CN111401041A - Problem prediction method and device, electronic equipment and storage medium - Google Patents
Problem prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111401041A CN111401041A CN202010209084.5A CN202010209084A CN111401041A CN 111401041 A CN111401041 A CN 111401041A CN 202010209084 A CN202010209084 A CN 202010209084A CN 111401041 A CN111401041 A CN 111401041A
- Authority
- CN
- China
- Prior art keywords
- historical
- user
- prediction
- preset model
- trained
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A problem prediction method, device, electronic equipment and storage medium, the method obtains the current behavior characteristic of the user and the current state characteristic of the user when detecting the problem that the user needs to consult; inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by acquiring historical input problems of a user in advance and distributing the historical behavior characteristics and the historical state characteristics of the corresponding user as training samples to obtain the trained preset model; the predicted problem is presented to the user. According to the method and the device for predicting the consultation problem of the user, the scheme of a machine learning algorithm is adopted, the trained preset model is utilized, the problem that the user possibly consults with the client personnel is intelligently predicted, the prediction efficiency and the accuracy of the consultation problem of the user in a client system are improved, the labor cost and the time cost are reduced, and the user experience is improved.
Description
Technical Field
The present application relates to the field of computers, and in particular, to a problem prediction method and apparatus, an electronic device, and a storage medium.
Background
With the development of the internet, when a user encounters a problem during operations such as online transaction or after-sale, the user often needs to use a customer service system, and the customer service system is dedicated to solving the problem encountered by the user in the product using process and optimizing the product using experience of the user. At present, a user mainly solves problems by self-help through helping to feed back common problems in a page, accesses a call center or an online customer service, and interactively solves the problems through voice or characters.
In the related art, the problem to be solved by the user is predicted mainly by adopting a statistical-based or rule-based mode, and the method generally needs customer service personnel of a customer service system to predict the problem to be proposed by the user according to the rule or law of the user question analyzed by the customer service personnel according to the past work experience. The method has low problem coverage rate and high requirement on the professional degree of customer service personnel, requires the customer service personnel to summarize experience and maintain and update the problem prediction rule frequently, not only increases the pressure of the customer service personnel, but also increases the time cost and the labor cost, and has poor user experience.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
In order to solve the technical problem, the application provides a problem prediction method, a problem prediction device, an electronic device and a storage medium.
In a first aspect, the present application provides a problem prediction method, comprising the steps of:
when a user is detected to need to consult a problem, acquiring the current behavior characteristics of the user and the current state characteristics of the user;
inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by using a historical input problem of a user obtained in advance and historical behavior characteristics and historical state characteristics of the user corresponding to distribution as training samples to obtain the trained preset model;
and displaying the predicted problem to a user.
With reference to the first aspect, in a first possible implementation manner of the first aspect, the predicting problem is multiple, and the presenting the predicting problem to the user includes:
sequencing the prediction problems by utilizing a preset sequencing learning algorithm to obtain a sequencing result;
screening out at least one prediction problem to be recommended from the sorting result;
and displaying the at least one predicted question to be recommended to a user.
With reference to the first aspect, in a second possible implementation manner of the first aspect, the method further includes:
acquiring historical input questions posed by a plurality of users in a historical period, and acquiring historical behavior characteristics and historical state characteristics corresponding to the historical input questions;
and training the preset model by taking the historical input problems, the historical behavior characteristics and the historical state characteristics of the user as training samples to obtain the trained preset model.
With reference to the first aspect, in a third possible implementation manner of the first aspect, the method further includes:
analyzing the correlation among the historical behavior characteristics by using a preset correlation analysis algorithm to obtain a plurality of correlation values;
and taking the historical behavior characteristics corresponding to the relevance value as the training sample under the condition that the relevance value is greater than a preset threshold value.
With reference to the first aspect, in a fourth possible implementation manner of the first aspect, the historical feature information includes one or more of the following: historical account information, historical order information, historical behavior trace information, information of historical operation pages, context information of historical chat interfaces, historical device types, historical network information and historical access link information.
