Express data query method and device and electronic equipment

Abstract

The invention provides an express data query method and apparatus, and an electronic device. The method comprises the steps of receiving an input text request; analyzing the text request based on a preset semantic understanding model, identifying keywords and themes, and determining an intention of a user to input a question based on the keywords and the themes; obtaining structured data matched with the intention in a database based on the keyword, the theme and the determined intention, and converting the structured data into a text to be output; according to the invention, salesmen can be helped to quickly search express data, time and energy are saved, and clients can be better served.

Description

Technical Field

[0001] The present disclosure relates to the field of express delivery technology, and in particular to an express delivery data query method, device and electronic device. Background Art

[0002] With the development of online shopping, express delivery has also increased; currently, the delivery work is mainly done manually, and the tasks are heavy and diverse, consuming a lot of time and energy of the salesperson. It is difficult for the salesperson's handheld terminal to contact customers, answer customer questions, and inquire about the work status of the previous day, resulting in low service quality and poor customer service experience. Summary of the invention

[0003] The present disclosure provides a method, device and electronic device for querying express data to at least solve the above technical problems existing in the prior art.

[0004] According to a first aspect of the present disclosure, a method for querying express data is provided, the method comprising:

[0005] receiving input text request;

[0006] Analyze the text request based on a preset semantic understanding model, identify keywords and topics, and determine the intention of the user input question based on the keywords and topics;

[0007] Based on the keywords, topics and determined intents, structured data matching the intents in a database is acquired, and the structured data is converted into text output.

[0008] In one possible implementation, the input text request includes at least one of the following:

[0009] Receiving a voice request from a handheld terminal, recognizing the voice into text, and obtaining a text request;

[0010] receiving a text request from a handheld terminal;

[0011] Receive a picture request from the handheld terminal, recognize the text in the picture, and obtain a text request.

[0012] In one possible implementation, analyzing the text request based on a preset semantic understanding model to identify keywords and topics includes:

[0013] Performing word segmentation processing on the text through the semantic understanding model;

[0014] Use word vector technology to convert the segmented text into word vectors;

[0015] Perform contextual semantic understanding on the text converted into word vectors to obtain the meaning of individual words, the relationship between words, and the meaning of the entire sentence;

[0016] Based on the meaning of the individual words, the relationship between the words, and the meaning of the entire sentence, keywords and topics are identified.

[0017] In one possible implementation, determining the intention of the user input question based on the keywords and topics includes:

[0018] The semantic understanding model identifies the intention of the user input question based on the keywords and topics;

[0019] When the confidence of the recognized intent exceeds a preset threshold, the intent of the user input question is output.

[0020] In one possible implementation, when the confidence levels of the recognized intentions are all lower than a preset threshold, a prompt message for re-entering the text request is generated.

[0021] In one possible implementation, the acquiring structured data matching the intent in a database based on the keywords, topics and determined intent includes at least one of the following:

[0022] Based on the keywords, themes and the determined intention to contact the customer, obtain the customer phone list in the database and broadcast it;

[0023] Based on the keywords, the subject and the determined intention, when the item is to be queried, obtaining the express delivery information matching the queried number in the database; the express delivery information includes logistics information, waybill number and customer name;

[0024] Based on the keywords, themes and the determined intention, when searching by post station, obtaining the express parcel information of the post station that has not been delivered in the database;

[0025] Based on the keywords, the subject and the determined intention, when leaving a voice message upon signing, obtaining the message wording information in the database;

[0026] When the work situation analysis is based on the keywords, themes and the determined intention, obtaining the work situation data of the corresponding time period in the database;

[0027] When the question is a question and answer based on the keywords, the subject and the determined intention, answer information matching the question in the database is obtained based on the question.

[0028] In one possible implementation, the working condition data of the preset time period is displayed in a combination of digital and graphical form;

[0029] Display modes include:

[0030] Graphical display: according to the different attributes of work status data, data graph, column graph, bar graph, pie chart, line graph, trend state graph, area graph, quadrant graph, surface graph, tree graph, radar graph, histogram, box graph, waterfall graph, funnel graph, combination graph or dynamic graph are used for display;

[0031] Color display uses multiple colors to differentiate data elements.

