與接收方通信的頻率以及接收方通信的情緒反應資料中的至少一項。
為了解決上述問題，本發明實施例公開了一種物流對象配送資訊的獲取方法，包括：
獲取至少一個物流對象的物流資訊，所述物流資訊包括所述物流對象關聯的接收方的接收方終端的通信連接資訊；
依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求；
將所述通信請求發送至伺服器，所述伺服器用於依據所述通信請求中的通信連接資訊建立與所述至少一個物流對象關聯的接收方終端的通信，以及，依據通信過程中的通信資訊確定所述至少一個物流對象的配送資訊；
接收所述伺服器發送的所述至少一個物流對象的配送資訊。
可選地，所述獲取至少一個物流對象的物流資訊的步驟包括：
獲取預設時間段內待配送的物流對象的物流對象標識；
將所述物流對象標識添加至待配送列表中；
獲取所述待配送列表中物流對象標識關聯的接收方資訊，所述接收方資訊包括接收方終端的通信連接資訊。
可選地，所述依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求的步驟包括：
檢測是否接收到針對所述待配送列表中所述物流對象標識對應的通信連接資訊的通信請求；
若是，則依據所述待配送列表中物流對象標識關聯的通信連接資訊產生通信請求。
可選地，所述方法還包括：
展示所述物流對象的配送資訊。
為了解決上述問題，本發明實施例公開了一種物流對象配送資訊的獲取裝置，包括：
通信請求接收模組，用於接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊；
通信建立模組，用於依據所述通信連接資訊與所述接收方終端建立通信；
通信資訊接收模組，用於在通信過程中接收所述接收方終端的通信資訊；
配送資訊確定模組，用於依據所述通信資訊確定所述物流對象的配送資訊；
配送資訊發送模組，用於將所述配送資訊發送至所述配送方終端。
可選地，所述通信資訊為語音資訊，所述配送資訊確定模組包括：
文件資訊轉換子模組，用於將所述語音資訊轉換為文件資訊；
語義分析子模組，用於對所述文件資訊進行語義分析，得到所述物流對象的配送資訊。
可選地，所述語義分析子模組包括：
斷句單元，用於對所述文件資訊進行斷句處理，得到至少一個語句；
分詞單元，用於對所述至少一個語句進行分詞，得到各個語句的分詞集合；
過濾單元，用於對所述分詞集合進行過濾，得到各個語句的至少一個關鍵詞；
核心意圖匹配單元，用於依據所述關鍵詞在預置的關鍵詞-語義資訊庫中進行匹配，得到各個語句的核心意圖；
配送資訊確定單元，用於依據各個語句的核心意圖確定所述物流對象的配送資訊。
可選地，所述配送資訊確定單元包括：
分類子單元，用於對各個語句的核心意圖進行分類，得到與配送資訊相關的核心意圖分類；
權重獲取子單元，用於依據預置的意圖等級權重表，獲取所述核心意圖分類中每個核心意圖的權重；
目標意圖確定子單元，用於依據所述核心意圖分類中每個核心意圖的權重進行意圖仲裁確定目標意圖；
配送資訊確定子單元，用於依據預置的意圖-配送資訊對照表，獲取所述目標意圖對應的配送資訊。
可選地，所述過濾單元包括：
詞性過濾子單元，用於依據預置詞性表對所述分詞集合進行詞性過濾；
及/或，
詞頻過濾子單元，用於依據預置詞頻表對所述分詞集合進行詞頻過濾；
及/或，
停用詞過濾子單元，用於依據預置停用詞詞表對所述分詞集合進行停用詞過濾。
可選地，所述裝置還包括：
反應文件資訊獲取模組，用於依據所述配送資訊，獲取與所述配送資訊對應的反應文件資訊；
語音轉換模組，用於將所述反應文件資訊轉換為反應語音；
反應語音發送模組，用於將所述反應語音發送至所述接收方終端。
可選地，還包括：
行為資料獲取模組，用於獲取接收方的歷史行為資料；
建立通信確定模組，用於依據所述歷史行為資料確定是否與所述接收方終端建立通信。
可選地，所述歷史行為資料封包括接收方地理位置資訊、接收方歷史收件行為資料、接收方肖像、與接收方通信的頻率以及接收方通信的情緒反應資料中的至少一項。
為了解決上述問題，本發明實施例公開了一種物流對象配送資訊的獲取裝置，包括：
物流資訊獲取模組，用於獲取至少一個物流對象的物流資訊，所述物流資訊包括所述物流對象關聯的接收方的接收方終端的通信連接資訊；
通信請求產生模組，用於依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求；
通信請求發送模組，用於將所述通信請求發送至伺服器，所述伺服器用於依據所述通信請求中的通信連接資訊建立與所述至少一個物流對象關聯的接收方終端的通信，以及，根據通信過程中的通信資訊確定所述至少一個物流對象的配送資訊；
配送資訊接收模組，用於接收所述伺服器發送的所述至少一個物流對象的配送資訊。
可選地，所述物流資訊獲取模組包括：
物流對象標識獲取子模組，用於獲取預設時間段內待配送的物流對象的物流對象標識；
待配送列表產生子模組，用於將所述物流對象標識添加至待配送列表中；
通信連接資訊獲取子模組，用於獲取所述待配送列表中物流對象標識關聯的接收方資訊，所述接收方資訊包括接收方終端的通信連接資訊。
可選地，所述通信請求產生模組包括：
操作檢測子模組，用於檢測是否接收到針對所述待配送列表中所述物流對象標識對應的通信連接資訊的通信請求；
通信請求產生子模組，用於依據所述待配送列表中物流對象標識關聯的通信連接資訊產生通信請求。
可選地，所述裝置還包括：
配送資訊展示模組，用於展示所述物流對象的配送資訊。
為了解決上述問題，本發明實施例公開了一種物流對象配送資訊的獲取系統，包括配送方終端和伺服器，
所述伺服器包括：
通信請求接收模組，用於接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊；
通信建立模組，用於依據所述通信連接資訊與所述接收方終端建立通信；
通信資訊接收模組，用於在通信過程中接收所述接收方終端的通信資訊；
配送資訊確定模組，用於依據所述通信資訊確定所述物流對象的配送資訊；
配送資訊發送模組，用於將所述配送資訊發送至所述配送方終端；
所述配送方終端包括：
物流資訊獲取模組，用於獲取至少一個物流對象的物流資訊，所述物流資訊包括所述物流對象關聯的接收方的接收方終端的通信連接資訊；
通信請求產生模組，用於依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求；
通信請求發送模組，用於將所述通信請求發送至伺服器，所述伺服器用於依據所述通信請求中的通信連接資訊建立與所述至少一個物流對象關聯的接收方終端的通信，以及，根據通信過程中的通信資訊確定所述至少一個物流對象的配送資訊；
配送資訊接收模組，用於接收所述伺服器發送的所述至少一個物流對象的配送資訊。
為了解決上述問題，本發明實施例公開了一種裝置，包括：一個或多個處理器；和其上儲存有指令的一個或多個機器可讀介質，當由所述一個或多個處理器執行時，使得所述裝置執行本發明實施例所述的一個或多個的方法。
為了解決上述問題，本發明實施例公開了一個或多個機器可讀介質，其上儲存有指令，當由一個或多個處理器執行時，使得裝置執行本發明實施例所述的一個或多個的方法。
本發明實施例包括以下優點：
本發明實施例中，配送方終端可以將針對待配送物流對象關聯的接收方終端的通信請求發送至伺服器，由伺服器與各個物流對象關聯的接收方終端進行通信，並通過通信資訊確定配送資訊後發送至配送方終端，配送方無需逐個與物流對象關聯的接收方終端進行通信以確定物流對象的配送資訊，實現了批量獲取物流對象的配送資訊，一方面降低了配送方與接收方的溝通時間成本，提高了物流對象的配送效率；另一方面，由機器代替配送方與接收方通信，能夠在派件數量大、溝通時間長和溝通品質的三重壓力下實現高履約配送水平，提高了接收方體感。
本發明實施例中，對通信中的收件終端的語音資訊識別出的多個核心意圖進行分類，並根據與配送資訊相關的核心意圖分類中各個核心意圖的意圖等級權重進行多意圖仲裁以確定目標意圖，解決了傳統自然語言理解中長句多意圖解析的問題，能夠準確地從長語音資訊中識別接收方的意圖。
本發明實施例中，可以根據接收方的目標意圖產生反應語音資訊自動回復接收方終端，提高了與接收方的交互，進一步提高了接收方的體感。
本發明實施例中，可以根據接收方的歷史行為資料確定是否與接收方終端建立通信，避免了對接收方的無必要干擾。
本發明實施例中，配送方終端在向伺服器發送針對至少一個物流對象關聯的接收方終端的通信請求後，可以從伺服器接收到至少一個物流對象的配送資訊並展示，使得配送方可以根據配送資訊對物流對象進行配送，避免了未經消費者允許將快遞放在代收點而不送貨上門的問題，提高了消費者體感。
In view of the above problems, embodiments of the present invention are proposed to provide a method for acquiring logistics object distribution information, a device for acquiring logistics object distribution information, and a system for acquiring logistics object distribution information that overcome the above problems or at least partially solve the above problems .
In order to solve the above problems, an embodiment of the present invention discloses a method for acquiring distribution information of logistics objects, including:
Receiving a communication request sent by a terminal of a delivery party and directed to a receiver terminal associated with at least one logistics object, where the communication request includes communication connection information of the receiver terminal;
Establish communication with the receiver terminal according to the communication connection information;
Receiving communication information of the receiver terminal during communication;
Determine the distribution information of the logistics object based on the communication information;
Sending the delivery information to the delivery terminal.
Optionally, the communication information is voice information, and the step of determining the distribution information of the logistics object according to the communication information includes:
Convert the voice information into document information;
Perform semantic analysis on the document information to obtain distribution information of the logistics object.
Optionally, the step of performing semantic analysis on the document information to obtain the distribution information of the logistics object includes:
Perform sentence segmentation processing on the document information to obtain at least one sentence;
Performing word segmentation on the at least one sentence to obtain a word segmentation set for each sentence;
Filtering the word segmentation set to obtain at least one keyword of each sentence;
Match the keywords in the preset keyword-semantic information database according to the keywords to obtain the core intent of each sentence;
The distribution information of the logistics object is determined according to the core intention of each sentence.
Optionally, the step of determining the distribution information of the logistics object according to the core intention of each sentence includes:
Classify the core intentions of each sentence to get the core intention classification related to the distribution information;
Obtain the weight of each core intent in the core intent classification according to a preset intent level weight table;
In accordance with the weight of each core intention in the core intention classification, conduct intention arbitration to determine the target intention;
According to the preset intent-delivery information comparison table, obtain the delivery information corresponding to the target intent.
Optionally, the step of filtering the word segmentation set to obtain at least one keyword of each sentence includes:
Perform part-of-speech filtering on the participle set according to a preset part-of-speech table;
And/or,
Performing word frequency filtering on the word segmentation set according to a preset word frequency table;
And/or,
Perform stopword filtering on the word segmentation set according to a preset stopword vocabulary.
Optionally, the method further includes:
Obtain response document information corresponding to the distribution information according to the distribution information;
Convert the reaction document information into reaction speech;
Sending the reaction voice to the receiver terminal.
Optionally, before the step of establishing communication with the receiver terminal according to the communication connection information, the method further includes:
Obtain the historical behavior information of the receiver;
Determine whether to establish communication with the recipient terminal based on the historical behavior data.