In a second aspect, the present application provides an issue prediction apparatus, the apparatus comprising:
the system comprises an acquisition unit, a query unit and a processing unit, wherein the acquisition unit is used for acquiring the current behavior characteristics of a user and the current state characteristics of the user when a problem that the user needs to consult is detected;
the problem prediction unit is used for inputting the current behavior characteristics and the current state characteristics into a trained preset model and outputting prediction problems, wherein the preset model is trained by acquiring historical input problems of users in advance and distributing the historical behavior characteristics and the historical state characteristics of the corresponding users as training samples to obtain the trained preset model;
and the question display unit is used for displaying the predicted question to a user.
With reference to the second aspect, in a first possible implementation manner of the second aspect, the predicted problem is multiple, and the problem presentation unit includes:
the problem sorting subunit is used for sorting the predicted problems by utilizing a preset sorting learning algorithm to obtain a sorting result;
the problem screening subunit is used for screening out at least one prediction problem to be recommended from the sorting result;
and the question to be recommended display subunit is used for displaying the at least one predicted question to be recommended to the user.
With reference to the second aspect, in a second possible implementation manner of the second aspect, the apparatus further includes:
the system comprises a characteristic acquisition unit, a processing unit and a processing unit, wherein the characteristic acquisition unit is used for acquiring historical input problems proposed by a plurality of users in a historical period, and acquiring historical behavior characteristics and historical state characteristics corresponding to the historical input problems;
and the model training unit is used for training the preset model by taking the historical input problems, the historical behavior characteristics and the historical state characteristics of the user as training samples to obtain the trained preset model.
In a third aspect, the present application provides an electronic device, comprising: at least one processor, memory, at least one network interface, and a user interface;
the at least one processor, memory, at least one network interface, and user interface are coupled together by a bus system;
the processor is operable to perform the steps of the problem prediction method of the first aspect by calling a program or instructions stored by the memory.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the problem prediction method according to the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the problem prediction method, the problem prediction device, the electronic equipment and the storage medium, when a problem that a user needs to consult is detected, the current behavior characteristics of the user and the current state characteristics of the user are obtained; inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by using a historical input problem of a user obtained in advance and historical behavior characteristics and historical state characteristics of the user corresponding to distribution as training samples to obtain the trained preset model; and displaying the predicted problem to a user. According to the embodiment of the application, a scheme of a machine learning algorithm is adopted, a trained preset model is utilized, when the problem that a user needs to consult is detected, the problem that the user possibly consults client personnel is intelligently forecasted according to the input current behavior characteristic of the user and the input current state characteristic of the user, the preset model is trained by taking the obtained multidimensional historical input problem, historical behavior characteristic and historical state characteristic of the user as training samples, the accuracy of the output result of the preset model is improved, therefore, the forecasting result of the problem that the user needs to consult is obtained in real time, the forecasting efficiency and accuracy of the consultation problem of the user at a client system are improved, the labor cost and the time cost are reduced, and the user experience is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a problem prediction method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating another problem prediction method according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a problem prediction apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic flow chart of a problem prediction method provided in an embodiment of the present application, where the method specifically includes the following steps:
s101, when the problem that a user needs to consult is detected, the current behavior characteristics of the user and the current state characteristics of the user are obtained.
Optionally, when a certain user accesses the customer service system, including a help feedback page of the customer service system, an online customer service, a call center, and other pages, all may be regarded as a question that the user needs to consult, the ID of the user is obtained, and thus the current behavior characteristics of the user and the current state characteristics of the user are queried in each internal business system, where the current behavior characteristics of the user include one or more of the following: behavior trace information, information of an operation page, and context information including, but not limited to, device type, network information, and access link information; the current status characteristics of the user include, but are not limited to, account information and order information.
For example, the behavior track information includes, but is not limited to, a fast forward operation of the user for the play-class video page, a barrage switch operation of the user for the comment-class page, and the like; account information includes, but is not limited to, whether the account is sealed, whether the account is a member account; order information includes, but is not limited to, payment method, payment amount; the contextual information includes, but is not limited to, network status, the channel of the user to access the customer service system, the user's device type, and the like.
Through the acquired multi-dimensional user behavior characteristics and the acquired user account state characteristics, the accuracy and efficiency of problem prediction can be improved.
S102, inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by using historical input problems of users and historical behavior characteristics and historical state characteristics of users corresponding to distribution in advance as training samples, so that the trained preset model is obtained.
S103, displaying the prediction problem to a user.
