WO2020199961A1 - 候餐时长实时预估方法和系统 - Google Patents

候餐时长实时预估方法和系统 Download PDF

Info

Publication number
WO2020199961A1
WO2020199961A1 PCT/CN2020/080717 CN2020080717W WO2020199961A1 WO 2020199961 A1 WO2020199961 A1 WO 2020199961A1 CN 2020080717 W CN2020080717 W CN 2020080717W WO 2020199961 A1 WO2020199961 A1 WO 2020199961A1
Authority
WO
WIPO (PCT)
Prior art keywords
time
customer
waiting time
real
average
Prior art date
Application number
PCT/CN2020/080717
Other languages
English (en)
French (fr)
Inventor
刘胜涛
Original Assignee
时时同云科技(成都)有限责任公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 时时同云科技(成都)有限责任公司 filed Critical 时时同云科技(成都)有限责任公司
Publication of WO2020199961A1 publication Critical patent/WO2020199961A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/12—Hotels or restaurants
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
    • G07C2011/04—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere related to queuing systems

Definitions

  • the present disclosure relates to the technical field of time estimation, and in particular to a method and system for real-time estimation of waiting time.
  • a published patent with application publication number CN103473345A and application publication date of 2013.12.25 discloses a method of estimating time length, including: obtaining the waiting time of the task to be executed in the distributed system and the execution time of executing the task to be executed;
  • the waiting time of a task is the interval between the current time and the execution start time of a task, and the execution time of a task is the interval between the execution start time and the execution end time of a task; according to the waiting time of the task to be executed And the execution time of the task to be executed, the remaining time of the task to be executed is obtained, and the remaining time of a task is the interval time between the current time and the execution end time of a task.
  • this method of estimating duration does not have the feature data construction analysis function, the estimated result is inaccurate, the real-time performance is poor, and the method of communicating the estimated result is relatively simple.
  • the present disclosure provides a method and system for real-time estimation of waiting time, which can effectively overcome the lack of characteristic data construction analysis function in the prior art, and the estimation result is inaccurate and real-time The defect of poor performance and a single way of communicating the estimated results.
  • the present disclosure discloses a real-time estimation system for waiting time, including: a cloud database for storing data; a data collection module for collecting data; a characteristic data building module that communicates with the cloud database through the first wireless The module performs wireless communication and is used to construct a customer dining feature vector based on the collected data.
  • the elements of the customer dining feature vector constructed by the feature data construction module include at least one of the following: the number of people in the front n, the average waiting time of historical customers t1 , The average waiting time of customers in the same day t2, the historical average dining time t3, and the average dining time of current customers t4; the model training module communicates wirelessly with the cloud database through the second wireless communication module to use the built customer dining features Vector training store queuing time estimation algorithm; estimated time communication module, wireless communication with cloud database through the third wireless communication module, used to communicate the estimated time calculated by the trained store queuing time estimation algorithm To customers.
  • the present disclosure also discloses a method for real-time estimation of waiting time, including: collecting customer data, and constructing a customer dining feature vector based on the data.
  • the elements of the customer dining feature vector include at least one of the following: number of people in front n, history The average waiting time of customers t1, the average waiting time of customers in the same day t2, the historical average dining time t3, and the average dining time of current customers t4; input the customer's dining feature vector into the trained store queue waiting time estimation algorithm, and calculate the customer The estimated time to wait; among them, the constructed customer dining feature vector is used to train the store's waiting time estimation algorithm; the estimated time is communicated to the customer.
  • the present disclosure also discloses an electronic device, which includes:
  • At least one processor and,
  • a memory communicatively connected with 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, so that the at least one processor can execute any of the foregoing first aspect or any implementation of the first aspect Real-time estimation method of waiting time.
  • the present disclosure also discloses a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium stores at least one executable instruction, and the executable instruction is used to make a processor execute the aforementioned first aspect or the first aspect Real-time estimation method of waiting time in any implementation manner of.
  • the present disclosure also discloses a computer program product.
  • the computer program product includes a calculation program stored on a non-transitory computer-readable storage medium.
  • the computer program includes program instructions that, when executed by a processor, cause the processing The processor executes the method for estimating the waiting time in real time in the foregoing first aspect or any implementation of the first aspect.
  • the present disclosure provides a method and system for estimating the waiting time in real time, which has the following beneficial effects:
  • the data collection module can be used to collect data useful for constructing a waiting time estimation system, including the time node when customers start queuing, the time node when customers queuing ends, the time node when customers start eating, and the time node when customers finish eating. At least one of them, and construct the feature vector of each customer based on the collected data, so that the data update is real-time, so that the real-time estimation system of waiting time based on big data and AI technology is real-time and improves the estimation Accuracy of time