Optionally, the historical behavior data envelope includes at least one of the receiver's geographic location information, the receiver's historical receipt behavior data, the receiver's portrait, the frequency of communication with the receiver, and the emotional response data communicated by the receiver.
In order to solve the above problems, an embodiment of the present invention discloses a method for acquiring distribution information of logistics objects, including:
Acquiring logistics information of at least one logistics object, the logistics information including communication connection information of a receiver terminal of a receiver associated with the logistics object;
Generating a communication request for the receiver terminal associated with the at least one logistics object according to the communication connection information;
Sending the communication request to a server for establishing communication of the receiver terminal associated with the at least one logistics object according to the communication connection information in the communication request, and according to the communication in the communication process The information determines the distribution information of the at least one logistics object;
Receiving delivery information of the at least one logistics object sent by the server.
Optionally, the step of acquiring logistics information of at least one logistics object includes:
Obtain the logistics object identifier of the logistics object to be delivered within a preset time period;
Add the logistics object identifier to the list to be delivered;
Acquire receiver information associated with the logistics object identifier in the to-be-delivered list, where the receiver information includes communication connection information of the receiver terminal.
Optionally, the step of generating a communication request for the receiver terminal associated with the at least one logistics object according to the communication connection information includes:
Detecting whether a communication request for communication connection information corresponding to the logistics object identifier in the to-be-delivered list is received;
If yes, a communication request is generated according to the communication connection information associated with the logistics object identifier in the to-be-delivered list.
Optionally, the method further includes:
Display the distribution information of the logistics object.
In order to solve the above problems, an embodiment of the present invention discloses a device for acquiring distribution information of logistics objects, including:
A communication request receiving module, configured to receive a communication request sent by a terminal of a delivery party to a receiver terminal associated with at least one logistics object, where the communication request includes communication connection information of the receiver terminal;
A communication establishment module, configured to establish communication with the receiver terminal according to the communication connection information;
The communication information receiving module is used to receive the communication information of the receiver terminal during the communication process;
A distribution information determination module, used to determine the distribution information of the logistics object according to the communication information;
A delivery information sending module is used to send the delivery information to the delivery terminal.
Optionally, the communication information is voice information, and the distribution information determination module includes:
Document information conversion submodule, which is used to convert the voice information into document information;
The semantic analysis submodule is used for semantic analysis of the document information to obtain distribution information of the logistics object.
Optionally, the semantic analysis submodule includes:
A sentence-breaking unit, configured to perform sentence-breaking processing on the document information to obtain at least one sentence;
The word segmentation unit is used to segment the at least one sentence to obtain a word segmentation set of each sentence;
A filtering unit, configured to filter the word segmentation set to obtain at least one keyword of each sentence;
The core intent matching unit is used to match in the preset keyword-semantic information database according to the keywords to obtain the core intent of each sentence;
The distribution information determination unit is used to determine the distribution information of the logistics object according to the core intention of each sentence.
Optionally, the distribution information determination unit includes:
The classification subunit is used to classify the core intent of each sentence to obtain the core intent classification related to the distribution information;
A weight obtaining subunit, configured to obtain the weight of each core intent in the core intent classification according to a preset intent level weight table;
A target intention determination subunit, which is used to perform an intention arbitration to determine the target intention according to the weight of each core intention in the core intention classification;
The delivery information determination subunit is used to obtain delivery information corresponding to the target intent according to a preset intent-delivery information comparison table.
Optionally, the filtering unit includes:
The part-of-speech filtering subunit is used to perform part-of-speech filtering on the word segmentation set according to a preset part-of-speech table;
And/or,
The word frequency filtering subunit is used to filter the word frequency of the word segmentation set according to a preset word frequency table;
And/or,
The stop word filtering subunit is configured to filter stop words on the word segmentation set according to a preset stop word vocabulary.
Optionally, the device further includes:
The response document information acquisition module is used to obtain the response document information corresponding to the distribution information according to the distribution information;
The voice conversion module is used to convert the reaction document information into reaction voice;
The reactive voice sending module is used to send the reactive voice to the receiver terminal.
Optionally, it also includes:
Behavior data acquisition module, used to obtain historical behavior data of the receiver;
The establishment communication determination module is used for determining whether to establish communication with the receiver terminal according to the historical behavior data.
Optionally, the historical behavior data envelope includes at least one of the receiver's geographic location information, the receiver's historical receipt behavior data, the receiver's portrait, the frequency of communication with the receiver, and the emotional response data communicated by the receiver.
In order to solve the above problems, an embodiment of the present invention discloses a device for acquiring distribution information of logistics objects, including:
A logistics information acquisition module, for acquiring logistics information of at least one logistics object, the logistics information including communication connection information of a receiver terminal of a receiver associated with the logistics object;
A communication request generating module, configured to generate a communication request for the receiver terminal associated with the at least one logistics object according to the communication connection information;
A communication request sending module, configured to send the communication request to a server, and the server is used to establish communication of the receiver terminal associated with the at least one logistics object according to the communication connection information in the communication request, And, determine the distribution information of the at least one logistics object according to the communication information in the communication process;
The distribution information receiving module is configured to receive the distribution information of the at least one logistics object sent by the server.
Optionally, the logistics information acquisition module includes:
The logistics object identifier acquisition submodule is used to obtain the logistics object identifier of the logistics object to be distributed within a preset time period;
A sub-module for generating a list to be delivered is used to add the logistics object identifier to the list to be delivered;
The communication connection information obtaining submodule is used to obtain the receiver information associated with the logistics object identifier in the to-be-delivered list, and the receiver information includes the communication connection information of the receiver terminal.
Optionally, the communication request generating module includes:
An operation detection sub-module for detecting whether a communication request for communication connection information corresponding to the logistics object identifier in the to-be-delivered list is received;
The communication request generating submodule is used for generating a communication request according to the communication connection information associated with the logistics object identifier in the to-be-delivered list.
Optionally, the device further includes:
The distribution information display module is used to display the distribution information of the logistics object.
In order to solve the above problems, an embodiment of the present invention discloses a logistics object distribution information acquisition system, including a distribution terminal and a server,
The server includes:
A communication request receiving module, configured to receive a communication request sent by a terminal of a delivery party to a receiver terminal associated with at least one logistics object, where the communication request includes communication connection information of the receiver terminal;
A communication establishment module, configured to establish communication with the receiver terminal according to the communication connection information;
The communication information receiving module is used to receive the communication information of the receiver terminal during the communication process;
A distribution information determination module, used to determine the distribution information of the logistics object according to the communication information;
A distribution information sending module, used to send the distribution information to the terminal of the distribution side;
The distribution terminal includes:
A logistics information acquisition module, for acquiring logistics information of at least one logistics object, the logistics information including communication connection information of a receiver terminal of a receiver associated with the logistics object;
A communication request generating module, configured to generate a communication request for the receiver terminal associated with the at least one logistics object according to the communication connection information;
A communication request sending module, configured to send the communication request to a server, and the server is used to establish communication of the receiver terminal associated with the at least one logistics object according to the communication connection information in the communication request, And, determine the distribution information of the at least one logistics object according to the communication information in the communication process;
The distribution information receiving module is configured to receive the distribution information of the at least one logistics object sent by the server.
In order to solve the above problems, an embodiment of the present invention discloses an apparatus including: one or more processors; and one or more machine-readable media having instructions stored thereon, when executed by the one or more processors When the device is enabled to execute one or more methods described in the embodiments of the present invention.
In order to solve the above problems, the embodiments of the present invention disclose one or more machine-readable media on which instructions are stored, which, when executed by one or more processors, cause the device to execute one or more of the embodiments described in the present invention Methods.
The embodiments of the present invention include the following advantages:
In the embodiment of the present invention, the distributor terminal may send a communication request to the receiver terminal associated with the logistics object to be distributed to the server, and the server communicates with the receiver terminal associated with each logistics object, and the distribution is determined through the communication information After the information is sent to the terminal of the distributor, the distributor does not need to communicate with the receiver terminal associated with the logistics object one by one to determine the distribution information of the logistics object, which achieves batch acquisition of the distribution information of the logistics object, on the one hand, reduces the The cost of communication time improves the delivery efficiency of logistics objects; on the other hand, the machine replaces the delivery side to communicate with the receiver, which can achieve high fulfillment delivery level under the triple pressure of large number of parts, long communication time and communication quality. Receiver body sense.
In the embodiment of the present invention, multiple core intents identified by the voice information of the receiving terminal in communication are classified, and multi-intention arbitration is performed according to the intent level weight of each core intent in the core intent classification related to the distribution information to determine Target intent solves the problem of multi-intention parsing of long sentences in traditional natural language understanding, and can accurately identify the receiver's intent from long voice information.
In the embodiment of the present invention, a response voice information can be automatically generated according to the target intention of the receiver to reply to the terminal of the receiver, which improves the interaction with the receiver and further improves the receiver's body feeling.
In the embodiment of the present invention, it can be determined whether to establish communication with the receiver terminal according to the historical behavior data of the receiver, thereby avoiding unnecessary interference to the receiver.
In the embodiment of the present invention, after the distributor terminal sends a communication request for the receiver terminal associated with at least one logistics object to the server, it can receive and display the distribution information of the at least one logistics object from the server, so that the distributor can The delivery information distributes the logistics objects, avoids the problem of placing the courier at the collection point without the consumer's permission without delivering the goods to the door, and improves the consumer's feeling.