According to the embodiment of the application, a scheme of a machine learning algorithm is adopted, a trained preset model is utilized, when the problem that a user needs to consult is detected, the problem that the user possibly consults client personnel is intelligently forecasted according to the input current behavior characteristic of the user and the input current state characteristic of the user, the preset model is trained by taking the obtained multidimensional historical input problem, historical behavior characteristic and historical state characteristic of the user as training samples, the accuracy of the output result of the preset model is improved, therefore, the forecasting result of the problem that the user needs to consult is obtained in real time, the forecasting efficiency and accuracy of the consultation problem of the user at a client system are improved, the labor cost and the time cost are reduced, and the user experience is improved.
Optionally, the method further includes:
s11, acquiring historical input questions posed by a plurality of users in a historical period, and acquiring historical behavior characteristics and historical state characteristics corresponding to the historical input questions;
and S12, training the preset model by taking the historical input problems, the historical behavior characteristics and the historical state characteristics of the user as training samples to obtain the trained preset model.
According to the method and the device, historical input problems actively mentioned by the user in the customer service center of the customer service system in the historical period are collected, for example, the problems of user click, text input and work order are included, so that the collected historical problems are wide in range, namely more sample data are collected, the problems that the old user or the new user needs to consult can be predicted, and the accuracy of the prediction effect of the preset model is improved.
Optionally, the historical behavior characteristics include, but are not limited to, historical behavior trace information, information of historical operation pages, historical context information (e.g., historical device types, historical network information, and historical access link information); historical status features include, but are not limited to, historical account information and historical order information.
Optionally, a Bayesian algorithm or a fasttext algorithm is used for training the problem prediction model, the Bayesian algorithm has the advantage of high interpretability, and a scinit-learn open-source framework is selected for model development; the fasttext algorithm has the advantage of higher accuracy, and a fasttext frame of a facebook open source is selected for development; after the problem prediction model training is completed, the trained problem prediction model can be deployed on line, and the problem real-time prediction service is provided.
During training, a training sample is divided into a training set, a verification set and a test set according to a proportion, after a model is trained through the training sample, the model is tested through the test set to obtain a test result, if the test result reaches a preset threshold value, the training of the preset model is stopped, the trained preset model is issued to an online environment, and otherwise, the model is continuously trained.
The embodiment of the application can not only realize the automatic training of the preset model, but also realize the updating of the preset model, for example, collect and calculate the historical problems of the user on the previous day every day, and the historical behavior characteristics and the historical state characteristics corresponding to the historical problems, and form a new training sample with the historical samples, then train the model, test on a test set, obtain the test effect, if the effect reaches the set threshold value, the trained problem prediction model can be issued to the online environment, and the stability of the problem prediction model and the accuracy of the problem prediction can be further improved.
Optionally, the method further includes:
analyzing the correlation among the historical behavior characteristics by using a preset correlation analysis algorithm to obtain a plurality of correlation values;
and taking the historical behavior characteristics corresponding to the relevance value as the training sample under the condition that the relevance value is greater than a preset threshold value.
For example, the preset threshold may be set to 85%, and if the correlation value is 90%, it indicates that the correlation value is greater than the preset threshold, and the training sample is taken as the training sample; if the correlation value is 70%, it indicates that the correlation value is smaller than a preset threshold, and the historical behavior feature is not used as a training sample. The preset threshold value can also be set according to actual requirements, and the embodiment of the application does not limit the preset threshold value.
On one hand, the behavior data of the users are more complicated to collect, and the users need to communicate with all business parties and develop interfaces, and the users also spend time on inquiring the characteristics in real time on line; on the other hand, some behavior data have a small prediction relation to the problem, and the complexity of the preset model and the training difficulty are increased.
Therefore, according to the preset rule, the embodiment of the application executes the filtering operation on the historical behavior characteristics, filters out the data which do not meet the training requirement, and mainly comprises the following two aspects:
in a first aspect: according to business experience, important and relevant behavior data, such as fast forward playing, code stream playing and other behaviors, record of barrage, comment, cashier desk and the like, are collected firstly, and less important behavior data, such as skip among pages of a user, are not collected, so that the calculation amount of the data can be reduced, and the data processing speed is increased;
in a second aspect: the relevance of the historical behavior features is analyzed, the importance and the discrimination of the collected historical behavior features are analyzed through methods such as regularization and correlation analysis, the less important historical behavior features are filtered out, or the less obvious historical behavior features are combined, so that the calculated amount can be reduced, and the acquisition accuracy of the historical behavior features can be improved.