  • the elements in the customer dining feature vector include at least one of the following elements: including the number of people in the front n, the average waiting time of historical customers t1, the average waiting time of customers on the day t2, The historical average dining time t3 and the average dining time t4 of current customers.
  • the model training module is used to train the store queuing time estimation algorithm.
  • the historical queuing data of a store exceeds a certain amount (preliminarily set at 300), it can also be determined according to the actual use effect, and the queuing data can be used.
  • the xgboost algorithm is selected according to the actual situation, so that the real-time waiting time estimation system based on big data and AI technology can train the store to wait in line
  • the function of time estimation algorithm makes the model more accurate;
  • the estimated waiting time is communicated to customers, including the network query module, screen display module, and short message sending module.
  • the real-time predicted data can be communicated to users by sending short messages to customers every five minutes.
  • the real-time forecast data can be scrolled on the display through the form of an electronic display, and customers can query the real-time estimated time data through the store webpage, so that the data transmission of the real-time estimation system of waiting time based on big data and AI technology Ways are more diverse.
  • Figure 1 is a schematic diagram of the structure of the disclosed system
  • Figure 2 is a schematic diagram of the structure of the feature data building module of the present disclosure
  • FIG. 3 is a schematic diagram of the structure of the estimated time communication module of the present disclosure.
  • FIG. 4 is a flowchart of a method for real-time estimation of waiting time provided by an embodiment of the disclosure
  • FIG. 5 is a schematic structural diagram of an electronic device 50 provided by an embodiment of the disclosure.
  • a real-time estimation system of waiting time based on big data and AI technology includes a cloud database for data storage and transmission, and wireless communication with the cloud database through the first wireless communication module
  • the feature data building module used to construct the customer's dining feature vector
  • the model training module used to train the store waiting time estimation algorithm for wireless communication with the cloud database through the second wireless communication module
  • the cloud database through the third wireless communication module
  • the estimated time transmission module for wireless communication used to communicate the estimated time to the customer, and the data acquisition module connected to the characteristic data building module for collecting data.
  • the first wireless communication module, the second wireless communication module, and the third wireless communication module all use GPRS modules;
  • the estimated time communication module includes a network query module, a screen display module, and a short message sending module;
  • the data collected by the data collection module includes At least one of the following: the time node when the customer starts queuing, the time node when the customer queuing ends, the time node when the customer starts to eat, and the time node when the customer ends; the algorithm used by the model training module selects the xgboost algorithm.
  • FIG. 4 is a flowchart of a method for real-time estimation of waiting time provided by an embodiment of the disclosure. As shown in Figure 4, the method includes:
  • Step S410 Collect customer data, and construct a customer dining feature vector based on the data.
  • Step S420 Input the customer's dining feature vector into the trained store waiting time estimation algorithm to calculate the estimated time that the customer needs to wait; wherein the constructed customer dining feature vector is used to train the store's waiting time estimation algorithm.
  • Step S430 convey the estimated time to the customer.
  • the real-time waiting time estimation system based on big data and AI technology can be divided into five steps, namely:
  • the first step is data collection.
  • the data collection module can be used to collect data useful for constructing a waiting time estimation system, including the time node when customers start queuing, the time node when customers queuing ends, the time node when customers start eating, and customers eat At least one of the end time nodes, and construct the feature vector of each customer based on the collected data, so that the data update is real-time, so that the real-time waiting time estimation system based on big data and AI technology is real-time, Improve the accuracy of estimated time;
  • the second step is feature construction.
  • the feature data building module is used to construct the feature vector of the customer's dining.
  • the elements of the feature vector include the number of people in the front n, the average waiting time of historical customers t1, the average waiting time of customers on the day t2, and the average historical average dining time t3 and the average dining time of current customers t4; among them, the average waiting time of historical customers t1 refers to the average waiting time t1 of store customers before that day, that is, the customers who have queued at this merchant calculated based on the historical data before the day of queuing The average waiting time t1 of the store.
  • the average waiting time t1 of the store customers before the day can be expressed It is (t11+t12+t13)/3;
  • the average waiting time of customers in the same day t2 refers to the average waiting time t2 of shop customers that are queued on the day, which is the average waiting time of customers on the day calculated based on the merchant queuing data on the day of queuing.
  • the average waiting time t2 of the customers in the store on that day can be expressed It is (t21+t22+t23)/3;
  • the historical average dining time t3 refers to the store's historical average dining time t3, which is the average dining time of all people who have eaten in this store before the day of the line, if there are three people before the day of the line Have eaten in this store, and their dining time is t31, t32, t33, the store’s historical average dining time t3 can be expressed as (t31+t32+t33)/3;