為使本發明的上述目的、特徵和優點能夠更加明顯易懂，下面結合附圖和具體實施方式對本發明作進一步詳細的說明。
參照圖1，示出了本發明的一種物流對象配送資訊的獲取方法實施例1的步驟流程圖，本發明實施例的物流對象配送資訊的獲取方法可以應用於伺服器，具體可以包括如下步驟：
步驟101，接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊。
本發明實施例中，物流對象可以是包裹、快遞、外賣等物流物品，配送方可以是配送物流對象的快遞員、代收點或者驛站的管理員，接收方可以是物流對象的最終收件人或者最終收件人授權代為收件的中間人。物流對象通常由配送方配送到接收方，配送方終端可以是配送方用於管理接收到的物流對象的終端，接收方終端可以是接收方用於通信的終端。
例如，對於驛站管理員，在接收到各個快遞公司快遞員派發的物流對象後，可以通過移動終端掃描物流對象的面單對物流對象進行入庫、分類、獲取物流資訊等操作。驛站管理員通過配送方終端上的應用程式可以獲取需要配送的物流對象的待配送列表，該待配送列表中的物流對象在配送前需要與接收方聯繫以確認是送貨上門還是接收方到站自提。
又例如，在另外一種場景中，快遞員從網點領取需要自己配送的物流對象後，快遞員的配送終端的應用程式可以獲取需要配送的物流對象的待配送列表，該待配送列表中的物流對象在配送前需要與接收方聯繫以確認是送貨上門還是接收方到站自提。
例如，對於電話聯繫接收方，驛站管理員或快遞員可以在待配送列表中觸發“一鍵撥打”按鈕，則配送方終端針對待配送列表中的物流對象關聯的接收方終端產生通信請求，並將該通信請求發送至伺服器，由伺服器與各個接收方終端進行電話聯繫，該通信請求中可以包括接收方終端的通信連接資訊。
在本發明實施例中，如果接收方選擇手機電話聯繫，則通信連接資訊可以是接收方的手機號碼碼或者電話號碼，當然，通信連接資訊還可以是其它帳戶號碼，例如各種即時通信應用程式上接收方註冊的號碼，通信連接資訊還可以是其它以非明文形式顯示接收方終端資訊的標識、或者其它按鍵標識等，以確保接收方的隱私資訊不被洩露，本發明實施例對通信連接資訊的內容和顯示方式不加以限制。
在實際應用中，伺服器可以是與接收方終端連接的、能夠與多個接收方終端進行通信的平臺，例如可以是呼叫平臺，該呼叫平臺可以根據通信請求中的多個接收方終端的通信連接資訊與多個接收方終端進行語音或者文件通信。
步驟102，依據所述通信連接資訊與所述接收方終端建立通信。
在本發明實施例中，伺服器可以與多個接收方終端建立通信，例如，通信連接資訊可以是手機號碼碼或者電話號碼，則可以與多個手機或者固定電話建立語音通信，如果通信連接資訊是各種即時通信應用程式的帳號，則可以通過即時通信應用程式與通信帳號所登錄的接收方終端建立通信，該通信可以是語音通信(電話)或者文件資訊通信(簡訊或者聊天資訊)，本發明實施例對與接收方終端建立通信的方式不加以限制，對與接收方終端通信的方式亦不加以限制。
步驟103，在通信過程中接收所述接收方終端的通信資訊。
具體而言，如果是語音通信，則接收接收方終端的語音資訊，如果是即時應用程式通信，則接收接收方終端的語音資訊或者文件資訊。
步驟104，依據所述通信資訊確定所述物流對象的配送資訊。
本發明實施例中，如果通信資訊為語音資訊則可以將語音資訊轉換為文件資訊，例如通過ASR(自動語音識別技術，Automatic Speech Recognition)技術將語音資訊轉換為文件資訊。在得到文件資訊後，可以通過 NLU(自然語言理解，Natural Language Understanding)技術識別文件資訊中接收方的意圖，從而確定物流對象的配送資訊。
步驟105，將所述配送資訊發送至所述配送方終端。
伺服器在確定物流對象的配送資訊後，可以將通信請求針對的所有物流對象的配送資訊發送至配送方終端，在配送方終端展示物流對象的配送資訊，例如展示每個待配送的物流對象是送貨上門還是接收方到站自提等。
本發明實施例中，配送方終端將針對所有待配送物流對象關聯的接收方終端的通信請求發送至伺服器，通過伺服器與各個物流對象關聯的接收方終端進行通信，並通過通信資訊確定配送資訊後發送至配送方終端，配送方無需逐個與物流對象關聯的接收方終端進行通信以確定物流對象的配送資訊，實現了批量獲取物流對象的配送資訊，一方面降低了配送方的溝通時間成本，提高了物流對象的配送效率；另一方面，由機器代替配送方與接收方通信，能夠在派件數量大、溝通時間長和溝通品質的三重壓力下實現高履約配送水平，提高了接收方的體感。
參照圖2，示出了本發明的一種物流對象配送資訊的獲取方法實施例2的步驟流程圖，本發明實施例的物流對象配送資訊的獲取方法可以應用於伺服器，具體可以包括如下步驟：
步驟201，接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊。
本發明實施例中，可以在配送方終端針對待配送類別中的物流對象關聯的接收方終端產生通信請求，然後將通信請求發送至伺服器，則該伺服器接收到配送方終端發送的通信請求，通信請求中包括物流對象關聯的接收方終端的通信連接資訊，例如手機號碼碼或者固定電話號碼。
步驟202，依據所述通信連接資訊與所述接收方終端建立通信。
伺服器在接收到通信請求後，可以根據通信請求中的通信連接資訊建立與接收方終端的通信。
如圖3所示，以語音通信為示例，通信請求針對四個物流對象關聯的接收方使用者A、使用者B、使用者C和使用者D，則通信請求中包括了使用者A、使用者B、使用者C和使用者D的電話號碼，伺服器在接收到通信請求後，伺服器的外呼平臺根據通信請求中使用者A、使用者B、使用者C和使用者D的電話號碼，同時與使用者A、使用者B、使用者C和使用者D進行電話通信，進行語音交互，無需配送方逐個與使用者A、使用者B、使用者C和使用者D進行通話確定物流對象的配送資訊，大大降低了配送方的溝通時間成本，提高了物流對象的配送效率。
在本發明的一種優選實施例中，在步驟202之前還可以包括：獲取接收方的歷史行為資料；依據所述歷史行為資料確定是否與所述接收方終端建立通信。其中，歷史行為資料封包括接收方地理位置資訊、接收方歷史收件行為資料、接收方肖像、與接收方通信的頻率以及接收方通信的情緒反應資料中的至少一項。
例如，對於上述使用者A，在撥打電話前根據使用者A的歷史收件行為、使用者A的肖像如年齡、工作等來確定使用者A在家的時間來確定撥打電話的時機，或者根據聯繫使用者A的頻率、使用者A過往電話中的情緒反應來評估出使用者的疲勞度以判斷是否要給使用者A撥打電話。
本發明實施例中，可以根據接收方的歷史行為資料確定是否與接收方終端建立通信，既能夠避免了對接收方的無必要干擾，又提高了通信的效率。
步驟203，在通信過程中接收所述接收方終端的通信資訊，所述通信資訊為語音資訊。
本發明實施例中，通信資訊可以為語音資訊，例如與接收方電話通信過程中接收方的語音資訊。通信資訊還可以是文件資訊，例如給多個手機發送簡訊後收到的簡訊資訊或者是即時通信應用程式中接收方回復的文件資訊。
步驟204，將所述語音資訊轉換為文件資訊。
如果通信資訊是語音資訊，則可以通過ASR(自動語音識別技術，Automatic Speech Recognition)技術將語音資訊轉換為文件資訊，如果是文件資訊可以不做處理。
步驟205，對所述文件資訊進行語義分析，得到所述物流對象的配送資訊。
本發明實施例中，步驟205可以包括如下子步驟：
子步驟S11，對所述文件資訊進行斷句處理，得到至少一個語句。
在實際應用中，文件資訊可能比較長，則需要對文件資訊進行斷句，包括段落劃分和語句劃分，例如根據文件資訊中的特徵字符對文件資訊進行斷句，比如根據文件資訊中的句號、逗號、分號、感嘆號、問號、空格等對文件資訊進行斷句處理，得到至少一個語句。
子步驟S12，對所述至少一個語句進行分詞，得到各個語句的分詞集合。
本發明實施例中，可以基於字串匹配的分詞方法、基於理解的分詞方法和基於統計的分詞方法中的至少一種對每個語句做分詞處理。
基於字串匹配的分詞方法又稱為機械分詞方法，是按照一定的策略將待分析的語句中的字串與一個“充分大的”機器詞典中的詞條進行配，若在詞典中找到某個字串，則匹配出一個分詞。
基於理解的分詞方法是通過電腦模擬人對句子的理解，達到識別分詞的效果，基本思想是在分詞的同時進行句法、語義分析，利用句法資訊和語義資訊來處理歧義現象，通常包括三個部分：分詞子系統、句法語義子系統、總控部分。在總控部分的協調下，分詞子系統可以獲得有關詞、句子等的句法和語義資訊來對分詞歧義進行判斷，其模擬了人對句子的理解過程。
基於統計的分詞方法是基於從形式上詞是穩定的字的組合，在上下文中相鄰的字同時出現的次數越多，就越有可能構成一個詞。因此字與字相鄰共現的頻率或機率能夠較好的反映成詞的可信度。可以對語句中相鄰共現的各個字的組合的頻率進行統計，計算兩個字的互現資訊。互現資訊體現了兩個字之間結合關係的緊密程度，當緊密程度高於某一個臨限值時，便可認為此字組可能構成了一個詞。
子步驟S13，對所述分詞集合進行過濾，得到各個語句的至少一個關鍵詞。
本發明實施例是通過對文件資訊進行語義分析確定物流對象的配送資訊，為了提高語義分析的準確性和效率，可以對分詞集合進行過濾以去掉無用的分詞，具體而言，可以依據預置詞性表對所述分詞集合進行詞性過濾；及/或，依據預置詞頻表對所述分詞集合進行詞頻過濾；及/或，依據預置停用詞詞表對所述分詞集合進行停用詞過濾。
詞性表可以是保存了物流場景中不影響語義分析的字詞，例如形容詞、副詞等，詞頻表可以是物流場景中使用頻率較低的字詞，停用詞表可以是物流場景中不使用的字詞。
通過詞頻表和停用詞表，可以針對分詞集合中詞頻較低的字詞和停用字詞做定向的過濾，同時通過詞性表對不影響語義分析的形容詞等進行過濾，使得每個語句得到至少一個關鍵詞。
子步驟S14，依據所述關鍵詞在預置的關鍵詞-語義資訊庫中進行匹配，得到各個語句的核心意圖。
在實際應用中，可以結合物流場景設置關鍵詞-語義資訊庫，如下表1所示：
以上表1是以核心意圖為在家，不在家，自提和費用為示例說明關鍵詞-語義資訊庫，在實際應用中還可以設置關於營業時間等其它關鍵詞-語義資訊庫。
在得到每個語句的關鍵詞後，可以採用關鍵詞在預置的關鍵詞-語義資訊庫進行匹配，得到各個語句的核心意圖。
子步驟S15，依據各個語句的核心意圖確定所述物流對象的配送資訊。
在確定各個語句的核心意圖後，可以根據核心意圖確定物流對象的配送資訊，配送資訊可以是物流對象的配送方式，例如可以是送貨上門或者到站自提。
在本發明的一種優選實施例中，子步驟S15可以包括如下子步驟：
子步驟S15-1，對各個語句的核心意圖進行分類，得到與配送資訊相關的核心意圖分類。
在實際應用中，接收方的每個語句的意圖並非全部與物流對象的配送資訊相關，可以將每個語句的使用者意圖稱為核心意圖，例如在送貨上門的場景中，使用者語句中的在家、不在家、自提是核心意圖，其他的例如費用、營業時間等為非核心意圖，因此可以對各個語句的核心意圖進行分類，得到與配送資訊相關的核心意圖分類。
子步驟S15-2，依據預置的意圖等級權重表，獲取所述核心意圖分類中每個核心意圖的權重。
具體而言，可以通過大量線上真實場景電話錄音對每個核心意圖設置初始權重，然後通過每天進行線上實測，迭代較佳化核心意圖權重建立意圖等級權重表，該意圖等級權重表中記錄了核心意圖及其等級權重，因此可以根據預置的意圖等級權重表獲取每個核心意圖的權重。
子步驟S15-4，依據所述核心意圖分類中每個核心意圖的權重進行意圖仲裁確定目標意圖。
在與接收方終端通信過程中，文件資訊可以包括多個語句，每個語句可以包多個關鍵詞，通過關鍵詞可以匹配到相應的核心意圖，從多個核心意圖中可以確定與配送資訊相關的核心意圖分類，因此需要對核心意圖分類中的核心意圖進行意圖仲裁以確定出目標意圖。
核心意圖分類在配送場景中不僅僅包括與配送資訊相關的核心意圖，還可以包括與自提時間相關的營業時間等分類。
例如，在一次通話中，使用者A的核心意圖分類中包括“不在家”、“在家”和“在家”，“不在家”的權重為10、“在家”的權重為10，則“在家”的權重和為20，大於“不在家”的權重10，則目標意圖為“在家”。
又例如，在一次通話中，使用者A的核心意圖分類包括 “不在家”、“自提”和“營業時間”，“不在家”的權重為5，“自提”的權重為5，“營業時間”的權重為10，則目標意圖為“自提”和“營業時間”。
本發明實施例對語音資訊識別出的多個核心意圖進行分類，並根據與配送資訊相關的核心意圖分類中各個核心意圖的意圖等級權重進行意圖仲裁以確定的目標意圖，解決了傳統自然語言理解中長句多意圖解析的問題，能夠準確地從長語音資訊中識別接收方的意圖。
子步驟S15-5，依據預置的意圖-配送資訊對照表，獲取所述目標意圖對應的配送資訊。
在實際應用中，不同的核心意圖對應不同的配送資訊，如下表2所示：
上述表2中，還可以建立其它目標意圖對應的資訊，例如，目標意圖為營業時間或者費用，則對應的資訊為營業時間資訊和費用資訊。
步驟206，依據所述配送資訊，獲取與所述配送資訊對應的反應文件資訊。
在本發明實施例中，伺服器與接收方終端進行通信，需要與接收方終端進行交互，在獲取配送資訊後，可以對接收方終端進行反應，以提高接收方的體感，具體地，可以獲取預置的與配送資訊對應的反應文件資訊，例如，配送資訊可以是送貨上門，則反應文件可以是“好的，那待會見”，如果配送資訊是到站自提，則反應文件可以是“好的，我們的營業時間是上午九點到晚九點，這個時間內您都可以來自提”，反應文件可以根據配送資訊不同進行不同的設定，本發明實施例對此不加以限制。
步驟207，將所述反應文件資訊轉換為反應語音。
在獲取反應文件資訊後，如果是語音通信，則將反應文件資訊轉換為反應語音，如果是文件通信，則無需轉換。
步驟208，將所述反應語音發送至所述接收方終端。
在語音通信中，伺服器可以將反應語音發送至接收方終端，以提高與接收方的交互提感。
以下結合示例對本發明實施例獲取配送資訊的流程進行說明。
示例一
如圖4所示，在示例一中通過電話通信說明物流對象配送資訊的獲取流程如下：
S1，伺服器接收到接收方配送方終端一鍵撥打請求後發起溝通，伺服器通過機器人建立與多個接收方終端的語音通信；
S2，使用者反應，機器人開場白後，使用者進行反應，伺服器可以接收到接收方終端的使用者的語音資訊；
S3，語音轉文件，伺服器將語音資訊轉為文件資訊；
S4，語意識別，對文件資訊中的語意進行識別，確定語音資訊中的意圖；
S5，語意匹配，根據從文件資訊中識別出的語意，匹配對應的反應文件；
S6，智慧反應，將反應文件轉換為語音後發送至接收方終端以進行使用者反應；
S7，結束通話。
S8，將配送資訊發送至接收方終端。
其中，步驟S4包括：
S4-1，斷句處理，對文件進行進行斷句處理，得到至少一個語句；
S4-2，分詞處理，對斷句後的至少一個語句進行分詞，得到分詞集合；
S4-3，詞性過濾處理，對分詞集合進行詞性過濾，去掉形容詞、副詞等與配送資訊無關的分詞；
S4-4，詞頻過濾處理，對分詞集合進行詞頻過濾，去掉物流配送場景中使用頻率低的分詞；
S4-5，停用詞過濾處理，對分詞集合進行停用詞過濾，去掉物流配送場景中不適用的分詞，通過步驟S4-3-步驟S4-5後，得到關鍵詞，如果關鍵詞只有一個，執行步驟S4-7，否則執行S4-6；
S4-6，核心意圖分類，對多個關鍵詞進行核心意圖分類，得到與配送資訊相關的核心意圖分類；
S4-7，意圖識別，通過關鍵詞-語義資訊庫匹配核心意圖，進行意圖識別；
S4-8，多意圖仲裁，如果有多個核心意圖，則根據等級權重表獲取核心意圖的權重，根據權重進行意圖仲裁，得到目標意圖。
本示例中配送方通過一鍵撥打將通信請求發送至伺服器，由伺服器代替配送方與接收方進行語音通信並通過語意識別獲取物流對象的配送資訊，實現了批量獲取物流對象的配送資訊，一方面降低了配送方的溝通時間成本，提高了物流對象的配送效率；另一方面，由機器代替配送方與接收方通信，能夠在派件數量大、溝通時間長和溝通品質的三重壓力下實現高履約配送水平，提高了接收方的體感。
本示例中，對通信中的接收方終端的語音資訊識別出的多個核心意圖進行分類，並根據與配送資訊相關的核心意圖分類中各個核心意圖的意圖等級權重進行意圖仲裁以確定目標意圖，解決了傳統自然語言理解中長句多意圖解析的問題，能夠準確地從長語音資訊中識別接收方的意圖。
本發明實施例中，可以根據接收方的目標意圖產生反應語音資訊自動回復接收方終端，提高了與接收方的交互，進一步提高了接收方的體感。
示例二
以下結合表3和線上場景對本發明中伺服器獲取物流對象配送資訊進行說明：
表3：
如上表3所示，
使用者回復：是指伺服器與使用者通信過程中接到接收方終端使用者的語音資訊；
ASR識別：是指將使用者語音資訊轉換為文件資訊，並進行了斷句處理；
詞性分析是指對文件資訊的每個字/詞進行詞性分析，並且進行了分詞處理；
詞性過濾：是指去掉與配送資訊無關的分詞，例如：分詞中的“不好意思”對配送資訊分析無用，可以去掉；
詞頻過濾：是指去掉物流配送場景中使用頻率低的分詞，例如分詞中的“下班”可以去掉；
停用詞過濾：是指去掉物流配送場景中停止使用的分詞，例如分詞中的“時候”可以去掉；
核心意圖：是指過濾後的分詞對應的意圖，可以從關鍵詞-語義資訊庫中匹配得到；例如，“我現在不在家”對應核心意圖為“不在家”，“我晚點自己去拿”對應核心意圖為“自提”，“你們營業時間是到” 對應核心意圖為“營業時間”；
意圖等級：是指預先劃分的各個核心意圖對應的等級權重；
意圖仲裁：是指結合核心意圖及等級權重對多個核心意圖進行仲裁，確定接收方最終的意圖，如表3中，自提與配送資訊相關，營業時間的權重為10，則最終意圖是自提和詢問營業時間；
操作：是指記錄最終意圖和反應接收方，如表3，伺服器記錄接收方意圖為自提和詢問營業時間，則對該意圖進行反應，如“好的，我們的營業時間是早上九點到晚九點，這個時間內您都可以來自提”。
在示例二中，伺服器自動與接收方終端通信，並根據通信中接收方終端的語音資訊進行意圖識別得到物流對象的配送資訊，降低了配送方的溝通時間成本，提高了物流對象的配送效率。
示例三
以下結合線上場景對本發明中伺服器對多意圖進行仲裁加以說明：
在示例三中，使用者回復：“我不在家，我媽媽在家，你拿上去吧”，通過如表1所示的關鍵詞-語義資訊庫匹配，得到這三個語句的意圖為“不在家”、“在家”、“在家”，通過等級權重表得到“在家”和“不在家”的權重均為10，則“在家”的權重和為20，“不在家”的權重是10，則最終意圖仲裁後為“在家”，對應的配送資訊是“送貨上門”。
本示例中可以根據與配送資訊相關的核心意圖分類中各個核心意圖的意圖等級權重進行意圖仲裁以確定目標意圖，解決了傳統自然語言理解中長語句多意圖解析的問題，能夠準確地從長語音資訊中識別接收方的意圖。
參照圖5，示出了本發明的一種物流對象配送資訊的獲取方法實施例3的步驟流程圖，本發明實施例的物流對象配送資訊的獲取方法可以應用於配送方終端，具體可以包括如下步驟：
步驟301，獲取至少一個物流對象的物流資訊，所述物流資訊包括所述物流對象關聯的接收方的接收方終端的通信連接資訊。
本發明實施例中，配送方可以是物流對象代收點，例如驛站等。配送方可以通過以下子步驟獲取物流對象的物流資訊：
子步驟S21，獲取預設時間段內待配送的物流對象的物流對象標識；
子步驟S22，將所述物流對象標識添加至待配送列表中；
子步驟S23，獲取所述待配送列表中物流對象標識關聯的接收方資訊，所述接收方資訊包括接收方終端的通信連接資訊。
具體而言，配送方在接收物流對象時，可以通過配送方終端掃描物流對象上的面單對物流對象進行入庫、分類、獲取物流資訊等操作。驛站管理員或者快遞員通過配送方終端上的應用程式可以獲取需要配送的物流對象的待配送列表，該待配送列表中的物流對象在配送前需要與接收方聯繫以確認是送貨上門還是接收方到站自提，待配送列表中包括物流對象標識以及該物流對象的接收方的聯繫方式，例如接收方的電話號碼等。
步驟302，依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求；
本發明實施例中，步驟302可以包括如下子步驟：
子步驟S31，檢測是否接收到針對所述待配送列表中所述物流對象標識對應的通信連接資訊的通信請求；
子步驟S32，依據所述待配送列表中物流對象標識關聯的通信連接資訊產生通信請求。
如圖6所示，在本發明實施例中，配送方終端可以獲取當前時間為止尚未與接收方聯繫的待配送列表，該待配送列表中包括待配送物流對象的資訊，例如可以是物流對象標識，例如“包裹A”，該物流對象標識可以是物流對象的運單號、物流對象運單上的名稱、和接收方的名稱等，該待配送列表中包括了待配送的物流對象的接收方的通信連接資訊和外呼觸發鍵。
當然，物流對象的資訊還可以是接收方的通信連接資訊、姓名、地址等，其中通信連接資訊可以是接收方的手機號碼碼、固定電話號碼等，當然也可以是其它非明文形式的通信連接資訊以確保接收方的隱私洩露，例如通信資訊可以是接收方終端的標識或者其它標識，通過該標識可以在後臺獲取接收方的明文通信連接資訊以產生通信請求，保證了接收方的手機號碼碼、固定電話號碼等隱私不被洩露。
如圖6所示，以驛站管理員或者快遞員需要獲取包裹A、包裹B和包裹C的配送資訊為示例，驛站管理員或者快遞員在包裹A、包裹B和包裹C入庫時掃描包裹上的面單，獲取到包裹A、包裹B和包裹C的單號、接收方的電話等資訊，並顯示在待配送列表中，該待配送列表中設置有“一鍵撥打”按鈕，驛站管理員或者快遞員可以通過“一鍵撥打”按鈕觸發配送方終端產生通信請求並發送至伺服器，由伺服器通過包裹A、包裹B和包裹C中的接收方的電話號碼與包裹A、包裹B和包裹C對應的接收方進行通話。
以上是通過待配送列表中的按鈕觸發產生通信請求發送至伺服器，在實際應用中也可以預設週期或者在掃描物流對象面單獲取物流對象資訊後自動產生通信請求發送至伺服器，本發明實施例對產生通信請求的方式和時間不加以限制。
步驟303，將所述通信請求發送至伺服器，所述伺服器用於依據所述通信請求中的通信連接資訊建立與所述至少一個物流對象關聯的接收方終端的通信，以及，依據通信過程中的通信資訊確定所述至少一個物流對象的配送資訊。
配送方終端將通信請求發送至伺服器後，伺服器可以通過外呼平臺的機器人與接收方終端進行通信，獲取接收方終端的通信資訊後進行斷句、分詞、過濾和語義分析以確定配送資訊，並將配送資訊發送至配送方終端。
步驟304，接收所述伺服器發送的所述至少一個物流對象的配送資訊。
配送方終端可以接收到伺服器發送的物流對象的配送資訊，較佳地，展示物流對象的配送資訊。
如圖7所示為本發明實施例中配送方終端顯示物流對象的配送資訊的示例，在圖7中，包裹A的配送資訊為送貨上門，包裹A的配送資訊為送貨上門，包裹B的配送資訊為到站自提。
本發明實施例中，配送方終端可以將針對待配送物流對象關聯的接收方終端的通信請求發送至伺服器，由伺服器與各個物流對象關聯的接收方終端進行通信，並通過通信資訊確定配送資訊後發送至配送方終端，配送方無需逐個與物流對象關聯的接收方終端進行通信以確定物流對象的配送資訊，實現了批量獲取物流對象的配送資訊，一方面降低了配送方的溝通時間成本，提高了物流對象的配送效率；另一方面，由機器代替配送方與接收方通信，能夠在派件數量大、溝通時間長和溝通品質的三重壓力下實現高履約配送水平，提高了接收方的體感。
參照圖8，示出了本發明的一種物流對象配送資訊的獲取裝置實施例1的結構框圖，本發明實施例的物流對象配送資訊的獲取裝置可以應用於伺服器，所述裝置包括：
通信請求接收模組401，用於接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊；
通信建立模組402，用於依據所述通信連接資訊與所述接收方終端建立通信；
通信資訊接收模組403，用於在通信過程中接收所述接收方終端的通信資訊；
配送資訊確定模組404，用於依據所述通信資訊確定所述物流對象的配送資訊；
配送資訊發送模組405，用於將所述配送資訊發送至所述配送方終端。
可選地，所述通信資訊為語音資訊，所述配送資訊確定模組404包括：
文件資訊轉換子模組，用於將所述語音資訊轉換為文件資訊；
語義分析子模組，用於對所述文件資訊進行語義分析，得到所述物流對象的配送資訊。
可選地，所述語義分析子模組包括：
斷句單元，用於對所述文件資訊進行斷句處理，得到至少一個語句；
分詞單元，用於對所述至少一個語句進行分詞，得到各個語句的分詞集合；
過濾單元，用於對所述分詞集合進行過濾，得到各個語句的至少一個關鍵詞；
核心意圖匹配單元，用於依據所述關鍵詞在預置的關鍵詞-語義資訊庫中進行匹配，得到各個語句的核心意圖；
配送資訊確定單元，用於依據各個語句的核心意圖確定所述物流對象的配送資訊。
可選地，所述配送資訊確定單元包括：
分類子單元，用於對各個語句的核心意圖進行分類，得到與配送資訊相關的核心意圖分類；
權重獲取子單元，用於依據預置的意圖等級權重表，獲取所述核心意圖分類中每個核心意圖的權重；
目標意圖確定子單元，用於依據所述核心意圖分類中每個核心意圖的權重進行意圖仲裁確定目標意圖；
配送資訊確定子單元，用於依據預置的意圖-配送資訊對照表，獲取所述目標意圖對應的配送資訊。
可選地，所述過濾單元包括：
詞性過濾子單元，用於依據預置詞性表對所述分詞集合進行詞性過濾；
及/或，
詞頻過濾子單元，用於依據預置詞頻表對所述分詞集合進行詞頻過濾；
及/或，
停用詞過濾子單元，用於依據預置停用詞詞表對所述分詞集合進行停用詞過濾。
可選地，所述裝置還包括：
反應文件資訊獲取模組，用於依據所述配送資訊，獲取與所述配送資訊對應的反應文件資訊；
語音轉換模組，用於將所述反應文件資訊轉換為反應語音；
反應語音發送模組，用於將所述反應語音發送至所述接收方終端。
可選地，還包括：
行為資料獲取模組，用於獲取使用者的歷史行為資料；
建立通信確定模組，用於依據所述歷史行為資料確定是否與所述接收方終端建立通信。
可選地，所述歷史行為資料封包括使用者地理位置資訊、使用者歷史收件行為資料、使用者肖像、與使用者通信的頻率以及使用者通信的情緒反應資料中的至少一項。
參照圖9，示出了本發明的一種物流對象配送資訊的獲取裝置實施例2的結構框圖，本發明實施例的物流對象配送資訊的獲取裝置可以應用於配送方終端，所述裝置包括：
物流資訊獲取模組501，用於獲取至少一個物流對象的物流資訊，所述物流資訊包括所述物流對象關聯的接收方的接收方終端的通信連接資訊；