Optionally, the historical status features include one or more of: historical account information and historical order information; the historical behavioral characteristics include one or more of: historical behavior trace information, information of historical operation pages, historical device types, historical network information and historical access link information.
In order to facilitate understanding of the embodiments of the present application, specific examples are described below.
Optionally, as shown in fig. 2, an embodiment of the present application further provides a problem prediction method, where the number of prediction problems is multiple, and the method includes the following steps:
s201, when a problem that a user needs to consult is detected, acquiring current behavior characteristics of the user and current state characteristics of the user.
S202, inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by acquiring historical input problems of a user in advance and distributing historical behavior characteristics and historical state characteristics of the corresponding user as training samples, so that the trained preset model is obtained.
S203, sequencing the prediction problems by using a preset sequencing learning algorithm to obtain a sequencing result.
Optionally, the preset ranking learning algorithm includes, but is not limited to, pointwise, pairwise or listwise, and the problem prediction accuracy can be further improved by using a ranking scheme in which the predicted problems are ranked by the pointwise, pairwise or listwise.
S204, screening out at least one prediction problem to be recommended from the sorting result.
S205, displaying the at least one prediction question to be recommended to the user.
For a call center of a customer service system, because real-time interaction of voice needs to be realized, the value of N to-be-consulted problems is selected to be too large, voice interruption may be caused due to too long data processing time, and user experience is also well influenced, therefore, the embodiment of the application can display the value of N to the user by screening out 3 to-be-recommended prediction problems, or directly display the first prediction problem to the user as the to-be-consulted prediction problem when the probability of sequencing the first prediction problem is high, so that the data processing speed and the matching success rate are improved, and the user experience is improved.
It should be noted that the number of prediction questions to be recommended may be selected according to actual needs, which is not limited in the embodiment of the present application.
As shown in fig. 3, an embodiment of the present application further provides a problem prediction apparatus, where the apparatus includes:
the acquiring unit 31 is configured to acquire a current behavior feature of a user and a current state feature of the user when a user is detected to have a consultation problem;
the problem prediction unit 32 is configured to input the current behavior feature and the current state feature into a trained preset model, and output a prediction problem, where the preset model is trained by using a historical input problem of a user and a historical behavior feature and a historical state feature of a user corresponding to distribution obtained in advance as training samples, so as to obtain the trained preset model;
a question presentation unit 33 for presenting the predicted question to a user.
Optionally, the predicted problem is multiple, and the problem presentation unit includes:
a problem sorting subunit (not shown in the figure) for sorting the predicted problems by using a preset sorting learning algorithm to obtain a sorting result;
a question screening subunit (not shown in the figure) for screening out at least one predicted question to be recommended from the sorting result;
and a to-be-recommended question presentation subunit (not shown in the figure) for presenting the at least one predicted question to be recommended to the user.
Optionally, the apparatus further comprises:
the system comprises a characteristic acquisition unit, a processing unit and a processing unit, wherein the characteristic acquisition unit is used for acquiring historical input problems proposed by a plurality of users in a historical period, and acquiring historical behavior characteristics and historical state characteristics corresponding to the historical input problems;
and the model training unit is used for training the preset model by taking the historical input problems, the historical behavior characteristics and the historical state characteristics of the user as training samples to obtain the trained preset model.
Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps as described in the method embodiments, for example, including:
when a user is detected to need to consult a problem, acquiring the current behavior characteristics of the user and the current state characteristics of the user;
inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by using a historical input problem of a user obtained in advance and historical behavior characteristics and historical state characteristics of the user corresponding to distribution as training samples to obtain the trained preset model;
and displaying the predicted problem to a user.
Fig. 4 is a schematic structural diagram of an electronic device according to another embodiment of the present invention. The electronic device 400 shown in fig. 4 includes: at least one processor 401, memory 402, at least one network interface 404, and other user interfaces 403. The various components in the electronic device 400 are coupled together by a bus system 405. It is understood that the bus system 405 is used to enable connection communication between these components. The bus system 405 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 405 in fig. 4.
The user interface 403 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.