  • the average dining time of current customers is t4, which is When a customer arrives in the queue, the average length of time that the customer who is currently dining has been dining at present.
  • the average dining time t4 of current customers can be expressed as (t41+t42+t43)/3; then for any customer who has queued, we can construct their feature vector in the corresponding restaurant as (n, t1, t2, t3 , t4) and their corresponding waiting time t, can also increase or decrease the elements of the feature vector according to the actual situation, so that the real-time estimation system of waiting time based on big data and AI technology has the function of constructing the feature vector of the customer’s dining. Further improve the accuracy of the estimated time;
  • the third step is model training.
  • Use the model training module to train the store queuing time estimation algorithm.
  • the historical queuing data of a store exceeds a certain amount (preliminarily set at 300), it can also be determined according to the actual use effect.
  • Queuing data specifically constructed features and corresponding waiting time, are used to train the waiting time estimation algorithm of the store, and the xgboost algorithm is selected according to the actual situation, so that the real-time waiting time estimation system based on big data and AI technology has Train the function of the algorithm for predicting the waiting time in the store queue, making the model more accurate;
  • the fourth step is to collect real-time data and estimate the waiting time.
  • a customer comes to the store to queue, we can immediately calculate the customer's feature vector (n, t1, t2, t3, t4) and input it into
  • the trained xgboost model calculates that the customer needs to wait; but it does not end at this time, because what is estimated at this time is only the length of time that the customer may need to wait under normal circumstances at the time, but I don’t know if there will be any later Sudden circumstances, if the person in the front line suddenly leaves, or the person dining at the time suddenly leaves or eats faster than usual, these situations will greatly reduce the length of time that the line-up person may need to wait, which leads us to based on the previous feature data The predicted waiting time is inaccurate; therefore, it is necessary to continuously collect data in real time to calculate the number of people in the front n, the average waiting time of customers on the day t2, and the average dining time of current customers t4.
  • the fifth step is to communicate the estimated waiting time to customers, including network query module, screen display module, and short message sending module.
  • the real-time predicted data can be communicated to users by sending short messages to customers every five minutes.
  • the real-time forecast data can also be scrolled on the display through the form of an electronic display, and customers can query real-time estimated time data through the store webpage, so that the data of the real-time estimation system of waiting time based on big data and AI technology Communication methods are more diverse.
  • the electronic device 50 includes at least one processor 501 (for example, a CPU), at least one input and output interface 504, a memory 502, and at least one communication bus 503 for implementing The connection and communication between these components.
  • the at least one processor 501 is configured to execute computer instructions stored in the memory 502, so that the at least one processor 501 can execute any one of the foregoing embodiments of the method for real-time estimation of waiting time.
  • the memory 502 is a non-transitory memory (non-transitory memory), which can include volatile memory, such as high-speed random access memory (RAM: Random Access Memory), or non-volatile memory (non-volatile memory) , Such as at least one disk storage.
  • volatile memory such as high-speed random access memory (RAM: Random Access Memory)
  • non-volatile memory non-volatile memory
  • the communication connection with at least one other device or unit is realized through at least one input and output interface 504 (which may be a wired or wireless communication interface).
  • the memory 502 stores a program 5021
  • the processor 501 executes the program 5021, which is used to execute the content in any of the foregoing embodiments of the method for real-time estimation of waiting time.
  • the electronic device can exist in many forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communications.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has calculation and processing functions, and generally also has mobile Internet features.
  • Such terminals include: PDA, MID and UMPC devices, such as iPad.
  • Portable entertainment equipment This type of equipment can display and play multimedia content.
  • Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • Specific server a device that provides computing services.
  • the composition of a server includes a processor, hard disk, memory, system bus, etc.
  • the server is similar to a general computer architecture, but due to the need to provide highly reliable services, it is High requirements in terms of performance, reliability, security, scalability, and manageability.
  • the description is relatively simple, and for related parts, please refer to the partial description of the method embodiment.
  • a "computer-readable medium” can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, device, or device or in combination with these instruction execution systems, devices, or devices.
  • computer readable media include the following: electrical connections (electronic devices) with one or more wiring, portable computer disk cases (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable and editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer-readable medium may even be paper or other suitable media on which the program can be printed, because it can be used, for example, by optically scanning the paper or other media, and then editing, interpreting, or other suitable media if necessary. The program is processed in a manner to obtain the program electronically and then stored in the computer memory.
  • multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a logic gate circuit for implementing logic functions on data signals
  • Discrete logic circuits application-specific integrated circuits with suitable combinational logic gates
  • PGA programmable gate array
  • FPGA field programmable gate array