通信請求產生模組502，用於依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求；
通信請求發送模組503，用於將所述通信請求發送至伺服器，所述伺服器用於依據所述通信請求中的通信連接資訊建立與所述至少一個物流對象關聯的接收方終端的通信，以及，根據通信過程中的通信資訊確定所述至少一個物流對象的配送資訊；
配送資訊接收模組504，用於接收所述伺服器發送的所述至少一個物流對象的配送資訊。
可選地，所述物流資訊獲取模組501包括：
物流對象標識獲取子模組，用於獲取預設時間段內待配送的物流對象的物流對象標識；
待配送列表產生子模組，用於將所述物流對象標識添加至待配送列表中；
通信連接資訊獲取子模組，用於獲取所述待配送列表中物流對象標識關聯的接收方資訊，所述接收方資訊包括接收方終端的通信連接資訊。
可選地，所述通信請求產生模組502包括：
操作檢測子模組，用於檢測是否接收到針對所述待配送列表中所述物流對象標識對應的通信連接資訊的通信請求；
通信請求產生子模組，用於依據所述待配送列表中物流對象標識關聯的通信連接資訊產生通信請求。
可選地，所述裝置還包括：
配送資訊展示模組，用於展示所述物流對象的配送資訊。
參照圖10，示出了本發明的一種物流對象配送資訊的獲取系統實施例的結構框圖，所述系統包括伺服器100和配送方終端200；
所述伺服器100包括：
通信請求接收模組1001，用於接收配送方終端發送的、針對至少一個物流對象關聯的接收方終端的通信請求，所述通信請求中包括接收方終端的通信連接資訊；
通信建立模組1002，用於依據所述通信連接資訊與所述接收方終端建立通信；
通信資訊接收模組1003，用於在通信過程中接收所述接收方終端的通信資訊；
配送資訊確定模組1004，用於依據所述通信資訊確定所述物流對象的配送資訊；
配送資訊發送模組1005，用於將所述配送資訊發送至所述配送方終端；
所述配送方終端200包括：
物流資訊獲取模組2001，用於獲取至少一個物流對象的物流資訊，所述物流資訊包括所述物流對象關聯的接收方的接收方終端的通信連接資訊；
通信請求產生模組2002，用於依據所述通信連接資訊產生針對所述至少一個物流對象關聯的接收方終端的通信請求；
通信請求發送模組2003，用於將所述通信請求發送至伺服器，所述伺服器用於依據所述通信請求中的通信連接資訊建立與所述至少一個物流對象關聯的接收方終端的通信，以及，根據通信過程中的通信資訊確定所述至少一個物流對象的配送資訊；
配送資訊接收模組2004，用於接收所述伺服器發送的所述至少一個物流對象的配送資訊。
本發明實施例還提供了一種裝置，包括：一個或多個處理器；和其上儲存有指令的一個或多個機器可讀介質，當由所述一個或多個處理器執行時，使得所述裝置執行實施例1及/或實施例2及/或實施例3所述的一個或多個的方法。
本發明實施例還提供了一個或多個機器可讀介質，其上儲存有指令，當由一個或多個處理器執行時，使得裝置執行實施例1及/或實施例2及/或實施例3所述的一個或多個的方法。
對於裝置實施例而言，由於其與方法實施例基本相似，所以描述的比較簡單，相關之處參見方法實施例的部分說明即可。
本說明書中的各個實施例均採用循序的方式描述，每個實施例重點說明的都是與其他實施例的不同之處，各個實施例之間相同相似的部分互相參見即可。
本領域內的技術人員應明白，本發明實施例的實施例可提供為方法、裝置、或電腦程式產品。因此，本發明實施例可採用完全硬體實施例、完全軟體實施例、或結合軟體和硬體方面的實施例的形式。而且，本發明實施例可採用在一個或多個其中包含有電腦可用程式碼的電腦可用儲存介質(包括但不限於磁盤記憶體、CD-ROM、光學記憶體等)上實施的電腦程式產品的形式。
本發明實施例是參照根據本發明實施例的方法、終端設備(系統)、和電腦程式產品的流程圖和/或方塊圖來描述的。應理解可由電腦程式指令實現流程圖和/或方塊圖中的每一流程和/或方塊、以及流程圖和/或方塊圖中的流程和/或方塊的結合。可提供這些電腦程式指令到通用電腦、專用電腦、嵌入式處理機或其他可程式設計資料處理終端設備的處理器以產生一個機器，使得通過電腦或其他可程式設計資料處理終端設備的處理器執行的指令產生用於實現在流程圖一個流程或多個流程和/或方塊圖一個方塊或多個方塊中指定的功能的裝置。
這些電腦程式指令也可儲存在能引導電腦或其他可程式設計資料處理終端設備以特定方式工作的電腦可讀記憶體中，使得儲存在該電腦可讀記憶體中的指令產生包括指令裝置的製造品，該指令裝置實現在流程圖一個流程或多個流程和/或方塊圖一個方塊或多個方塊中指定的功能。
這些電腦程式指令也可裝載到電腦或其他可程式設計資料處理終端設備上，使得在電腦或其他可程式化終端設備上執行一系列操作步驟以產生電腦實現的處理，從而在電腦或其他可程式化終端設備上執行的指令提供用於實現在流程圖一個流程或多個流程和/或方塊圖一個方塊或多個方塊中指定的功能的步驟。
儘管已描述了本發明實施例的優選實施例，但本領域內的技術人員一旦得知了基本進步性概念，則可對這些實施例做出另外的變更和修改。所以，所附申請專利範圍意欲解釋為包括優選實施例以及落入本發明實施例範圍的所有變更和修改。
最後，還需要說明的是，在本文中，諸如第一和第二等之類的關係用語僅僅用來將一個實體或者操作與另一個實體或操作區分開來，而不一定要求或者暗示這些實體或操作之間存在任何這種實際的關係或者順序。而且，用語“包括”、“包含”或者其任何其他變體意在涵蓋非排他性的包含，從而使得包括一系列要素的過程、方法、物品或者終端設備不僅包括那些要素，而且還包括沒有明確列出的其他要素，或者是還包括為這種過程、方法、物品或者終端設備所固有的要素。在沒有更多限制的情況下，由語句“包括一個……”限定的要素，並不排除在包括所述要素的過程、方法、物品或者終端設備中還存在另外的相同要素。
以上對本發明所提供的一種物流對象配送資訊的獲取方法和一種物流對象配送資訊的獲取裝置、一種物流對象配送資訊的獲取系統進行了詳細介紹，本文中應用了具體個例對本發明的原理及實施方式進行了闡述，以上實施例的說明只是用於幫助理解本發明的方法及其核心思想；同時，對於本領域的一般技術人員，依據本發明的思想，在具體實施方式及應用範圍上均會有改變之處，綜上所述，本說明書內容不應理解為對本發明的限制。In order to make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail in conjunction with the accompanying drawings and specific embodiments. Referring to FIG. 1, it shows a flowchart of steps of Embodiment 1 of a method for acquiring logistics object distribution information according to the present invention. The method for obtaining logistics object distribution information according to an embodiment of the present invention may be applied to a server, and may specifically include the following steps: Step 101: Receive a communication request sent by a distribution terminal to a receiver terminal associated with at least one logistics object, where the communication request includes communication connection information of the receiver terminal. In the embodiment of the present invention, the logistics object may be parcel, express, takeaway and other logistics items, the delivery party may be a courier, collection point or post manager of the delivery logistics object, and the recipient may be the final recipient of the logistics object Or the final recipient authorizes to act as the intermediary for the receipt. The logistics objects are usually delivered by the delivery side to the recipient. The delivery terminal may be a terminal used by the delivery side to manage the received logistics object, and the recipient terminal may be a terminal used by the recipient for communication. For example, for the post manager, after receiving the logistics objects distributed by the couriers of various courier companies, they can scan the logistics object's face sheet through the mobile terminal to perform operations such as warehousing, classification, and obtaining logistics information. The station administrator can obtain the list of logistics objects to be delivered through the application on the terminal of the delivery party. The logistics objects in the list of delivery to be delivered need to contact the recipient before delivery to confirm whether the delivery is home or the recipient arrives at the station Self mention. For another example, in another scenario, after the courier receives a logistics object that needs to be delivered from the outlet, the application of the delivery terminal of the courier can obtain a list of the logistics objects to be delivered, and the logistics objects in the list Before delivery, you need to contact the receiver to confirm whether it is delivered to the door or the receiver will pick up at the station. For example, for telephone contact with the recipient, the station administrator or courier can trigger the "one-click dial" button in the list to be delivered, and the delivery terminal generates a communication request for the recipient terminal associated with the logistics object in the list to be delivered, and The communication request is sent to the server, and the server makes telephone contact with each receiver terminal. The communication request may include communication connection information of the receiver terminal. In the embodiment of the present invention, if the receiver selects mobile phone contact, the communication connection information may be the receiver's mobile phone number or phone number. Of course, the communication connection information may also be other account numbers, such as various instant messaging applications The number registered by the receiver and the communication connection information may also be other identifiers that display the terminal information of the receiver in a non-clear text form, or other key identifiers, etc., to ensure that the receiver's private information is not leaked. The content and display mode are not restricted. In practical applications, the server may be a platform connected to the receiver terminal and capable of communicating with multiple receiver terminals, for example, it may be a call platform, which can communicate with multiple receiver terminals in the communication request The connection information performs voice or file communication with multiple receiver terminals. Step 102: Establish communication with the receiver terminal according to the communication connection information. In the embodiment of the present invention, the server can establish communication with multiple recipient terminals. For example, the communication connection information can be a mobile phone number code or a phone number, then voice communication can be established with multiple mobile phones or fixed phones. If the communication connection information Accounts of various instant messaging applications, you can establish communication with the receiver terminal registered in the communication account through the instant messaging application. The communication can be voice communication (telephone) or document information communication (simple message or chat information). The embodiment does not limit the method of establishing communication with the receiver terminal, and does not restrict the method of communicating with the receiver terminal. Step 103: Receive communication information of the receiver terminal during communication. Specifically, if it is voice communication, the voice information of the receiver terminal is received, and if it is real-time application communication, the voice information or document information of the receiver terminal is received. Step 104: Determine the distribution information of the logistics object according to the communication information. In the embodiment of the present invention, if the communication information is voice information, the voice information can be converted into document information, for example, ASR (Automatic Speech Recognition Technology, Automatic Speech Recognition) technology is used to convert the voice information into document information. After obtaining the document information, you can use the NLU (Natural Language Understanding, Natural Language Understanding) technology to identify the recipient's intention in the document information to determine the distribution information of the logistics object. Step 105: Send the delivery information to the delivery terminal. After the server determines the distribution information of the logistics object, it can send the distribution information of all the logistics objects targeted by the communication request to the terminal of the distribution side, and display the distribution information of the logistics object on the terminal of the distribution side, for example, show that each logistics object to be distributed is The door-to-door delivery is still provided by the receiver at the station. In the embodiment of the present invention, the distribution terminal sends a communication request to all receiver terminals associated with the logistics objects to be distributed to the server, communicates with the receiver terminals associated with each logistics object through the server, and determines the distribution through communication information After the information is sent to the terminal of the delivery side, the delivery side does not need to communicate with the recipient terminal associated with the logistics object one by one to determine the delivery information of the logistics object, which realizes the bulk acquisition of the delivery information of the logistics object, on the one hand, reduces the communication time cost of the delivery side , Improves the distribution efficiency of logistics objects; on the other hand, the machine replaces the delivery side to communicate with the receiver, which can achieve a high level of delivery under the triple pressure of large number of parts, long communication time and communication quality, and improves the receiver Somatosensory. Referring to FIG. 2, there is shown a flowchart of steps of Embodiment 2 of a method for acquiring distribution information of logistics objects according to the present invention. The method for obtaining distribution information of logistics objects according to an embodiment of the present invention may be applied to a server, and may specifically include the following steps: Step 201: Receive a communication request sent by a distribution terminal to a receiver terminal associated with at least one logistics object, where the communication request includes communication connection information of the receiver terminal. In the embodiment of the present invention, the delivery terminal may generate a communication request for the recipient terminal associated with the logistics object in the category to be delivered, and then send the communication request to the server, and the server receives the communication request sent by the delivery terminal The communication request includes the communication connection information of the recipient terminal associated with the logistics object, such as a mobile phone number code or a fixed telephone number. Step 202: Establish communication with the receiver terminal according to the communication connection information. After receiving the communication request, the server can establish communication with the receiver terminal according to the communication connection information in the communication request. As shown in FIG. 3, taking voice communication as an example, the communication request is directed to the recipient users A, B, C, and D associated with the four logistics objects. The communication request includes user A and user. The phone numbers of user B, user C, and user D. After the server receives the communication request, the server's outbound platform uses the phone numbers of user A, user B, user C, and user D in the communication request. Number, at the same time, telephone communication with user A, user B, user C and user D, voice interaction, without the need for the delivery party to communicate with user A, user B, user C and user D one by one The distribution information of the logistics object greatly reduces the communication time cost of the distribution party and improves the distribution efficiency of the logistics object. In a preferred embodiment of the present invention, before step 202, it may further include: acquiring historical behavior data of the recipient; and determining whether to establish communication with the recipient terminal according to the historical behavior data. The historical behavior data cover includes at least one of the receiver's geographic location information, the receiver's historical collection behavior data, the receiver's portrait, the frequency of communication with the receiver, and the receiver's emotional response data. For example, for the above user A, before making a call, determine the time when user A is at home based on user A's historical receiving behavior, user A's portrait such as age, work, etc., or according to contact The frequency of user A and the emotional response of user A's past calls are used to evaluate the user's fatigue to determine whether to call user A. In the embodiment of the present invention, whether to establish communication with the receiver terminal can be determined according to the historical behavior data of the receiver, which can avoid unnecessary interference with the receiver and improve communication efficiency. Step 203: Receive communication information of the receiver terminal during the communication process, where the communication information is voice information. In the embodiment of the present invention, the communication information may be voice information, for example, the voice information of the receiver during the telephone communication with the receiver. The communication information can also be document information, such as the SMS information received after sending SMS to multiple mobile phones or the document information returned by the receiver in the instant messaging application. Step 204: Convert the voice information into document information. If the communication information is voice information, you can use ASR (Automatic Speech Recognition Technology, Automatic Speech Recognition) technology to convert the voice information into document information. If it is document information, you can leave it out. Step 205: Perform semantic analysis on the document information to obtain distribution information of the logistics object. In the embodiment of the present invention, step 205 may include the following sub-steps: Sub-step S11, performing sentence segmentation processing on the document information to obtain at least one sentence. In practical applications, the document information may be relatively long, you need to segment the document information, including paragraph division and sentence division, for example, according to the characteristic characters in the document information, the document information is segmented, such as the period, comma, Semicolon, exclamation mark, question mark, space, etc. are used to segment the document information to obtain at least one sentence. Sub-step S12, performing word segmentation on the at least one sentence to obtain a word segmentation set for each sentence. In the embodiment of the present invention, at least one of a word segmentation method based on word string matching, a word segmentation method based on understanding, and a word segmentation method based on statistics may be used to perform word segmentation processing on each sentence. The word segmentation method based on word string matching is also called mechanical word segmentation method. It is to match the word string in the sentence to be analyzed with the entry in a "fully large" machine dictionary according to a certain strategy. If a certain word is found in the dictionary Words, a word segmentation is matched. The word segmentation method based on understanding is to simulate the understanding of the sentence by the computer to achieve the effect of identifying the word segmentation. The basic idea is to perform syntactic and semantic analysis at the same time of word segmentation, and use syntactic information and semantic information to deal with ambiguity, usually including three parts : Word segmentation subsystem, syntactic and semantic subsystem, general control part. Under the coordination of the general control part, the word segmentation subsystem can obtain syntactic and semantic information about words, sentences, etc. to judge the word segmentation ambiguity, which simulates the process of human understanding of sentences. The word segmentation method based on statistics is based on the combination of words whose form is a stable word. The more occurrences of adjacent words in the context, the more likely it is to form a word. Therefore, the frequency or probability of co-occurrence of words adjacent to the word can better reflect the credibility of the word. It is possible to count the frequency of the combination of each word co-occurring in the sentence to calculate the mutual occurrence information of the two words. The mutual information reflects the closeness of the combination between the two words. When the closeness is higher than a certain threshold, it can be considered that this word group may constitute a word. Sub-step S13, filtering the word segmentation set to obtain at least one keyword of each sentence. The embodiment of the present invention determines the distribution information of the logistics object by performing semantic analysis on the document information. In order to improve the accuracy and efficiency of the semantic analysis, the word segmentation set can be filtered to remove the useless word segmentation. Specifically, it can be based on the preset part of speech Table performs part-of-speech filtering on the word segmentation set; and/or, performs word frequency filtering on the word segmentation set according to a preset word frequency table; and/or, performs stop word filtering on the word segmentation set according to a preset stop word vocabulary table . The part-of-speech table may be a word that does not affect the semantic analysis in the logistics scene, such as adjectives, adverbs, etc., the word frequency table may be a word that is used less frequently in the logistics scene, and the stop word list may not be used in the logistics scene. Word. Through the word frequency table and the stop word list, you can filter the words and stop words in the word segmentation set with low frequency, and filter the adjectives that do not affect the semantic analysis through the part of speech table, so that each sentence gets At least one keyword. In sub-step S14, matching is performed in the preset keyword-semantic information database according to the keywords to obtain the core intent of each sentence. In practical applications, the keyword-semantic information database can be set in conjunction with logistics scenarios, as shown in Table 1 below: Table 1 above illustrates the keyword-semantic information database with the core intention of being at home, not at home, self-promotion and expenses as examples. In practical applications, other keyword-semantic information databases such as business hours can also be set. After the keywords of each sentence are obtained, the keywords can be matched in a preset keyword-semantic information database to obtain the core intent of each sentence. In sub-step S15, the distribution information of the logistics object is determined according to the core intention of each sentence. After determining the core intent of each sentence, you can determine the distribution information of the logistics object according to the core intent. The distribution information can be the distribution method of the logistics object, for example, it can be delivered to the door or picked up at the station. In a preferred embodiment of the present invention, sub-step S15 may include the following sub-steps: Sub-step S15-1, classify the core intent of each sentence to obtain the core intent classification related to the distribution information. In practical applications, the intention of each sentence of the receiver is not all related to the distribution information of the logistics object. The user intention of each sentence can be called the core intention. For example, in the scene of home delivery, the user sentence At home, not at home, and self-provisioning are core intentions. Others, such as expenses and business hours, are non-core intentions. Therefore, you can classify the core intentions of each sentence to obtain the core intention classification related to distribution information. Sub-step S15-2, according to the preset intention level weight table, obtain the weight of each core intention in the core intention classification. Specifically, you can set initial weights for each core intent through a large number of online real-world phone recordings, and then through daily online measurement, iteratively optimize the core intent weights to establish an intent level weight table, which records the core in the intent level weight table Intents and their level weights, so the weight of each core intent can be obtained according to a preset intent level weight table. In sub-step S15-4, intent arbitration is performed according to the weight of each core intention in the core intention classification to determine the target intention. During the communication with the receiver terminal, the document information can include multiple sentences, and each sentence can include multiple keywords. The keywords can be matched to the corresponding core intent, and the multiple core intents can be determined to be related to the distribution information. The core intent classification of the core intent needs arbitration to determine