It is understood that the Memory 402 in embodiments of the present invention may be either volatile Memory or non-volatile Memory, or may include both volatile and non-volatile Memory, wherein non-volatile Memory may be Read Only Memory (ROM), Programmable Read Only Memory (PROM), Erasable Programmable Read Only Memory (EPROM), Electrically Erasable Programmable Read Only Memory (EEPROM), or flash Memory volatile Memory may be Random Access Memory (RAM) which functions as an external cache Memory, by way of example but not limitation, many forms of RAM are available, such as Static Random Access Memory (Static RAM, SRAM), Dynamic Random Access Memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory (syncronous DRAM, SDRAM), Double data rate Synchronous Dynamic Random Access Memory (Double data RAM, ddrstate, SDRAM), Enhanced Synchronous DRAM (Enhanced DRAM), or SDRAM L, including, but not limited to, any of the other types of RAM suitable for direct Access, including SDRAM, and RAM, and SDRAM, and RAM, and SDRAM, and RAM.
In some embodiments, memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 4021 and application programs 4022.
The operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is configured to implement various basic services and process hardware-based tasks. The application programs 4022 include various application programs, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. A program for implementing the method according to the embodiment of the present invention may be included in the application 4022.
In this embodiment of the present invention, by calling a program or an instruction stored in the memory 402, specifically, a program or an instruction stored in the application 4022, the processor 401 is configured to execute the method steps provided by the method embodiments, for example, including:
when a user is detected to need to consult a problem, acquiring the current behavior characteristics of the user and the current state characteristics of the user;
inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by using a historical input problem of a user obtained in advance and historical behavior characteristics and historical state characteristics of the user corresponding to distribution as training samples to obtain the trained preset model;
and displaying the predicted problem to a user.
The method disclosed in the above embodiments of the present invention may be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 401. The Processor 401 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402 and completes the steps of the method in combination with the hardware.
For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable logic devices (P L D), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in a plurality of software and/or hardware when implementing the invention.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A problem prediction method, characterized in that it comprises the steps of:
when a user is detected to need to consult a problem, acquiring the current behavior characteristics of the user and the current state characteristics of the user;
inputting the current behavior characteristics and the current state characteristics into a trained preset model, and outputting a prediction problem, wherein the preset model is trained by using a historical input problem of a user obtained in advance and historical behavior characteristics and historical state characteristics of the user corresponding to distribution as training samples to obtain the trained preset model;
and displaying the predicted problem to a user.
2. The method of claim 1, wherein the predicted problem is a plurality of predicted problems, and wherein presenting the predicted problem to the user comprises:
sequencing the prediction problems by utilizing a preset sequencing learning algorithm to obtain a sequencing result;
screening out at least one prediction problem to be recommended from the sorting result;
and displaying the at least one predicted question to be recommended to a user.
3. The method of claim 1, further comprising:
acquiring historical input questions posed by a plurality of users in a historical period, and acquiring historical behavior characteristics and historical state characteristics corresponding to the historical input questions;
and training the preset model by taking the historical input problems, the historical behavior characteristics and the historical state characteristics of the user as training samples to obtain the trained preset model.
4. The method of claim 3, further comprising:
analyzing the correlation among the historical behavior characteristics by using a preset correlation analysis algorithm to obtain a plurality of correlation values;
and taking the historical behavior characteristics corresponding to the relevance value as the training sample under the condition that the relevance value is greater than a preset threshold value.
5. The method of any of claims 1-4, wherein the historical state features include one or more of: historical account information and historical order information; the historical behavioral characteristics include one or more of: historical behavior trace information, information of historical operation pages, historical device types, historical network information and historical access link information.
6. An issue prediction apparatus, the apparatus comprising:
the system comprises an acquisition unit, a query unit and a processing unit, wherein the acquisition unit is used for acquiring the current behavior characteristics of a user and the current state characteristics of the user when a problem that the user needs to consult is detected;
the problem prediction unit is used for inputting the current behavior characteristics and the current state characteristics into a trained preset model and outputting prediction problems, wherein the preset model is trained by acquiring historical input problems of users in advance and distributing the historical behavior characteristics and the historical state characteristics of the corresponding users as training samples to obtain the trained preset model;
and the question display unit is used for displaying the predicted question to a user.