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种候餐时长实时预估方法及系统，该系统包括用于数据存储与传输的云数据库，与云数据库通过第一无线通信模块进行无线通信的用于构建顾客就餐特征向量的特征数据构建模块，与云数据库通过第二无线通信模块进行无线通信的用于训练店铺排队等待时长预估算法的模型训练模块，与云数据库通过第三无线通信模块进行无线通信的用于将预估时间传达给客户的预估时间传达模块，与特征数据构建模块相连的用于采集数据的数据采集模块。

Description

候餐时长实时预估方法和系统
相关申请公开的交叉参考
本申请要求于2019年3月29日提交中国专利局、申请号为201910252658.4、名称为“一种基于大数据及AI技术的候餐时长实时预估系统”的中国专利申请公开的优先权，其全部内容通过引用结合在本申请公开中。
技术领域
本公开涉及时长预估技术领域，尤其涉及一种候餐时长实时预估方法和系统。
背景技术
随着社会经济的发展和人们生活水平的提高，越来越多的人乐于去餐厅和饭店就餐。但是长期以来一直困扰大家的一个问题就是，当我们去比较火爆的餐厅就餐时，往往需要排队，但又不能准确的知道还需要等多久，以至于排队体验很差。如果在开始排队的时候就能够准确地知道还需要等多久，那么排队的人就可以先去做自己想做的事，等轮到自己用餐的时候再过来直接就餐，而不必一直排队等候。然而，传统的等待时长预估方法不具有特征数据构建分析功能，预估结果不准确，实时性较差，且预估结果传达方式较为单一。因此，研发一种基于大数据及AI技术的候餐时长实时预估系统是解决上述问题的关键所在。
在申请公布号为CN103473345A、申请公布日为2013.12.25的公开专利中公开了一种预估时长的方法，包括：获取分布式系统中待执行任务的等待时长和执行待执行任务的执行时长；一个任务的等待时长为当前时间与一个任务的执行开始时间之间的间隔时长，一个任务的执行时长为一个任务的执行开始时间与执行结束时间之间的间隔时长；根据待执行任务的等待时长和待执行任务的执行时长，获得待执行任务的剩余时长，一个任务的剩余时长为当前时间与一个任务的执行结束时间之间的间隔时长。应用该公开方法可以获得待执行任务的剩余时长，即获得当前时间与待执行任务的执行结束时间之间的间隔时长，从而能够方便后续的资源调度或其他任务的安排。
但这种预估时长的方法不具有特征数据构建分析功能，预估结果不准确，实时性较差，且预估结果传达方式较为单一。
发明内容
(一)解决的技术问题
针对现有技术所存在的上述缺点，本公开提供了一种候餐时长实时预估方法和系统，能够有效克服现有技术所存在的不具有特征数据构建分析功能，预估结果不准确，实时性较差，且预估结果传达方式较为单一的缺陷。
(二)技术方案
为了实现上述目的，本公开揭示一种候餐时长实时预估系统，包括：云数据库，用于存储数据；数据采集模块，用于采集数据；特征数据构建模块，与云数据库通过第一无线通信模块进行无线通信，用于根据采集到的数据构建顾客就餐特征向量，特征数据构建模块构建的顾客就餐特征向量的元素包括下列中的至少一个：排在前面的人数n、历史顾客平均等待时长t1、当天顾客平均排队等待时长t2、历史平均就餐时长t3、以及当前就餐顾客平均就餐时长t4；模型训练模块，与云数据库通过第二无线通信模块进行无线通信，用于使用构建好的顾客就餐特征向量训练店铺排队等待时长预估算法；预估时间传达模块，与云数据库通过第三无线通信模块进行无线通信，用于将通过训练好的店铺排队等待时长预估算法计算出的预估时间传达给顾客。
本公开还揭示一种候餐时长实时预估方法，包括：采集顾客的数据，根据数据构建顾客就餐特征向量，顾客就餐特征向量的元素包括下列中的至少一个：排在前面的人数n、历史顾客平均等待时长t1、当天顾客平均排队等待时长t2、历史平均就餐时长t3以及当前就餐顾客平均就餐时长t4；将顾客就餐特征向量输入至训练好的店铺排队等待时长预估算法，计算得到该顾客需要等待的预估时间；其中，使用构建好的顾客就餐特征向量训练店铺排队等待时长预估算法；将预估时间传达给顾客。
本公开还揭示一种电子设备，该电子设备包括：
至少一个处理器；以及，
与该至少一个处理器通信连接的存储器；其中，
该存储器存储有可被该至少一个处理器执行的指令，该指令被该至少一 个处理器执行，以使该至少一个处理器能够执行前述任第一方面或第一方面的任一实现方式中的候餐时长实时预估方法。
本公开还揭示一种非暂态计算机可读存储介质，该非暂态计算机可读存储介质存储有至少一可执行指令，该可执行指令用于使处理器执行前述第一方面或第一方面的任一实现方式中的候餐时长实时预估方法。
本公开还揭示一种计算机程序产品，该计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序，该计算机程序包括程序指令，当该程序指令被处理器执行时，使该处理器执行前述第一方面或第一方面的任一实现方式中的候餐时长实时预估方法。
(三)有益效果
与现有技术相比，本公开提供了一种候餐时长实时预估方法和系统，具有以下有益效果：
第一，可以利用数据采集模块采集对于构建排队等待时长预估系统有用的数据，具体包括顾客开始排队的时间节点、顾客排队结束的时间节点、顾客开始就餐的时间节点以及顾客就餐结束的时间节点中的至少一个，并根据采集到的数据构建每个顾客的特征向量，使得数据更新具有实时性，从而使得基于大数据及AI技术的候餐时长实时预估系统具有实时性，提高了预估时间的准确性；