the target intent. The core intention classification in the distribution scenario includes not only the core intention related to the distribution information, but also includes the business hours and other classifications related to the self-lift time. For example, in a call, the core intention classification of user A includes "not at home", "at home" and "at home", the weight of "not at home" is 10, and the weight of "at home" is 10, then "at home" The weight sum of is 20, which is greater than the weight of "not at home" 10, the target intention is "at home". For another example, in a call, the core intention classification of user A includes "not at home", "self-promotion" and "business hours", the weight of "not at home" is 5, and the weight of "self-promotion" is 5, " The weight of "business hours" is 10, then the target intentions are "self-report" and "business hours". The embodiments of the present invention classify multiple core intentions recognized by voice information, and perform intention arbitration to determine the target intention according to the intention level weight of each core intention in the core intention classification related to the distribution information, which solves the traditional natural language understanding The problem of multi-intent parsing of medium and long sentences can accurately identify the intent of the receiver from long voice information. Sub-step S15-5, according to the preset intent-delivery information comparison table, obtain the delivery information corresponding to the target intent. In practical applications, different core intentions correspond to different delivery information, as shown in Table 2 below: In Table 2 above, information corresponding to other target intents can also be established. For example, if the target intent is business hours or expenses, the corresponding information is business hours information and expense information. Step 206: Acquire response document information corresponding to the delivery information according to the delivery information. In the embodiment of the present invention, the server communicates with the receiver terminal and needs to interact with the receiver terminal. After obtaining the distribution information, the server can react to the receiver terminal to improve the receiver's feeling. Specifically, it can Obtain the preset response document information corresponding to the delivery information. For example, the delivery information can be the door-to-door delivery, then the response document can be "OK, then wait for the meeting", if the delivery information is self-collected at the station, the reaction document can It’s “Okay, our business hours are from 9 am to 9 pm, you can come from this time”, the response file can be set differently according to different delivery information, this embodiment of the present invention does not limit this. Step 207: Convert the reaction document information into reaction speech. After acquiring the reaction document information, if it is voice communication, the reaction document information is converted into reaction speech, and if it is document communication, there is no need to convert. Step 208: Send the reaction voice to the receiver terminal. In voice communication, the server can send the reaction voice to the receiver's terminal to improve the interaction with the receiver. The following describes the process of obtaining distribution information according to an embodiment of the present invention with reference to examples. Example 1 is shown in Figure 4. In Example 1, the flow of obtaining distribution information of logistics objects is illustrated by telephone communication as follows: S1, the server initiates communication after receiving a one-key dial request from the recipient's distribution terminal, and the server establishes Voice communication of multiple receiver terminals; S2, user response, after the robot opens, the user reacts, the server can receive the user's voice information of the receiver terminal; S3, voice to file, the server will voice information Turn into document information; S4, semantic recognition, recognize the semantic meaning in the document information, determine the intent in the voice information; S5, semantic matching, match the corresponding response document according to the semantic meaning recognized from the document information; S6, Smart response, convert the response file to voice and send it to the receiver terminal for user response; S7, end the call. S8: Send the delivery information to the receiver's terminal. Among them, step S4 includes: S4-1, sentence segmentation processing, performing sentence segmentation processing on the file to obtain at least one sentence; S4-2, word segmentation processing, segmenting at least one sentence after the sentence segmentation to obtain a word segmentation set; S4-3, Part-of-speech filtering processing, part-of-speech filtering of word segmentation sets, removing adjectives, adverbs and other non-distribution word segmentation; S4-4, word frequency filtering processing, word segmentation filtering of word segmentation set, removing low-frequency participles in logistics distribution scenarios; S4 -5, stop word filtering process, stop word filtering on the participle set, remove the unsuitable word segmentation in the logistics distribution scene, after step S4-3-step S4-5, get the keyword, if there is only one keyword, Step S4-7 is executed, otherwise S4-6 is executed; S4-6, core intent classification, core intent classification for multiple keywords to obtain core intent classification related to distribution information; S4-7, intent recognition, through keywords -Semantic information database matches the core intent and performs intent recognition; S4-8, multi-intent arbitration. If there are multiple core intents, the weight of the core intent is obtained according to the rank weight table, and the intent arbitration is performed according to the weight to obtain the target intent. In this example, the distribution party sends the communication request to the server by one-click dialing, and the server performs voice communication on behalf of the distribution party and the receiver and obtains the distribution information of the logistics object through semantic recognition. On the one hand, it reduces the cost of the communication time of the distribution party and improves the distribution efficiency of the logistics object; on the other hand, the machine replaces the distribution party to communicate with the receiver, which can triple the pressure of large number of parts, long communication time and communication quality. Achieve a high level of fulfillment and delivery, improve the receiver's feeling. In this example, the multiple core intents identified by the voice information of the receiving terminal in the communication are classified, and the intent arbitration is performed according to the intent level weight of each core intent in the core intent classification related to the distribution information to determine the target intent. It solves the problem of multi-intention parsing of long sentences in traditional natural language understanding, and can accurately identify the receiver's intent from long voice information. In the embodiment of the present invention, a response voice information can be automatically generated according to the target intention of the receiver to reply to the terminal of the receiver, which improves the interaction with the receiver and further improves the receiver's body feeling. Example 2 The following describes the acquisition of distribution information of logistics objects by the server in the present invention in conjunction with Table 3 and online scenarios: Table 3: As shown in Table 3 above, user reply: refers to the voice information received by the receiving end user during the communication between the server and the user; ASR recognition: refers to the conversion of the user's voice information into document information, and the sentence is broken Processing; part-of-speech analysis refers to performing part-of-speech analysis on each word/word of document information, and performing word segmentation processing; part-of-speech filtering: removing participles that are not related to distribution information, for example: "sorry" in the participle for distribution information Analysis is useless and can be removed; word frequency filtering: refers to the removal of low-frequency participles used in logistics distribution scenarios, such as "off-duty" in the participle; stop word filtering: refers to the removal of discontinued participles in logistics distribution scenarios, such as The "time" in the participle can be removed; core intent: refers to the intent corresponding to the filtered participle, which can be matched from the keyword-semantic information database; for example, "I am not at home" corresponds to the core intent is "not at home" , "I'll pick it up later" corresponds to the core intent of "self-promotion", "Your business hours are up" corresponds to the core intent of "business hours"; Intent level: refers to the pre-divided core weight corresponding to each core intent; Intent Arbitration: Refers to the arbitration of multiple core intents in combination with the core intent and rank weights to determine the final intent of the receiver. As shown in Table 3, self-reporting is related to delivery information and the weight of business hours is 10, then the final intent is self-reporting And inquire about business hours; operation: refers to record the final intention and respond to the receiver, as shown in Table 3, the server records the receiver's intention as self-report and inquires about the business hours, then reacts to the intent, such as "OK, our business The time is from 9 am to 9 pm, during this time you can come from the mention." In the second example, the server automatically communicates with the recipient terminal, and performs intent recognition based on the voice information of the recipient terminal in the communication to obtain the distribution information of the logistics object, which reduces the communication time cost of the distribution party and improves the distribution efficiency of the logistics object . Example 3 The following describes the server in the present invention for arbitration of multiple intentions in conjunction with an online scenario: In Example 3, the user replies: "I am not at home, my mother is at home, you take it", as shown in Table 1 Keyword-semantic information database matching, the intention of getting these three sentences is "not at home", "at home", "at home", and the weight of "at home" and "not at home" is 10 through the rank weight table, then " The weight sum of "at home" is 20, and the weight of "not at home" is 10, then the final intention is to be "at home" after arbitration, and the corresponding delivery information is "home delivery". In this example, intent arbitration can be performed according to the intent level weight of each core intent in the core intent classification related to the distribution information to solve the target intent, which solves the problem of multi-intent parsing of long sentences in traditional natural language understanding, and can accurately read from long speech Identify the recipient’s intention in the information. Referring to FIG. 5, a flowchart of steps of Embodiment 3 of a method for acquiring distribution information of logistics objects according to the present invention is shown. The method for obtaining distribution information of logistics objects according to an embodiment of the present invention may be applied to a terminal of a delivery side, and may specifically include the following steps Step 301: Acquire logistics information of at least one logistics object, where the logistics information includes communication connection information of a receiver terminal of a receiver associated with the logistics object. In the embodiment of the present invention, the delivery party may be a logistics object collection point, such as a post or the like. The delivery party can obtain the logistics information of the logistics object through the following sub-steps: Sub-step S21, obtain the logistics object identifier of the logistics object to be distributed within a preset time period; Sub-step S22, add the logistics object identifier to the to-be-delivered list ; Sub-step S23, acquiring the receiver information associated with the logistics object identifier in the to-be-delivered list, the receiver information includes communication connection information of the receiver terminal. Specifically, when the delivery side receives the logistics object, the delivery side terminal can scan the face sheet on the logistics object to perform operations such as warehousing, classification, and obtaining logistics information for the logistics object. The post manager or courier can obtain the list of logistics objects to be delivered through the application on the terminal of the delivery party. The logistics objects in the list of delivery to be delivered need to contact the recipient before delivery to confirm whether the delivery is onsite or received The party arrives at the station, and the list to be delivered includes the identification of the logistics object and the contact information of the recipient of the logistics object, such as the phone number of the recipient. Step 302: Generate a communication request for the receiver terminal associated with the at least one logistics object according to the communication connection information; in the embodiment of the present invention, step 302 may include the following sub-steps: Sub-step S31, detecting whether the A communication request for communication connection information corresponding to the logistics object identifier in the to-be-delivered list; sub-step S32, generating a communication request according to the communication connection information associated with the logistics object identifier in the to-be-delivered list. As shown in FIG. 6, in the embodiment of the present invention, the terminal of the delivery side may obtain a list of goods to be delivered that has not contacted the recipient at the current time, and the list of goods to be delivered includes information of logistics objects to be delivered, such as a logistics object identifier , Such as "Package A", the logistics object identifier may be the logistics object's waybill number, the name of the logistics object's waybill, and the name of the recipient, etc. The list of to-be-delivered includes the recipient's Communication connection information and outgoing call trigger key. Of course, the logistics object information can also be the receiver's communication connection information, name, address, etc., where the communication connection information can be the receiver's mobile phone number code, fixed phone number, etc. Of course, it can also be other non-clear form communication connection Information to ensure the privacy of the receiver. For example, the communication information can be the identification of the receiver's terminal or other identification. Through this identification, the receiver's clear text communication connection information can be obtained in the background to generate a communication request, ensuring the receiver's mobile phone number code , Fixed telephone numbers and other privacy will not be disclosed. As shown in Figure 6, take the post manager or courier to obtain the delivery information of package A, package B and package C as an example. The post manager or courier scans the package on the package A, package B and package C when they enter the warehouse The face-to-face order, obtain the package number of package A, package B and package C, the receiver's phone number and other information, and display it in the list to be delivered. The list to be delivered is provided with a "one-click dial" button, the station administrator or The courier can use the "one-click dial" button to trigger the delivery terminal to generate a communication request and send it to the server. The server uses the phone number of the recipient in package A, package B and package C and package A, package B and package The receiver corresponding to C makes a call. The above is triggered by a button in the to-be-delivered list to generate a communication request and send it to the server. In actual applications, a communication cycle can be preset and the communication request can be automatically generated and sent to the server after scanning the logistics object sheet to obtain logistics object information. The invention The embodiment does not limit the method and time for generating the communication request. Step 303: Send the communication request to a server, the server is used to establish communication of the receiver terminal associated with the at least one logistics object according to the communication connection information in the communication request, and, according to the communication process The communication information in determines the distribution information of the at least one logistics object. After the distributor's terminal sends the communication request to the server, the server can communicate with the receiver's terminal through the robot of the outbound platform. After acquiring the communication information of the receiver's terminal, it can perform sentence segmentation, word segmentation, filtering and semantic analysis to determine the distribution information. And send the delivery information to the delivery terminal. Step 304: Receive distribution information of the at least one logistics object sent by the server. The distribution terminal can receive the distribution information of the logistics object sent by the server, and preferably, display the distribution information of the logistics object. As shown in FIG. 7, it is an example in which the distribution terminal displays distribution information of logistics objects in the embodiment of the present invention. In FIG. 7, the distribution information of package A is home delivery, the distribution information of package A is home delivery, and package B The delivery information is self-explanatory. In the embodiment of the present invention, the distributor terminal may send a communication request to the receiver terminal associated with the logistics object to be distributed to the server, and the server communicates with the receiver terminal associated with each logistics object, and the distribution is determined through the communication information After the information is sent to the terminal of the delivery side, the delivery side does not need to communicate with the recipient terminal associated with the logistics object one by one to determine the delivery information of the logistics object, which realizes the bulk acquisition of the delivery information of the logistics object, on the one hand, reduces the communication time cost of the delivery side , Improves the distribution efficiency of logistics objects; on the other hand, the machine replaces the delivery side to communicate with the receiver, which can achieve a high level of delivery under the triple pressure of large number of parts, long communication time and communication quality, and improves the receiver Somatosensory. Referring to FIG. 8, it shows a structural block diagram of Embodiment 1 of a logistics object distribution information acquisition device of the present invention. The logistics object distribution information acquisition device of the embodiment of the present invention can be applied to a server, and the device includes: communication The request receiving module 401 is used to receive the communication request sent by the distribution terminal to the receiver terminal associated with at least one logistics object, and the communication request includes the communication connection information of the receiver terminal; the communication establishment module 402 is used to To establish communication with the receiver terminal according to the communication connection information; a communication information receiving module 403, used to receive communication information of the receiver terminal during the communication process; a distribution information determination module 404, used to determine The communication information determines the distribution information of the logistics object; a distribution information sending module 405 is used to send the distribution information to the terminal of the delivery side. Optionally, the communication information is voice information, and the distribution information determination module 404 includes: a document information conversion sub-module for converting the voice information into document information; a semantic analysis sub-module for Perform semantic analysis on the document information to obtain distribution information of the logistics object. Optionally, the semantic analysis submodule includes: a sentence segmentation unit, which is used to perform sentence segmentation processing on the document information to obtain at least one sentence; a word segmentation unit, which is used to segment the at least one sentence to obtain the Word segmentation set; filtering unit for filtering the word segmentation set to obtain at least one keyword of each sentence; core intent matching unit for matching in the preset keyword-semantic information library according to the keyword To obtain the core intention of each sentence; the distribution information determination unit is used to determine the distribution information of the logistics object according to the core intention of each sentence. Optionally, the distribution information determination unit includes: a classification subunit for classifying the core intent of each sentence to obtain a core intent classification related to the distribution information; a weight acquisition subunit for use according to a preset intent level Weight table to obtain the weight of each core intent in the core intent classification; target intent determination subunit, used for intent arbitration to determine the target intent according to the weight of each core intent in the core intent classification; distribution information determination subunit , Used to obtain the distribution information corresponding to the target intent according to the preset intent-distribution information comparison table. Optionally, the filtering unit includes: a part-of-speech filtering sub-unit for performing part-of-speech filtering on the participle set according to a preset part-of-speech table; and/or, a word frequency filtering sub-unit for filtering the The word segmentation set performs word frequency filtering; and/or, a stop word filtering subunit, configured to perform stop word filtering on the word segmentation set according to a preset stop word vocabulary. Optionally, the device further includes: a response document information acquisition module for acquiring response document information corresponding to the distribution information based on the distribution information; a voice conversion module for converting the reaction document information Converted to reactive voice; reactive voice sending module, used to send the reactive voice to the receiver terminal. Optionally, the method further includes: a behavior data acquisition module for acquiring historical behavior data of the user; a communication determination module for determining whether to establish communication with the receiver terminal according to the historical behavior data. Optionally, the historical behavior data cover includes at least one of user geographic location information, user historical receiving behavior data, user portrait, frequency of communication with the user, and emotional response data of the user communication. Referring to FIG. 9, it shows a structural block diagram of an embodiment 2 of a device for acquiring distribution information of logistics objects according to the present invention. The device for obtaining distribution information of logistics objects according to an embodiment of the present invention can be applied to a terminal of a delivery side. The device includes: The logistics information acquisition module 501 is used to acquire logistics information of at least one logistics object, and the logistics information includes communication connection information of the receiver terminal of the receiver associated with the logistics object; the communication request generation module 502 is used to The communication connection information generates a communication request for a receiver terminal associated with the at least one logistics object; a communication request sending module 503 is used to send the communication request to a server, and the server is used to The communication connection information in the communication request establishes communication of the receiver terminal associated with the at least one logistics object, and determines the distribution information of the at least one logistics object based on the communication information in the communication process; the distribution information receiving module 504, It is used to receive the distribution information of the at least one logistics object sent by the server. Optionally, the logistics information acquisition module 501 includes: a logistics object identifier acquisition submodule for acquiring a logistics object identifier of a logistics object to be delivered within a preset time period; a submodule for generating a delivery list is used to Add the logistics object identifier to the list to be delivered; a communication connection information acquisition submodule, used to obtain information about the receiver associated with the logistics object identifier in the list to be delivered, the receiver information including communication of the receiver terminal Connection information. Optionally, the communication request generation module 502 includes: an operation detection submodule, configured to detect whether a communication request for communication connection information corresponding to the logistics object identifier in the to-be-delivered list is received; a communication request is generated The submodule is used for generating a communication request according to the communication connection information associated with the logistics object identifier in the to-be-delivered list. Optionally, the device further includes: a distribution information display module for displaying distribution information of the logistics object. Referring to FIG. 10, it shows a structural block diagram of an embodiment of a logistics object distribution information acquisition system of the present invention. The system includes a server 100 and a distribution terminal 200; The server 100 includes: a communication request receiving module 1001, used to receive a communication request sent by a distributor terminal to a receiver terminal associated with at least one logistics object, where the communication request includes communication connection information of the receiver terminal; a communication establishment module 1002, used to The communication connection information establishes communication with the receiving terminal; the communication information receiving module 1003 is used to receive the communication information of the receiving terminal during the communication process; the distribution information determining module 1004 is used to determine based on the communication information Delivery information of the logistics object; Delivery information sending module 1005, used to send the delivery information to the delivery side terminal; The delivery side terminal 200 includes: a logistics information acquisition module 2001, used to acquire at least one Logistics information of the logistics object, where the logistics information includes communication connection information of the receiver terminal of the receiver associated with the logistics object; a communication request generation module 2002, used to generate the at least one logistics according to the communication connection information The communication request of the receiver terminal associated with the object; the communication request sending module 2003 is used to send the communication request to a server, and the server is used to establish and at least the communication connection information in the communication request. Communication of a receiver terminal associated with a logistics object, and determining the distribution information of the at least one logistics object according to the communication information in the communication process; a distribution information receiving module 2004, configured to receive the at least one sent by the server Delivery information of a logistics object. An embodiment of the present invention also provides an apparatus, including: one or more processors; and one or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, cause all The device executes one or more methods described in Embodiment 1 and/or Embodiment 2 and/or Embodiment 3. Embodiments of the present invention also provide one or more machine-readable media on which instructions are stored, which, when executed by one or more processors, cause the device to execute Embodiment 1 and/or Embodiment 2 and/or embodiments 3. One or more of the methods described. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment. The embodiments in this specification are described in a sequential manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. Those skilled in the art should understand that the embodiments of the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may employ computer program products implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program code form. The embodiments of the present invention are described with reference to flowcharts and/or block diagrams of the method, terminal device (system), and computer program product according to the embodiments of the present invention. It should be understood that each flow and/or block in the flowchart and/or block diagram and a combination of the flow and/or block in the flowchart and/or block diagram can be implemented by computer program instructions. These computer programming instructions can be provided to a general purpose computer, a dedicated computer, an embedded processor, or other programmable data processing terminal device processor to produce a machine that is executed by a computer or other programmable data processing terminal device processor The instructions generate means for implementing the functions specified in one block or multiple blocks of one flow or multiple flows of the flowchart and/or one block of the block diagram. These computer program instructions can also be stored in a computer readable memory that can guide the computer or other programmable data processing terminal equipment to work in a specific manner, so that the generation of instructions stored in the computer readable memory includes the manufacture of the instruction device The instruction device implements the functions specified in one block or multiple blocks in one flow or multiple flows in the flowchart and/or one block or multiple blocks in the block diagram. These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operating steps can be performed on the computer or other programmable terminal device to generate computer-implemented processing, so that the computer or other programmable The instructions executed on the terminal device provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams. Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic progressive concept. Therefore, the scope of the attached patent application is intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention. Finally, it should also be noted that in this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these entities Or there is any such actual relationship or order between operations. Moreover, the terms "include", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device that includes a series of elements includes not only those elements, but also those that are not explicitly listed The other elements listed may also include elements inherent to such processes, methods, articles or terminal equipment. Without more restrictions, the element defined by the sentence "include one..." does not exclude that there are other identical elements in the process, method, article, or terminal device that includes the element. The above provides a detailed description of a method for obtaining logistics object distribution information, a device for obtaining logistics object distribution information, and a system for obtaining logistics object distribution information provided by the present invention. Specific examples are applied to the principles and implementation of the present invention. The method is described. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; meanwhile, for those of ordinary skill in the art, based on the idea of the present invention, the specific implementation and application scope will be There are changes, in summary, the content of this specification should not be understood as a limitation of the present invention.