7. The apparatus of claim 6, wherein the predicted problem is a plurality of problems, and the problem presentation unit comprises:
the problem sorting subunit is used for sorting the predicted problems by utilizing a preset sorting learning algorithm to obtain a sorting result;
the problem screening subunit is used for screening out at least one prediction problem to be recommended from the sorting result;
and the question to be recommended display subunit is used for displaying the at least one predicted question to be recommended to the user.
8. The apparatus of claim 6, further comprising:
the system comprises a characteristic acquisition unit, a processing unit and a processing unit, wherein the characteristic acquisition unit is used for acquiring historical input problems proposed by a plurality of users in a historical period, and acquiring historical behavior characteristics and historical state characteristics corresponding to the historical input problems;
and the model training unit is used for training the preset model by taking the historical input problems, the historical behavior characteristics and the historical state characteristics of the user as training samples to obtain the trained preset model.
9. An electronic device, characterized in that the electronic device comprises: at least one processor, memory, at least one network interface, and a user interface;
the at least one processor, memory, at least one network interface, and user interface are coupled together by a bus system;
the processor is operable to perform the steps of the problem prediction method of any one of claims 1 to 5 by calling a program or instructions stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the problem prediction method according to one of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010209084.5A CN111401041A (en) | 2020-03-23 | 2020-03-23 | Problem prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010209084.5A CN111401041A (en) | 2020-03-23 | 2020-03-23 | Problem prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111401041A true CN111401041A (en) | 2020-07-10 |
Family
ID=71431137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010209084.5A Pending CN111401041A (en) | 2020-03-23 | 2020-03-23 | Problem prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401041A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307047A (en) * | 2020-10-29 | 2021-02-02 | 中国平安财产保险股份有限公司 | Production problem processing method, device, equipment and storage medium |
| CN113158102A (en) * | 2021-02-23 | 2021-07-23 | 北京三快在线科技有限公司 | Page configuration method and device, electronic equipment and computer readable medium |
| CN113239173A (en) * | 2021-06-09 | 2021-08-10 | 深圳集智数字科技有限公司 | Method and device for processing question and answer data, storage medium and electronic equipment |
| CN113256180A (en) * | 2021-07-07 | 2021-08-13 | 杭州实在智能科技有限公司 | Customer service work order information intelligent dynamic loading method and system based on machine learning |
| CN113342862A (en) * | 2021-04-19 | 2021-09-03 | 北京房江湖科技有限公司 | Query recommendation method and device, electronic equipment and readable storage medium |
| CN113537297A (en) * | 2021-06-22 | 2021-10-22 | 同盾科技有限公司 | Behavior data prediction method and device |
| CN113761139A (en) * | 2020-08-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Intention prejudging method and device |
| CN113962662A (en) * | 2021-10-27 | 2022-01-21 | 中国银行股份有限公司 | Card punching reminding method and device, electronic equipment and storage medium |
| CN114130038A (en) * | 2021-11-25 | 2022-03-04 | 浙江小族智能科技有限公司 | Amusement vehicle and control method and device thereof, storage medium and terminal |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108874823A (en) * | 2017-05-12 | 2018-11-23 | 阿里巴巴集团控股有限公司 | The implementation method and device of intelligent customer service |
| CN110162609A (en) * | 2019-04-11 | 2019-08-23 | 阿里巴巴集团控股有限公司 | For recommending the method and device asked questions to user |
| WO2019174395A1 (en) * | 2018-03-13 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for information recommendation, and device |
| CN110738527A (en) * | 2019-10-17 | 2020-01-31 | 中国建设银行股份有限公司 | feature importance ranking method, device, equipment and storage medium |
-
2020
- 2020-03-23 CN CN202010209084.5A patent/CN111401041A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108874823A (en) * | 2017-05-12 | 2018-11-23 | 阿里巴巴集团控股有限公司 | The implementation method and device of intelligent customer service |
| WO2019174395A1 (en) * | 2018-03-13 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for information recommendation, and device |