[0032] In one possible implementation, converting the structured data into text output includes at least one of the following:

[0033] Converting the structured data into text, recognizing the text into speech, and outputting the speech to a handheld terminal;

[0034] Converting the structured data into text, and outputting the text to a handheld terminal;

[0035] The structured data is converted into text, the text is converted into a picture, and the picture is output to a handheld terminal.

[0036] According to a second aspect of the present disclosure, a courier data query device is provided, the device comprising:

[0037] A receiving module, used for receiving an input text request;

[0038] An analysis module, configured to analyze the text request based on a preset semantic understanding model, identify keywords and topics, and determine the intention of the user input question based on the keywords and topics;

[0039] The output module is used to obtain structured data matching the intent in the database based on the keywords, topics and determined intents, and convert the structured data into text output.

[0040] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0041] at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.

[0044] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.

[0045] The express data query method, device and electronic device disclosed in the present invention, after receiving a text request, uses a semantic understanding model to analyze the text, identifies keywords and topics, and then determines the intention of the user's input question based on the keywords and topics, and finally combines the keywords, topics and intentions to obtain structured data matching the intention in the database, and then converts the structured data into text output, so that the salesperson can quickly read and find the desired data and get the desired answer, so as to quickly reply to customers or handle express delivery problems. It can also help the salesperson understand their work situation, save time and energy, and improve customer experience.

[0046] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0048] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0049] Figure 1 A schematic diagram of the implementation process of the express data query method according to an embodiment of the present disclosure is shown;

[0050] Figure 2 A schematic diagram showing the structure of a handheld terminal and a server according to an embodiment of the present disclosure is shown;

[0051] Figure 3 A structural diagram of a server according to an embodiment of the present disclosure is shown;

[0052] Figure 4 A schematic diagram of the structure of the express data query device according to an embodiment of the present disclosure is shown;

[0053] Figure 5 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0054] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0055] In the express delivery service industry, the pickup and delivery tasks of salesmen are the core links, which are directly related to service quality and customer satisfaction. With the advancement of technology, customers can enjoy seamless package tracking and appointment delivery experience through convenient mini-programs and official websites, which puts higher requirements on salesmen - to provide more efficient and accurate services. However, in a fast-paced working environment, cumbersome information processing, frequent communication needs and diverse task challenges quietly devour the time and energy of salesmen, becoming an invisible obstacle to service efficiency and customer satisfaction.

[0056] The express data query method, device and electronic device provided by the present application are introduced below in conjunction with the accompanying drawings.

[0057] like Figure 1 As shown, the embodiment of the present application provides a method for querying express data, the method comprising:

[0058] S101, receiving an input text request;

[0059] It is understandable that if Figure 2 As shown, the present application includes a handheld terminal and a server used by the salesperson, and the method provided by the present application is implemented based on the server. When the salesperson has a question that needs to be queried, he can input it through the handheld terminal, and the handheld terminal sends the request input by the salesperson to the server. It can be understood that the server provided by the present application is provided with models of multiple functions and a database for users to store various data.

[0060] like Figure 3 As shown, it can be understood that the server side in this application is divided into an access layer, a core business layer, and a persistence layer, each of which integrates a variety of technical framework services to support efficient, scalable and real-time data processing and business logic execution.

[0061] The access layer API serves as a portal for the client to interact with the backend service, and exchanges data through the HTTP protocol. Security measures such as parameter signature verification and token verification are used to enhance the security of the system, and high-concurrency scenarios are handled through mechanisms such as service current limiting and concurrency control. At the same time, the system uses the SSE (Server-Sent Events) mechanism to achieve real-time event push from the server to the client, improving the user experience and real-time performance of the application.

[0062] At the core business logic level, the rule engine supports business component development and hot deployment, which improves the flexibility and response speed of the system. Natural language processing (NLP) technology, such as Star Language Rasa service and Qianwen 32B large model, is used for tasks such as intent understanding, semantic analysis, and FAQ question and answer, which improves the intelligence level of the system. The system design also supports multi-tenant design, unified user model, and provides personalized services for different tenants.

[0063] In the data persistence layer, in order to ensure the stable operation of the system, a variety of database and cache technologies are integrated, such as MongoDB, Redis, etc., as well as message queue services (such as RocketMQ, Kafka) and coordinators (such as Zookeeper). These services work together to provide the system with efficient data storage, retrieval and messaging capabilities.

[0064] The system supports comprehensive monitoring and log collection functions, such as cat system monitoring, application logs, etc., which can monitor the system's operating status in real time and promptly discover and solve problems. At the same time, the system also provides data statistics and user behavior analysis functions, such as user time statistics, unrecognized speech statistics, etc., to provide data support for optimizing user experience and business decisions.

[0065] In summary, the server provided in this application demonstrates a highly integrated, scalable, secure and intelligent system, which provides a solid technical foundation for business development through reasonable component division and strong technical support.

[0066] Exemplarily, the model may be a semantic understanding model, etc. The database may store various express delivery order data, business work data, and salesperson's salary calculation rules, etc. Other data may also be provided, which is not limited in this application.

[0067] It can be understood that in this application, when the salesperson inputs a request on the handheld terminal, he can edit the text input through the display interface of the handheld terminal, or directly input the voice, or input the request by taking a photo of the handheld terminal. After receiving the request, the server will convert it into a text request first, regardless of whether the request is in voice, picture or other form, to facilitate the subsequent analysis of the text request by the semantic understanding model.

[0068] S102, analyzing the text request based on a preset semantic understanding model, identifying keywords and topics, and determining the intention of the user input question based on the keywords and topics;

[0069] It is understandable that the present application has multiple models on the server side, including not only the semantic understanding model but also other models, which are not limited in the present application. The present application uses the semantic understanding model to analyze the text request to obtain the keywords and topics in the text request, so as to determine the intention of the user input question based on the keywords and topics.

[0070] For example, when the salesperson inputs "query the order information of the mobile phone number ending in 1234", the keywords are 1234 and order, so it can be guessed that the intention of the question is "query the order information of the mobile phone number ending in 1234" or "query the order information of order number 1234"; when the salesperson inputs "yesterday's work data", the keywords are yesterday and work data, so it can be guessed that the intention of the question is, "query yesterday's work content", etc.

[0071] S103, based on the keywords, themes and the determined intent, obtaining structured data matching the intent in a database, and converting the structured data into text output.

[0072] It is understandable that in this application, structured data in the database is obtained based on keywords, topics and determined intentions. For example, when the intention is to query the order information of the mobile phone number ending in 1234, the order information about the mobile phone number ending in 1234 in the database is obtained, including all order information within a preset time period and orders that have been delivered or not delivered.

[0073] The express data query method provided in the present application, after receiving a text request, uses a semantic understanding model to analyze the text, identifies keywords and topics, and then determines the intention of the user's input question based on the keywords and topics. Finally, the keywords, topics and intentions are combined to obtain structured data matching the intention in the database, and then the structured data is converted into text output, so that the salesperson can quickly read and find the desired data and get the desired answers, so as to quickly reply to customers or handle express delivery issues. It can also help the salesperson understand their work situation, save time and energy, and improve customer experience.

[0074] In some embodiments, the input text request includes at least one of the following:

[0075] Receiving a voice request from a handheld terminal, recognizing the voice into text, and obtaining a text request;

[0076] receiving a text request from a handheld terminal;

[0077] Receive a picture request from the handheld terminal, recognize the text in the picture, and obtain a text request.

[0078] The salesperson of this application is equipped with a voice recognition module on the server. The voice recognition module receives voice and processes audio data, converts the audio data into text, and can also filter out the noise in the surrounding environment, extract the salesperson's audio data, and improve the accuracy of recognition. In this application, the salesperson can edit text input through the display interface of the handheld terminal, or can directly input voice by pressing the voice button, or can input the request by taking a photo by the handheld terminal or obtaining a picture from the album. After receiving the request, the server converts the voice or picture into a text request first.

[0079] It should be noted that when converting speech into text, after receiving the text request, the server first starts the hot word replacement mechanism to accurately identify and replace the polyphone phenomenon in the express industry and express-specific business vocabulary, such as multiple misreadings of some words, and unify them into standard nouns to improve the accuracy of text processing.

[0080] In some embodiments, analyzing the text request based on a preset semantic understanding model to identify keywords and topics includes:

[0081] Performing word segmentation processing on the text through the semantic understanding model;

[0082] Use word vector technology to convert the segmented text into word vectors;

[0083] Perform contextual semantic understanding on the text converted into word vectors to obtain the meaning of individual words, the relationship between words, and the meaning of the entire sentence;

[0084] Based on the meaning of the individual words, the relationship between the words, and the meaning of the entire sentence, keywords and topics are identified.

[0085] It is understandable that after receiving the text, the semantic understanding model in this application first segments the text to obtain the text after segmentation, and then converts the text after segmentation into a word vector, and then performs contextual semantic understanding to obtain the meaning of individual words, the relationship between words, and the meaning of the whole sentence, thereby obtaining keywords and topics. The contextual semantic understanding in this application introduces a session retention mechanism to deeply understand the contextual relationship in the salesperson's conversation. For situations with missing parameters or confirmation, it automatically supplements and guides to ensure the coherence and accuracy of intent recognition. If the current session cannot meet the context requirements, it will seamlessly switch to the RASA machine learning model for a new intent analysis.

[0086] In some embodiments, determining the intention of the user input question based on the keywords and topics includes:

[0087] The semantic understanding model identifies the intention of the user input question based on the keywords and topics;

[0088] When the confidence of the recognized intent exceeds a preset threshold, the intent of the user input question is output.

[0089] In some embodiments, when the confidence levels of the recognized intents are all below a preset threshold, a prompt message for re-entering the text request is generated.

[0090] It is understandable that the semantic understanding model in this application adopts the Rasa model. When the recognition credibility of the RASA model exceeds 92%, the salesperson's intention is accurately captured, so as to facilitate the database to match the preset business intentions and parameters. Subsequently, the corresponding operations are performed according to the configuration in the business logic library to achieve efficient and accurate business processing. If the confidence of the recognized intent is less than 92%, the intent is not output, but a prompt message for re-entering the text request is generated and sent to the handheld terminal to remind the salesperson to re-enter.

[0091] Among them, the salesperson's intentions include instruction intentions, diagnosis and analysis intentions, and knowledge question and answer intentions; for example, instruction intentions include checking whether there are undelivered items, batch outbound calls before delivery, checking items by the last digit, checking items by photo recognition, checking receipt pictures, one-click change of dispatch, checking items by delivery point and signing for them with one click, batch pickup, automatic reminder for overdue pickup, checking items that have not been shipped out of the warehouse, urging payment, checking communication records, reporting prohibited items, reporting damaged items, reporting intercepted items, reporting problem items, checking intercepted items, and performing return and replacement processing, jumping to common pages, checking business volume bills, checking today's income, withdrawing cash, etc.; diagnosis and analysis include work analysis, today's data, checking false signatures, checking pending work orders, checking the quality of loose piece services, etc.; knowledge question and answer include common questions, business-level assessment rules, express industry knowledge, checking the weather, etc.

[0092] In some embodiments, the acquiring structured data matching the intent in a database based on the keywords, topics, and determined intents includes at least one of the following:

[0093] Based on the keywords, themes and the determined intention to contact the customer, obtain the customer phone list in the database and broadcast it;

[0094] Based on the keywords, the subject and the determined intention, when the item is to be queried, obtaining the express delivery information matching the queried number in the database; the express delivery information includes logistics information, waybill number and customer name;

[0095] Based on the keywords, themes and the determined intention, when searching by post station, obtaining the express parcel information of the post station that has not been delivered in the database;

[0096] Based on the keywords, the subject and the determined intention, when leaving a voice message upon signing, obtaining the message wording information in the database;

[0097] When the work situation analysis is based on the keywords, themes and the determined intention, obtaining the work situation data of the corresponding time period in the database;

[0098] When the question is a question and answer based on the keywords, the subject and the determined intention, answer information matching the question in the database is obtained based on the question.

[0099] In this application, before delivery, the salesperson can use voice commands to quickly check whether there are any express parcels that have been missed or need to make a phone call for precise delivery. For example, if the voice says "batch outbound calls" or "call before delivery", the system will display the query results through voice broadcast and list. Afterwards, the salesperson can use voice or manually click the "batch outbound calls" button, and the system will automatically call the customer and synchronize the call results (such as the number of calls, call status, and delivery requirements) to the salesperson. If the first call fails, you can call again.

[0100] During the delivery process, salesmen often receive calls from customers asking for or looking for parcels. By using the voice command "check for parcels ending in 1234" or "ending in 1234", the system will broadcast the corresponding parcel information. If the parcel is being delivered, you can send a text message to the recipient by voice or by clicking the "Send SMS" button; if the salesman is delivering the parcel and has arrived at the customer's place, you can click the "Sign for" button to complete the photo signing. When the parcel has been signed for, you can check the signing location by voice or by clicking the "View Sign for Picture" button, and feedback to the customer.

[0101] After arriving at the delivery point, the salesperson can use voice commands to check the remaining express parcels, such as "check how many parcels are left at the Twin Towers", and the system will display all relevant express parcels. The salesperson can select some or all of the express parcels to sign for and take photos with one click.

[0102] When the customer is not at home during door-to-door delivery, the salesperson can sign for the package by taking a photo. After scanning the package barcode, you can leave a voice message to the customer. When the customer views the logistics details, he or she can not only see the photo of the signing location, but also hear the voice message, making it easy to find the package quickly.

[0103] In addition, in this application, the salesperson can query the work status by voice, and the database will retrieve and display yesterday's work status, and analyze it from four dimensions: "achievement value", "business volume", "service quality", and "digital application". Each dimension is divided into at least two or more sub-dimensions. When the performance is excellent, the system will dynamically prompt "You are great, please keep it up"; when the performance is average or poor, the system will prompt "There is still a lot of room for improvement, keep it up." In addition, when checking yesterday's work status, the salesperson can also view the current business data and make corresponding processing, such as details of items to be picked up, work orders to be processed, etc.

[0104] This application can also handle daily issues, such as how much the courier charges.

[0105] Specifically, the intentions of the salesperson in this application can include operational intentions: subdivided into simple queries (such as checking the last digit of a package, and instantly displaying the logistics track) and complex operations (such as batch outbound calls, automatic aggregation of information and support for one-click outbound calls, and real-time feedback of outbound call results). Non-operational: Relying on the big model to intelligently answer the express industry and YTO business knowledge, covering standard questions and daily consultations, providing accurate answers or recommended question lists to enhance user experience.

[0106] It should be noted that the data in the database of this application can also support dynamic loading / unloading of rule files at runtime, so that business processes can be adjusted without restarting the application. Automatically monitor changes in rule files, update rules in real time, and maintain the timeliness of business logic. It can also be combined with Spring Boot hot deployment, and automatically reload components after updates to ensure continuous optimization of business logic.

[0107] The express data query method provided in this application can also realize real-time Q&A of the salesperson. For non-operational questions, the SSE (Server-Sent Events) technology is used to build a real-time Q&A system. The GPT model runs on the server side, and pushes answers to the client GPT window in real time through HTTP long connection to ensure the smoothness and immediacy of Q&A interaction. In addition, the SSE service in this application is based on HTTP long connection, which effectively reduces client polling requests and reduces server pressure, while realizing instant data push and improving user experience. The technical solution of this application has achieved significant improvements in user experience, business processing efficiency and system flexibility.

[0108] In some embodiments, the working condition data of the preset time period is displayed in a combination of digital and graphical forms;

[0109] Display modes include:

[0110] Graphical display: according to the different attributes of work status data, data graph, column graph, bar graph, pie chart, line graph, trend state graph, area graph, quadrant graph, surface graph, tree graph, radar graph, histogram, box graph, waterfall graph, funnel graph, combination graph or dynamic graph are used for display;

[0111] Color display uses multiple colors to differentiate data elements.

[0112] In order to display the salesperson's work data more intuitively and prominently, different colors are used to display various data elements in different colors. For example, the express that has been delivered is green, the express that is about to reach the delivery deadline is bright yellow, and the express that has exceeded the delivery deadline is red, etc. The above differences can also be displayed in the form of charts.

[0113] In some embodiments, converting the structured data into text output includes at least one of the following:

[0115] Converting the structured data into text, recognizing the text into speech, and outputting the speech to a handheld terminal;

[0116] Converting the structured data into text, and outputting the text to a handheld terminal;

[0117] The structured data is converted into text, the text is converted into a picture, and the picture is output to a handheld terminal.

[0118] Specifically, this application returns carefully organized structured data or detailed question and answer texts to the client through an efficient transmission mechanism. The client once again demonstrates its flexibility, using text-to-speech synthesis (TSS) technology to play this information to the salesperson in voice form, achieving comprehensive, intuitive, and convenient information delivery. The entire process is designed to be smooth, greatly improving the user interaction experience and work efficiency.

[0119] like Figure 4 As shown, the embodiment of the present application provides an express data query device, the device comprising:

[0120] Receiving module 401, used for receiving an input text request;

[0121] An analysis module 402 is used to analyze the text request based on a preset semantic understanding model, identify keywords and topics, and determine the intention of the user input question based on the keywords and topics;

[0122] The output module 403 is used to obtain structured data matching the intent in the database based on the keywords, topics and determined intent, and convert the structured data into text output.

[0123] The present application provides an electronic device, including:

[0124] at least one processor; and

[0125] a memory communicatively connected to the at least one processor; wherein,

[0126] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of the above embodiments.

[0127] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0128] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0129] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0130] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0131] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the express data query method. For example, in some embodiments, the express data query method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the express data query method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the express data query method in any other appropriate manner (e.g., by means of firmware).

[0132] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0134] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0136] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0137] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0138] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0139] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0140] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for querying express data, characterized in that: The method comprises: Receive input text request; Analyze the text request based on a preset semantic understanding model, identify keywords and topics, and determine the intention of the user input question based on the keywords and topics; Based on the keywords, topics and determined intents, structured data matching the intents in a database is acquired, and the structured data is converted into text output.

2. The method according to claim 1, characterized in that: The input text request includes at least one of the following: Receiving a voice request from a handheld terminal, recognizing the voice into text, and obtaining a text request; receiving a text request from a handheld terminal; Receive a picture request from the handheld terminal, recognize the text in the picture, and obtain a text request.

3. The method according to claim 1, characterized in that The text request is analyzed based on a preset semantic understanding model to identify keywords and topics, including: Performing word segmentation processing on the text through the semantic understanding model; Use word vector technology to convert the segmented text into word vectors; Perform contextual semantic understanding on the text converted into word vectors to obtain the meaning of individual words, the relationship between words, and the meaning of the entire sentence; Based on the meaning of the individual words, the relationship between the words, and the meaning of the entire sentence, keywords and topics are identified.

4. The method according to claim 1, characterized in that: The determining the intention of the user input question based on the keywords and topics includes: The semantic understanding model identifies the intention of the user input question based on the keywords and topics; When the confidence of the recognized intent exceeds a preset threshold, the intent of the user input question is output.

5. The method according to claim 4, characterized in that When the confidence levels of the recognized intents are all lower than a preset threshold, a prompt message for re-entering the text request is generated.

6. The method according to claim 1, characterized in that The acquiring structured data matching the intent in a database based on the keywords, the subject, and the determined intent includes at least one of the following: Based on the keywords, themes and the determined intention to contact the customer, obtain the customer phone list in the database and broadcast it; Based on the keywords, the subject and the determined intention, when the item is to be queried, obtaining the express delivery information matching the queried number in the database; the express delivery information includes logistics information, waybill number and customer name; Based on the keywords, themes and the determined intention, when searching by post station, obtaining the express parcel information of the post station that has not been delivered in the database; Based on the keywords, the subject and the determined intention, when leaving a voice message upon signing, obtaining the message wording information in the database; When the work situation analysis is based on the keywords, themes and the determined intention, obtaining the work situation data of the corresponding time period in the database; When the question is a question and answer based on the keywords, the subject and the determined intention, answer information matching the question in the database is obtained based on the question.

7. The method according to claim 6, characterized in that Displaying the working condition data of the preset time period in a digital and graphical manner; Display modes include: Graphical display: according to the different attributes of work status data, data graph, column graph, bar graph, pie chart, line graph, trend state graph, area graph, quadrant graph, surface graph, tree graph, radar graph, histogram, box graph, waterfall graph, funnel graph, combination graph or dynamic graph are used for display; Color display uses multiple colors to differentiate data elements.

8. The method according to claim 1, characterized in that: The converting the structured data into text output includes at least one of the following: Converting the structured data into text, recognizing the text into speech, and outputting the speech to a handheld terminal; Converting the structured data into text, and outputting the text to a handheld terminal; The structured data is converted into text, the text is converted into a picture, and the picture is output to a handheld terminal.

9. A courier data query device, characterized in that: The device comprises: A receiving module, used for receiving an input text request; An analysis module, configured to analyze the text request based on a preset semantic understanding model, identify keywords and topics, and determine the intention of the user input question based on the keywords and topics; The output module is used to obtain structured data matching the intent in the database based on the keywords, topics and determined intents, and convert the structured data into text output.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

Images