第二，利用特征数据构建模块构建顾客就餐特征向量，顾客就餐特征向量中的元素下列中的至少一个：包括排在前面的人数n、历史顾客平均等待时长t1、当天顾客平均排队等待时长t2、历史平均就餐时长t3以及当前就餐顾客平均就餐时长t4，对于任意已经排过队的顾客我们可以构建他们在对应餐厅的特征向量为(n,t1,t2,t3,t4)以及他们对应的排队等待时长t，也可以根据实际情况增加或者减少特征，使得基于大数据及AI技术的候餐时长实时预估系统具有构建顾客就餐的特征向量的功能，进一步提高了预估时间的准确性；
第三，利用模型训练模块训练店铺排队等待时长预估算法，当一个店铺的历史排队数据超过一定量(初步定为300条)，也可根据实际使用效果确定，便可以使用这些排队数据，具体为构建的特征向量及对应的等待时长来训练该店铺的排队等待时长预估算法，根据实际情况选择使用xgboost算法，使得基于大数据及AI技术的候餐时长实时预估系统具有训练店铺排队等待时 长预估算法的功能，使得模型更加精确；
第四，不停地实时采集数据来计算排在前面的人数n，当天顾客平均排队等待时长t2以及当前就餐顾客平均就餐时长t4中的至少一个，并与t1以及t3中的至少一个一起重新输入到训练好的xgboost模型中得出新的预测时长；使得基于大数据及AI技术的候餐时长实时预估系统实时性进一步提高，预估数据更加精确；
第五，排队等待时长预估时间传达给顾客，包括网络查询模块、屏幕显示模块以及短信发送模块，可以通过每隔五分钟给顾客发一次短信的形式将实时预测出的数据传达给用户，也可以通过电子显示屏的形式将实时预测数据在显示屏上滚动播放，且可以让顾客通过店铺网页查询实时预估时间数据，使得基于大数据及AI技术的候餐时长实时预估系统的数据传达方式更加多样化。
附图说明
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本公开系统的结构示意图；
图2为本公开的特征数据构建模块的结构示意图；
图3为本公开的预估时间传达模块的结构示意图；
图4为本公开实施例提供的候餐时长实时预估方法的流程图；
图5为本公开实施例提供的电子设备50的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获 得的所有其他实施例，都属于本公开保护的范围。
一种基于大数据及AI技术的候餐时长实时预估系统，如图1至图3所示，包括用于数据存储与传输的云数据库，与云数据库通过第一无线通信模块进行无线通信的用于构建顾客就餐特征向量的特征数据构建模块，与云数据库通过第二无线通信模块进行无线通信的用于训练店铺排队等待时长预估算法的模型训练模块，与云数据库通过第三无线通信模块进行无线通信的用于将预估时间传达给客户的预估时间传达模块，与特征数据构建模块相连的用于采集数据的数据采集模块。
具体地，第一无线通信模块、第二无线通信模块、第三无线通信模块均采用GPRS模块；预估时间传达模块包括网络查询模块、屏幕显示模块以及短信发送模块；数据采集模块采集的数据包括下列中的至少一个：顾客开始排队的时间节点、顾客排队结束的时间节点、顾客开始就餐的时间节点以及顾客就餐结束的时间节点；模型训练模块使用的算法选择xgboost算法。
图4为本公开实施例提供的候餐时长实时预估方法的流程图。如图4所示，该方法包括：
步骤S410：采集顾客的数据，根据该数据构建顾客就餐特征向量。
步骤S420：将该顾客就餐特征向量输入至训练好的店铺排队等待时长预估算法，计算得到该顾客需要等待的预估时间；其中，使用构建好的顾客就餐特征向量训练店铺排队等待时长预估算法。
步骤S430：将该预估时间传达给顾客。
使用时，可以将基于大数据及AI技术的候餐时长实时预估系统分为五步进行，分别为：
第一步，数据采集，可以利用数据采集模块采集对于构建排队等待时长预估系统有用的数据，具体包括顾客开始排队的时间节点、顾客排队结束的时间节点、顾客开始就餐的时间节点以及顾客就餐结束的时间节点中的至少一个，并根据采集到的数据构建每个顾客的特征向量，使得数据更新具有实时性，从而使得基于大数据及AI技术的候餐时长实时预估系统具有实时性，提高了预估时间的准确性；
第二步，特征构建，利用特征数据构建模块构建顾客就餐的特征向量，特征向量的元素包括排在前面的人数n、历史顾客平均等待时长t1、当天顾客 平均排队等待时长t2、历史平均就餐时长t3以及当前就餐顾客平均就餐时长t4；其中，历史顾客平均等待时长t1是指排在当天之前的店铺顾客平均等待时长t1,即为根据排队当天之前历史数据计算出来的在此商户排队过的顾客的平均排队等待时长t1，如果历史数据中有三个顾客曾在此店铺排过队，而他们的排队等待时长分别为t11、t12、t13，则排在当天之前的店铺顾客平均等待时长t1可表示为(t11+t12+t13)/3；当天顾客平均排队等待时长t2是指排在当天的店铺顾客平均排队等待时长t2，即为根据排队当天商户排队数据计算出来的当天顾客平均排队等待时长，如果一个顾客过来排队时，当天在他之前曾有三个顾客在此店铺排过队，而他们的排队等待时长分别为t21、t22、t23，则排在当天的店铺顾客平均排队等待时长t2可表示为(t21+t22+t23)/3；历史平均就餐时长t3是指店铺历史平均就餐时长t3，即为排队当天之前所有在此店铺就过餐的人的平均就餐时长，假如排队当天之前有三个人曾在此店铺就过餐，他们的就餐时长分别为t31、t32、t33，则店铺历史平均就餐时长t3可表示为(t31+t32+t33)/3；当前就餐顾客平均就餐时长t4，即为当某一顾客到达排队时，当前正在就餐的顾客目前已经用餐的平均时长，假如当一个顾客到达一个店铺排队时，此时正在用餐的顾客有三个人，他们分别已经用餐时长为t41、t42、t43，则当前就餐顾客平均就餐时长t4可表示为(t41+t42+t43)/3；则对于任意已经排过队的顾客我们可以构建他们在对应餐厅的特征向量为(n,t1,t2,t3,t4)以及他们对应的排队等待时长t，也可以根据实际情况增加或者减少特征向量的元素，使得基于大数据及AI技术的候餐时长实时预估系统具有构建顾客就餐的特征向量的功能，进一步提高了预估时间的准确性；
第三步，模型训练，利用模型训练模块训练店铺排队等待时长预估算法，当一个店铺的历史排队数据超过一定量(初步定为300条)，也可根据实际使用效果确定，便可以使用这些排队数据，具体为构建的特征及对应的等待时长，来训练该店铺的排队等待时长预估算法，根据实际情况选择使用xgboost算法，使得基于大数据及AI技术的候餐时长实时预估系统具有训练店铺排队等待时长预估算法的功能，使得模型更加精确；
第四步，数据的实时采集及排队等待时长的预估，当一个顾客到该店铺来排队时我们便可以立即计算出该顾客的特征向量(n,t1,t2,t3,t4)并输入到训练好的xgboost模型中计算出该顾客需要等待时间；但此时并没有结束，因为 此时预估出来的只是该顾客在当时正常情况下可能需要等待的时长，但并不知道后面是否会有突发情况，如果后面排在前边的人突然有事离开或者当时就餐的人突然离开或吃的比平常快等这些情况都会大大减少此排队的人可能需要等待的时长，从而导致我们根据先前特征数据预测的等待时长不准；因此需要不停地实时采集数据来计算排在前面的人数n，当天顾客平均排队等待时长t2,当前就餐顾客平均就餐时长t4这三个特征数据，并与t1、t3一起重新输入到训练好的xgboost模型中得出新的预测时长；使得基于大数据及AI技术的候餐时长实时预估系统实时性进一步提高，预估数据更加精确；
第五步，排队等待时长预估时间传达给顾客，包括网络查询模块、屏幕显示模块、短信发送模块，可以通过每隔五分钟给顾客发一次短信的形式将实时预测出的数据传达给用户，也可以通过电子显示屏的形式将实时预测数据在显示屏上边滚动播放，且可以让顾客通过店铺网页查询实时预估时间数据，使得基于大数据及AI技术的候餐时长实时预估系统的数据传达方式更加多样化。
图5为本公开实施例提供的电子设备50的结构示意图，电子设备50包括至少一个处理器501(例如CPU)，至少一个输入输出接口504，存储器502，和至少一个通信总线503，用于实现这些部件之间的连接通信。至少一个处理器501用于执行存储器502中存储的计算机指令，以使至少一个处理器501能够执行前述任一候餐时长实时预估方法的实施例。存储器502为非暂态存储器(non-transitory memory)，其可以包含易失性存储器，例如高速随机存取存储器(RAM：Random Access Memory)，也可以包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。通过至少一个输入输出接口504(可以是有线或者无线通信接口)实现与至少一个其他设备或单元之间的通信连接。
在一些实施方式中，存储器502存储了程序5021，处理器501执行程序5021，用于执行前述任一候餐时长实时预估方法实施例中的内容。
该电子设备可以以多种形式存在，包括但不限于：
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括：智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备：这类设备属于个人计算机的范畴，有计算和 处理功能，一般也具备移动上网特性。这类终端包括：PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备：这类设备可以显示和播放多媒体内容。该类设备包括：音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)特定服务器：提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子设备。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将
一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些
实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
本说明书中的各个实施例均采用相关的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。
尤其，对于装置实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明 书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本公开的各部分可以用硬件、软件、固件或它们的组合来实现。
在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
以上所述，仅为本公开的具体实施方式，但本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以权利要求的保护范围为准。

Claims (13)

  1. 一种候餐时长实时预估系统，其特征在于，所述系统包括：
    云数据库，用于存储数据；
    数据采集模块，用于采集数据；
    特征数据构建模块，与所述云数据库通过第一无线通信模块进行无线通信，用于根据采集到的数据构建顾客就餐特征向量，所述特征数据构建模块构建的顾客就餐特征向量的元素包括下列中的至少一个：排在前面的人数n、历史顾客平均等待时长t1、当天顾客平均排队等待时长t2、历史平均就餐时长t3、以及当前就餐顾客平均就餐时长t4；
    模型训练模块，与所述云数据库通过第二无线通信模块进行无线通信，用于使用构建好的顾客就餐特征向量训练店铺排队等待时长预估算法；及
    预估时间传达模块，与所述云数据库通过第三无线通信模块进行无线通信，用于将通过训练好的店铺排队等待时长预估算法计算出的预估时间传达给顾客。
  2. 根据权利要求1所述的候餐时长实时预估系统，其特征在于：所述第一无线通信模块、第二无线通信模块、第三无线通信模块均采用GPRS模块。
  3. 根据权利要求1所述的候餐时长实时预估系统，其特征在于：
    所述数据采集模块进一步用于：实时采集排在前面的人数n、当天顾客平均排队等待时长t2、以及当前就餐顾客平均就餐时长t4中的至少一个；
    所述候餐时长实时预估系统还用于：将实时采集到的排在前面的人数n、当天顾客平均排队等待时长t2、以及当前就餐顾客平均就餐时长t4中的至少一个、以及历史顾客平均等待时长t1和历史平均就餐时长t3中的至少一个输入到店铺排队等待时长预估算法计算得到新的预估时间；
    所述预估时间传达模块进一步用于：将新的预估时间传达给顾客。
  4. 根据权利要求1-3任一项所述的候餐时长实时预估系统，其特征在于：所述预估时间传达模块包括网络查询模块、屏幕显示模块以及短信发送模块。
  5. 根据权利要求1-3任一项所述的候餐时长实时预估系统，其特征在于：所述数据采集模块采集的数据包括下列中的至少一个：顾客开始排队的时间节点、顾客排队结束的时间节点、顾客开始就餐的时间节点以及顾客就餐结束的时间节点。
  6. 根据权利要求1-3任一项所述的候餐时长实时预估系统，其特征在于：所述模型训练模块使用的算法选择xgboost算法。
  7. 一种候餐时长实时预估方法，其特征在于，所述方法包括：
    采集顾客的数据，根据所述数据构建顾客就餐特征向量，所述顾客就餐特征向量的元素包括下列中的至少一个：排在前面的人数n、历史顾客平均等待时长t1、当天顾客平均排队等待时长t2、历史平均就餐时长t3以及当前就餐顾客平均就餐时长t4；
    将所述顾客就餐特征向量输入至训练好的店铺排队等待时长预估算法，计算得到该顾客需要等待的预估时间，其中，使用构建好的顾客就餐特征向量训练店铺排队等待时长预估算法；及
    将所述预估时间传达给顾客。
  8. 根据权利要求7所述的候餐时长实时预估方法，其特征在于，所述数据包括下列中的至少一个：顾客开始排队的时间节点、顾客排队结束的时间节点、顾客开始就餐的时间节点和/或顾客就餐结束的时间节点。
  9. 根据权利要求7或8所述的候餐时长实时预估方法，其特征在于，所述采集顾客的数据，根据所述数据构建顾客就餐特征向量进一步包括：
    实时采集顾客的数据来计算排在前面的人数n、当天顾客平均排队等待时长t2、以及当前就餐顾客平均就餐时长t4中的至少一个；
    所述将所述顾客就餐特征向量输入至训练好的店铺排队等待时长预估算法，计算得到该顾客需要等待的预估时间进一步包括：
    将实时计算得到的排在前面的人数n、当天顾客平均排队等待时长t2以及当前就餐顾客平均就餐时长t4中的至少一个、以及历史顾客平均等待时长t1以及历史平均就餐时长t3中的至少一个输入到店铺排队等待时长预估算法计算得到新的预估时间；
    所述将所述预估时间传达给顾客进一步包括：将新的预估时间传达给顾客。
  10. 根据权利要求7或8所述的候餐时长实时预估方法，其特征在于：所述店铺排队等待时长预估算法选择xgboost算法。
  11. 一种电子设备，其特征在于，所述电子设备包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行前述任一权利要求7-10所述的候餐时长实时预估方法。
  12. 一种非暂态计算机可读存储介质，所述非暂态计算机可读存储介质存储有至少一可执行指令，所述可执行指令用于使处理器执行前述任一权利要求7-10所述的候餐时长实时预估方法。
  13. 一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序，所述计算机程序包括程序指令，当所述程序指令被处理器执行时，使所述处理器执行前述任一权利要求7-10所述的候餐时长实时预估方法。
PCT/CN2020/080717 2019-03-29 2020-03-23 候餐时长实时预估方法和系统 WO2020199961A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910252658.4A CN109978198B (zh) 2019-03-29 2019-03-29 一种基于大数据及ai技术的候餐时长实时预估系统
CN201910252658.4 2019-03-29

Publications (1)

Publication Number Publication Date
WO2020199961A1 true WO2020199961A1 (zh) 2020-10-08

Family

ID=67081917

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/080717 WO2020199961A1 (zh) 2019-03-29 2020-03-23 候餐时长实时预估方法和系统

Country Status (2)

Country Link
CN (1) CN109978198B (zh)
WO (1) WO2020199961A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113489851A (zh) * 2021-07-02 2021-10-08 拉卡拉支付股份有限公司 信息提示方法、装置、电子设备、存储介质及程序产品
CN114051057A (zh) * 2021-11-01 2022-02-15 北京百度网讯科技有限公司 云设备排队时长的确定方法、装置、电子设备和介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978198B (zh) * 2019-03-29 2021-11-26 时时同云科技(成都)有限责任公司 一种基于大数据及ai技术的候餐时长实时预估系统
CN111369326B (zh) * 2020-03-16 2023-05-23 湖南大学 “拼时间”餐饮管理系统
CN111862438B (zh) * 2020-07-03 2022-02-25 美味不用等（上海）信息科技股份有限公司 餐厅智能叫号排队方法与系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102479400A (zh) * 2010-11-24 2012-05-30 王军 一种用餐排队系统
CN103985186A (zh) * 2014-05-28 2014-08-13 南京亿栋信息科技有限公司 一种用于排队机的等待时间预测方法
US20180121875A1 (en) * 2015-01-05 2018-05-03 Amazon Technologies, Inc. Delivery prediction automation and risk mitigation
CN109214612A (zh) * 2018-11-20 2019-01-15 广东机场白云信息科技有限公司 一种基于xgboost机场客流量时空分布预测方法
CN109978198A (zh) * 2019-03-29 2019-07-05 客如云科技（成都）有限责任公司 一种基于大数据及ai技术的候餐时长实时预估系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100517394C (zh) * 2007-04-24 2009-07-22 暨南大学 一种智能排队叫号系统
CN105303019A (zh) * 2014-07-14 2016-02-03 富士通株式会社 事件预测方法和事件预测设备
CN105184944A (zh) * 2015-08-19 2015-12-23 吴昊 一种餐馆排队信息查询方法、装置及系统
JP7080578B2 (ja) * 2016-11-18 2022-06-06 キヤノン株式会社 情報処理装置、情報処理方法及びプログラム
CN108091029A (zh) * 2017-11-27 2018-05-29 深圳市赛亿科技开发有限公司 餐厅排号管理方法及系统
CN108647827B (zh) * 2018-05-15 2020-03-17 北京三快在线科技有限公司 商户排队时长的预测方法、装置、电子设备及存储介质
CN109087435A (zh) * 2018-08-13 2018-12-25 中国联合网络通信集团有限公司 排队时间的预测方法及排队系统
CN109242152A (zh) * 2018-08-16 2019-01-18 重阳健康数据技术（深圳）有限责任公司 一种智能就诊方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102479400A (zh) * 2010-11-24 2012-05-30 王军 一种用餐排队系统
CN103985186A (zh) * 2014-05-28 2014-08-13 南京亿栋信息科技有限公司 一种用于排队机的等待时间预测方法
US20180121875A1 (en) * 2015-01-05 2018-05-03 Amazon Technologies, Inc. Delivery prediction automation and risk mitigation
CN109214612A (zh) * 2018-11-20 2019-01-15 广东机场白云信息科技有限公司 一种基于xgboost机场客流量时空分布预测方法
CN109978198A (zh) * 2019-03-29 2019-07-05 客如云科技（成都）有限责任公司 一种基于大数据及ai技术的候餐时长实时预估系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113489851A (zh) * 2021-07-02 2021-10-08 拉卡拉支付股份有限公司 信息提示方法、装置、电子设备、存储介质及程序产品
CN114051057A (zh) * 2021-11-01 2022-02-15 北京百度网讯科技有限公司 云设备排队时长的确定方法、装置、电子设备和介质
CN114051057B (zh) * 2021-11-01 2023-11-03 北京百度网讯科技有限公司 云设备排队时长的确定方法、装置、电子设备和介质

Also Published As

Publication number Publication date
CN109978198A (zh) 2019-07-05
CN109978198B (zh) 2021-11-26

Similar Documents

Publication Publication Date Title
WO2020199961A1 (zh) 候餐时长实时预估方法和系统
TWI683272B (zh) 資訊獲取方法、提供方法、裝置及系統、儲存介質
WO2019100738A1 (zh) 多人参与的人机交互方法及装置
US20180096388A1 (en) Promotion information pushing method, apparatus, and system
US20190324779A1 (en) Using salience rankings of entities and tasks to aid computer interpretation of natural language input
US10042548B2 (en) Methods and systems for providing user feedback using an emotion scale
JP6729590B2 (ja) 情報処理装置、情報処理方法、およびプログラム
CN116032663B (zh) 基于边缘设备的隐私数据处理系统、方法、设备及介质
US20180069939A1 (en) Methods and Systems for Viewing User Feedback
JP7488871B2 (ja) 対話推薦方法、装置、電子機器、記憶媒体ならびにコンピュータプログラム
CN104008182A (zh) 社交网络交流影响力的测定方法及系统
KR20210154831A (ko) 딥 뉴럴 네트워크들을 사용하는 사업체에 구애받지 않는 상담 센터 예상된 대기 시간들의 예측
JP5893050B2 (ja) ソーシャル・メデイアにおけるコミュニティを検出する方法、コンピュータ・プログラム、コンピュータ
CN111832308A (zh) 语音识别文本连贯性处理方法和装置
CN114065864B (zh) 联邦学习方法、联邦学习装置、电子设备以及存储介质
CN111460085A (zh) 基于图结构的知识点推荐方法及装置
CN113641807A (zh) 对话推荐模型的训练方法、装置、设备和存储介质
WO2020151548A1 (zh) 关注页面的排序方法及装置
WO2017160357A1 (en) Question and answer interface based on contextual information
CN112507104A (zh) 对话系统获取方法、装置、存储介质及计算机程序产品
CN111242431A (zh) 信息处理方法和装置、构建客服对话工作流的方法和装置
CN116775815B (zh) 对话数据的处理方法、装置、电子设备及存储介质
JP2010044507A (ja) 人物とアバターとの類似度を判定する装置、方法及びプログラム
CN116484880A (zh) 信息处理方法、装置、电子设备及存储介质
CN116521832A (zh) 对话交互方法、装置及系统、电子设备和存储介质

Legal Events

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

Ref document number: 20782463

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20782463

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20782463

Country of ref document: EP

Kind code of ref document: A1