| CN110162609A (en) * | 2019-04-11 | 2019-08-23 | 阿里巴巴集团控股有限公司 | For recommending the method and device asked questions to user |
| CN110738527A (en) * | 2019-10-17 | 2020-01-31 | 中国建设银行股份有限公司 | feature importance ranking method, device, equipment and storage medium |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113761139A (en) * | 2020-08-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Intention prejudging method and device |
| CN112307047B (en) * | 2020-10-29 | 2023-07-14 | 中国平安财产保险股份有限公司 | Production problem processing method, device, equipment and storage medium |
| CN112307047A (en) * | 2020-10-29 | 2021-02-02 | 中国平安财产保险股份有限公司 | Production problem processing method, device, equipment and storage medium |
| CN113158102A (en) * | 2021-02-23 | 2021-07-23 | 北京三快在线科技有限公司 | Page configuration method and device, electronic equipment and computer readable medium |
| CN113342862A (en) * | 2021-04-19 | 2021-09-03 | 北京房江湖科技有限公司 | Query recommendation method and device, electronic equipment and readable storage medium |
| CN113342862B (en) * | 2021-04-19 | 2024-05-07 | 贝壳找房(北京)科技有限公司 | Query recommendation method and device, electronic equipment and readable storage medium |
| CN113239173A (en) * | 2021-06-09 | 2021-08-10 | 深圳集智数字科技有限公司 | Method and device for processing question and answer data, storage medium and electronic equipment |
| CN113239173B (en) * | 2021-06-09 | 2023-12-12 | 深圳集智数字科技有限公司 | Question-answer data processing method and device, storage medium and electronic equipment |
| CN113537297A (en) * | 2021-06-22 | 2021-10-22 | 同盾科技有限公司 | Behavior data prediction method and device |
| CN113256180A (en) * | 2021-07-07 | 2021-08-13 | 杭州实在智能科技有限公司 | Customer service work order information intelligent dynamic loading method and system based on machine learning |
| CN113962662A (en) * | 2021-10-27 | 2022-01-21 | 中国银行股份有限公司 | Card punching reminding method and device, electronic equipment and storage medium |
| CN114130038A (en) * | 2021-11-25 | 2022-03-04 | 浙江小族智能科技有限公司 | Amusement vehicle and control method and device thereof, storage medium and terminal |
| CN114130038B (en) * | 2021-11-25 | 2023-08-22 | 浙江小族智能科技有限公司 | Amusement vehicle, control method and device thereof, storage medium and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401041A (en) | Problem prediction method and device, electronic equipment and storage medium | |
| CN108628741B (en) | Webpage testing method and device, electronic equipment and medium | |
| US20210158711A1 (en) | Guiding creation of an electronic survey | |
| US11016877B2 (en) | Remote virtual code tracking of participant activities at a website | |
| US11113721B2 (en) | Dynamic sentiment-based mapping of user journeys | |
| Kroehne et al. | How to conceptualize, represent, and analyze log data from technology-based assessments? A generic framework and an application to questionnaire items | |
| US11294972B2 (en) | Generating sequential segments with pre-sequence and post-sequence analytics data | |
| US10812627B2 (en) | Frontend process mining | |
| Callegaro | Paradata in web surveys | |
| US11709875B2 (en) | Prioritizing survey text responses | |
| Heymann et al. | Turkalytics: analytics for human computation | |
| US20210398164A1 (en) | System and method for analyzing and predicting emotion reaction | |
| US20210035132A1 (en) | Predicting digital survey response quality and generating suggestions to digital surveys | |
| US9830148B1 (en) | Providing user-specific source code alert information | |
| CN104993962A (en) | Method and system for acquiring use state of terminal | |
| CN111400586A (en) | Group display method, terminal, server, system and storage medium | |
| US20210256545A1 (en) | Summarizing and presenting recommendations of impact factors from unstructured survey response data | |
| Fottrell et al. | Probabilistic methods for verbal autopsy interpretation: InterVA robustness in relation to variations in a priori probabilities | |
| US20150095202A1 (en) | Recommending Product Groups in Ecommerce | |
| US20130036367A1 (en) | Updating a user Interface | |
| CN110674404A (en) | Link information generation method, device, system, storage medium and electronic equipment | |
| US11715121B2 (en) | Computer system and method for electronic survey programming | |
| CN111200639B (en) | Information pushing method and device based on user operation behavior and electronic equipment | |
| CN112686705A (en) | Method and device for predicting sales effect data and electronic equipment | |
| Cheng et al. | Website analytics for government user behavior during COVID-19 pandemic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |