CN111475630A - Information processing method and device and electronic equipment - Google Patents
Information processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN111475630A CN111475630A CN202010247348.6A CN202010247348A CN111475630A CN 111475630 A CN111475630 A CN 111475630A CN 202010247348 A CN202010247348 A CN 202010247348A CN 111475630 A CN111475630 A CN 111475630A
- Authority
- CN
- China
- Prior art keywords
- question
- answer
- user
- generating
- request
- 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.)
- Granted
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 17
- 238000003672 processing method Methods 0.000 title abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 10
- 230000006399 behavior Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 230000006854 communication Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 3
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Computer Interaction (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an information processing method and device and electronic equipment. One embodiment of the method comprises: acquiring a request problem of a user; processing the request problem by using an artificial intelligence training model to obtain a first processing result; if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question; and feeding back the generated second question, the first answer and the second answer. According to the embodiment of the invention, the one-time solution rate is improved through repeated access behaviors of the user, so that the user can obtain information enough for solving the problem in the one-time access process without accessing the intelligent customer service system again, and the experience degree of the user is improved.
Description
Technical Field
The present invention relates to the field of intelligent control technologies, and in particular, to an information processing method and apparatus, and an electronic device.
Background
In the prior art, after inquiring about a question from the smart customer service system, a user may also ask another question related to the question again, and therefore, the user needs to access the smart customer service system many times, which causes much inconvenience.
One important criterion for an intelligent customer service system is one-time resolution. The one-time solution rate is more and more emphasized by enterprises, and the enterprise considers the one-time problem solving capability as a competitive advantage of the enterprise in the industry, so that the method not only can save human resources and reduce operation cost for the enterprise, but also can improve the image and create more sales opportunities for the enterprise.
Disclosure of Invention
In view of this, embodiments of the present invention provide an information processing method, an information processing apparatus, and an electronic device, which can effectively improve a one-time resolution.
To achieve the above object, according to a first aspect of embodiments of the present invention, there is provided an information processing method, including: acquiring a request problem of a user; processing the request problem by using an artificial intelligence training model to obtain a first processing result; if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question; and feeding back the generated second question, the first answer and the second answer.
Optionally, if the first processing result indicates that the requested question satisfies a specific condition, determining that the requested question is a first question, and generating a second question associated with the first question, and a first answer corresponding to the first question and a second answer corresponding to the second question, includes: if the first processing result represents that the request problem meets a specific condition, determining that the request problem is a first problem; generating a second question associated with the first question according to the first question; processing the first question and the second question by using a question-answering model to obtain a second processing result; and if the second processing result represents that the first question and the second question both pass the test, generating a first answer corresponding to the first question and a second answer corresponding to the second question.
Optionally, the generating, according to the first question, a second question associated with the first question includes: according to the first question, selecting a question data set with the first question from a question-answering library to generate a plurality of question data sets, wherein each question in the question data sets has corresponding access time, and the first access question corresponds to the first access time; selecting a problem with access time after first access time and adjacent to the first access time from each problem data set of the plurality of problem data sets as a second candidate problem, and generating a plurality of second candidate problems; calculating the weight of each second candidate question in the plurality of second candidate questions by using an algorithm, and determining the second candidate question with the weight meeting a preset threshold value as the second question associated with the first question.
Optionally, the selecting, from each of the plurality of question data sets, a question having an access time after a first access time and adjacent to the first access time as a second candidate question, and generating a plurality of second candidate questions includes: selecting a question with an access time after the first access time from each question data set of the plurality of question data sets as a second preselected question, and generating a plurality of second preselected question data sets; selecting a second preselected issue adjacent to the first visit time from each of the plurality of second preselected issue data sets as a second candidate issue, generating a plurality of second candidate issues.
Optionally, the selecting, according to the first question, a question data set having the first question from a question-and-answer library to generate a plurality of question data sets includes: according to the first question, selecting a repeated access user accessing the first question from a question-answering library as a repeated user, and generating a plurality of repeated users; and sequencing all the questions accessed by each repeated user in the multiple repeated users according to the access time to generate multiple question data sets.
Optionally, the selecting, according to the first question, a repeat-access user who accesses the first question from a question-and-answer library as a repeat user, and generating a plurality of repeat users includes: selecting all users accessing the first question from a question and answer library; and selecting the repeated access user from all the users as a repeated user to generate a plurality of repeated users.
Optionally, feeding back the generated second question, the first answer, and the second answer includes: feeding back the generated first answer to the user while pushing the second question; receiving a request of the user for the second question, and determining whether the user has the second question according to the request of the user; and if the user has the second question, feeding back the generated second answer to the user.
To achieve the above object, according to a second aspect of the embodiments of the present invention, there is also provided an information processing apparatus including: the acquisition module is used for acquiring a request problem of a user; the artificial intelligence training module is used for processing the request problem by utilizing an artificial intelligence training model to obtain a first processing result; a generating module, configured to determine that the requested question is a first question if the first processing result indicates that the requested question meets a specific condition, and generate a second question associated with the first question, and a first answer corresponding to the first question and a second answer corresponding to the second question; and the feedback module feeds back the generated second question, the first answer and the second answer.
Optionally, the generating module includes: the determining unit is used for determining that the request problem is a first problem if the first processing result represents that the request problem meets a specific condition; a first generating unit, configured to generate a second question associated with the first question according to the first question; the question-answering unit is used for processing the first question and the second question by using a question-answering model to obtain a second processing result; and a second generating unit, configured to generate a first answer corresponding to the first question and a second answer corresponding to the second question if the second processing result indicates that both the first question and the second question pass the test.
To achieve the above object, according to a third aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of information processing according to the first aspect.
Based on the technical scheme, the acquired request problem is processed by using the artificial intelligence training model, the request problem is determined to be a first problem according to a processing result, and then a second problem associated with the first problem, a first answer corresponding to the first problem and a second answer corresponding to the second problem are generated; and finally, the generated second question, the first answer and the second answer are fed back to the user, so that the user can obtain enough information for solving the problem in the process of one-time access without accessing the intelligent customer service system again, the efficiency of one-time problem solving is improved, and the experience degree of the user is improved.
Further effects of the above-described non-conventional alternatives will be described below in connection with specific embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein: in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a flow chart of a method of information processing according to an embodiment of the present invention;
FIG. 2 is a diagram of an information processing apparatus according to an embodiment of the present invention;
FIG. 3 is a diagram of an exemplary system architecture in which embodiments of the present invention may be employed;
fig. 4 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The embodiment of the invention aims to process the request question of the user through the artificial intelligence training model so as to determine the request question as a first question and generate a second question, a first answer and a second answer which are associated with the first question, so that the user can obtain answer information of a plurality of questions in one request, the one-time solution rate of customer service is improved, and the experience degree of the user is further improved.
Fig. 1 is a flowchart of an embodiment of a method for processing information, the method including:
s101, acquiring a request problem of a user;
specifically, the request question of the user can be obtained through voice or text input and the like.
S102, processing the request problem by using an artificial intelligence training model to obtain a first processing result;
specifically, the artificial intelligence training model is trained in advance by using training samples.
S103, if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question;
specifically, if the first processing result represents that the request problem meets a specific condition, determining that the request problem is a first problem; generating a second question associated with the first question according to the first question; processing the first question and the second question by using a question-answering model to obtain a second processing result; and if the second processing result represents that the first question and the second question both pass the test, generating a first answer corresponding to the first question and a second answer corresponding to the second question.
Generating, from the first question, a second question associated with the first question, including: according to a first question, selecting a question data set with the first question from a question-answering library, and generating a plurality of question data sets, wherein each question in the question data sets has corresponding access time, and the first question corresponds to the first access time; selecting a problem with access time after the first access time and adjacent to the first access time from each problem data set of the plurality of problem data sets as a second candidate problem, and generating a plurality of second candidate problems; and calculating the weight of each second candidate question in the plurality of second candidate questions by using an algorithm, and determining the second candidate question with the weight meeting a preset threshold value as the second question associated with the first question.
Selecting a question with an access time after the first access time and adjacent to the first access time from each question data set of the plurality of question data sets as a second candidate question, and generating a plurality of second candidate questions, wherein the second candidate questions comprise: selecting a question with an access time after the first access time from each question data set of the plurality of question data sets as a second pre-selection question, and generating a plurality of second pre-selection question data sets; a second preselected question adjacent to the first visit time is selected from each of a plurality of second preselected question data sets as a second candidate question, generating a plurality of second candidate questions.
According to the first question, selecting a question data set with the first question from a question-and-answer library, and generating a plurality of question data sets, wherein the question data sets comprise: according to the first question, selecting a repeated access user accessing the first question from a question-answering library as a repeated user, and generating a plurality of repeated users; and sequencing all the problems accessed by each repeated user in the multiple repeated users according to the access time to generate multiple problem data sets.
According to the first question, selecting repeated access users accessing the first question from a question-answer library as repeated users, and generating a plurality of repeated users, wherein the method comprises the following steps: selecting all users accessing the first question from a question-and-answer library; and selecting the repeated access user from all the users as a repeated user to generate a plurality of repeated users.
For example, the first problem is the "connect wifi problem". And selecting all users who have access to the wifi connection question from the question and answer library. And selecting repeated users such as the user A, the user B and the user C which repeatedly access the question-answering library from all the users. Sequencing all the problems accessed by the user A from front to back according to the access time to obtain a first problem data set, wherein the first problem data set has four problems; all questions accessed by the user B are sequentially ordered from front to back according to the access time to obtain a second question data set, and the second question data set has five questions; and all questions accessed by the user C are sequenced from front to back according to the access time to obtain a third question data set, and the third question data set has six questions. Selecting a problem with the access time after the first access time from the first problem data set as a second preselection problem to obtain three second preselection problems, and further generating a second preselection problem data set corresponding to the first problem data set; selecting a problem with the access time after the first access time from the second problem data set as a second preselection problem to obtain a second preselection problem, and further generating a second preselection problem data set corresponding to the second problem data set; and selecting the problem with the access time after the first access time from the third problem data set as a second pre-selection problem, obtaining two second pre-selection problems, and further generating a second pre-selection problem data set corresponding to the third problem data set. Selecting a second preselected question adjacent to the first visit time from each of the three second preselected question data sets as a second candidate question, and generating three second candidate questions. The weight of each of the three second candidate questions is calculated using an algorithm, for example, the weights of the three second candidate questions are 0.5, 0.2, and 0.7, respectively. And determining a second candidate question with the weight larger than the preset threshold as a second question associated with the first question, wherein the second candidate question with the weight of 0.7 is determined as a second question and the second question is a 'black screen question' because the preset threshold is 0.6.
It should be noted that the second question associated with the first question may be multiple, and the number of the second questions is determined by the size of the preset threshold. For example, an algorithm is used to calculate the weight of each of the three second candidate questions, with weights of 0.5, 0.2, and 0.7, respectively. When the preset threshold is 0.4, two second problems are associated with the first problem; when the preset threshold is 0.6, there is only one second problem associated with the first problem.
It should be noted that the access time corresponding to the first question in each question data set may be the same or different.
Here, the specific condition is that the number of words of the request question is not less than the preset number of words and the similarity score between the request question and the first question satisfies a preset similarity threshold.
And S104, feeding back the generated second question, the first answer and the second answer.
Specifically, the generated first answer is fed back to the user while the second question is pushed; receiving a request of the user for the second question to determine whether the user has the second question according to the request of the user; and if the user has the second problem, feeding back the generated second answer to the user, and if the user does not have the second problem, not pushing the second answer to the user and ending the operation.
In addition, the second question and the second answer can be pushed to the user while the generated first answer is fed back to the user, and the request of the user for the second question is not required to be confirmed.
For example, users often revisit questions about consulting the black screen after asking a wifi connection question. And the weight of the phenomenon is very high, so that the intelligent customer service system can actively inquire whether the screen blacking phenomenon exists or directly provide answers to the screen blacking problem to the user after the wifi problem is pushed and connected. Therefore, the user can obtain the information which can solve the problem sufficiently in the process of one-time access, so that the user does not need to access the intelligent customer service system again, and the experience degree of the user is improved.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and the inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
The embodiment of the invention obtains a first processing result by obtaining the request problem of the user and processing the request problem by utilizing an artificial intelligence training model; if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question; and finally, feeding back the generated second question, the first answer and the second answer to the user.
FIG. 2 is a diagram illustrating an information processing apparatus according to an embodiment of the present invention; the apparatus 200, comprising: an obtaining module 201, configured to obtain a request question of a user; the artificial intelligence training module 202 is used for processing the request problem by using an artificial intelligence training model to obtain a first processing result; a generating module 203, configured to determine that the request question is a first question if the first processing result indicates that the request question meets a specific condition, and generate a second question associated with the first question, and a first answer corresponding to the first question and a second answer corresponding to the second question; the feedback module 204 feeds back the generated second question, the first answer, and the second answer.
In an alternative embodiment, the generating module comprises: the determining unit is used for determining that the request problem is a first problem if the first processing result represents that the request problem meets a specific condition; a first generating unit, configured to generate a second question associated with the first question according to the first question; the question-answering unit is used for processing the first question and the second question by using a question-answering model to obtain a second processing result; and the second generating unit is used for generating a first answer corresponding to the first question and a second answer corresponding to the second question if the second processing result represents that the first question and the second question both pass the test.
In an alternative embodiment, the first generating unit includes: the first sub-generation unit is used for selecting a question data set with a first question from the question-answering library according to the first question and generating a plurality of question data sets, wherein each question in the question data sets has corresponding access time, and the first question corresponds to the first access time; a second sub-generation unit, configured to select, from each of the plurality of problem data sets, a problem whose access time is after the first access time and adjacent to the first access time as a second candidate problem, and generate a plurality of second candidate problems; a sub-calculation unit for calculating a weight of each of the plurality of second candidate questions using an algorithm; a sub-determination unit configured to determine a second candidate question whose weight satisfies a preset threshold as a second question associated with the first question.
In an alternative embodiment, the second sub-generation unit includes: a first unit, configured to select, from each of the plurality of question data sets, a question whose access time is after the first access time as a second pre-selection question, and generate a plurality of second pre-selection question data sets; a second unit for selecting a second preselected question adjacent to the first visit time from each of a plurality of second preselected question data sets as a second candidate question, generating a plurality of second candidate questions.
In an alternative embodiment, the first sub-generation unit includes: the first unit is used for selecting a repeated access user accessing the first question from the question-answering library as a repeated user according to the first question and generating a plurality of repeated users; and the second unit is used for sequencing all the problems accessed by each repeated user in the multiple repeated users according to the access time to generate multiple problem data sets.
In an alternative embodiment, the first subunit comprises: the selecting unit is used for selecting all users accessing the first question from the question-answering library; and the generating unit is used for selecting the repeated access user from all the users as a repeated user and generating a plurality of repeated users.
The device can execute the information processing method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the information processing method. For details of the information processing method provided in the embodiment of the present invention, reference may be made to the following description.
As shown in fig. 3, the system architecture 300 may include terminal devices 301, 302, 303, a network 304 and a server 305 for an exemplary system architecture diagram to which embodiments of the present invention may be applied. The network 304 serves as a medium for providing communication links between the terminal devices 301, 302, 303 and the server 305. Network 304 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal device 301, 302, 303 to interact with the server 305 via the network 304 to receive or send messages or the like. The terminal devices 301, 302, 303 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 301, 302, 303 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 305 may be a server providing various services, such as a background management server (for example only) providing support for click events generated by users using the terminal devices 301, 302, 303. The background management server may analyze and perform other processing on the received click data, text content, and other data, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the processing method provided in the embodiment of the present application is generally executed by the server 305, and accordingly, the question answering device is generally disposed in the server 305.
It should be understood that the number of terminal devices, networks, and servers in fig. 3 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 4, shown is a block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment. The terminal device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 4, a computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM)403, in the RAM 403, various programs and data required for the operation of the system 400 are also stored, the CPU 401, the ROM 402, and the RAM 403 are connected to each other by a bus 404 AN input/output (I/O) interface 405 is also connected to the bus 404, AN input section 406 including a keyboard, a mouse, and the like, AN output section 407 including a Cathode Ray Tube (CRT), a liquid crystal display (L CD), and the like, a speaker, and the like, a storage section 408 including a hard disk, and the like, and a communication section 409 including a network such as a L AN card, a modem, and the like are connected to the I/O interface 405, a communication section 409 performs communication processes via a network such as the internet, a drive 410 is also connected to the I/O interface 405, a removable medium 411 such as a magnetic disk, a magneto-optical disk, a semiconductor memory, and the like are installed on a drive 410 as necessary to facilitate the computer to be read out.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program performs the above-described functions defined in the system of the present invention when executed by a Central Processing Unit (CPU) 401.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a sending module, an obtaining module, a determining module, and a first processing module. The names of these modules do not in some cases constitute a limitation on the unit itself, and for example, the sending module may also be described as a "module that sends a picture acquisition request to a connected server".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: s101, acquiring a request problem of a user; s102, processing the request problem by using an artificial intelligence training model to obtain a first processing result; s103, if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question; and S104, feeding back the generated second question, the first answer and the second answer.
The embodiment of the invention obtains a first processing result by obtaining the request problem of the user and processing the request problem by utilizing an artificial intelligence training model; if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question; and finally, feeding back the generated second question, the first answer and the second answer to the user. Therefore, the embodiment of the invention improves the one-time resolution rate through repeated access behaviors of the user, so that the user can obtain information enough for solving the problem in the one-time access process without accessing the intelligent customer service system again, and the experience degree of the user is improved.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only an exemplary embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present invention, and the present invention shall be covered thereby. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A method of information processing, comprising:
acquiring a request problem of a user;
processing the request problem by using an artificial intelligence training model to obtain a first processing result;
if the first processing result represents that the request question meets a specific condition, determining that the request question is a first question, and generating a second question associated with the first question, a first answer corresponding to the first question and a second answer corresponding to the second question;
and feeding back the generated second question, the first answer and the second answer.
2. The method of claim 1, wherein determining that the requested question is a first question and generating a second question associated with the first question and a first answer corresponding to the first question and a second answer corresponding to the second question if the first processing result indicates that the requested question satisfies a certain condition comprises:
if the first processing result represents that the request problem meets a specific condition, determining that the request problem is a first problem;
generating a second question associated with the first question according to the first question;
processing the first question and the second question by using a question-answering model to obtain a second processing result;
and if the second processing result represents that the first question and the second question both pass the test, generating a first answer corresponding to the first question and a second answer corresponding to the second question.
3. The method of claim 2, wherein generating, from the first question, a second question associated with the first question comprises:
according to the first question, selecting a question data set with the first question from a question-answering library to generate a plurality of question data sets, wherein each question in the question data sets has corresponding access time, and the first access question corresponds to the first access time;
selecting a problem with access time after first access time and adjacent to the first access time from each problem data set of the plurality of problem data sets as a second candidate problem, and generating a plurality of second candidate problems;
calculating a weight for each of the plurality of second candidate questions using an algorithm;
determining a second candidate question whose weight satisfies a preset threshold as a second question associated with the first question.
4. The method of claim 3, wherein selecting a question from each question data set of the plurality of question data sets having an access time after a first access time and adjacent to the first access time as a second candidate question, and generating a plurality of second candidate questions comprises:
selecting a question with an access time after the first access time from each question data set of the plurality of question data sets as a second preselected question, and generating a plurality of second preselected question data sets;
selecting a second preselected issue adjacent to the first visit time from each of the plurality of second preselected issue data sets as a second candidate issue, generating a plurality of second candidate issues.
5. The method of claim 3, wherein selecting a question data set having a first question from a question and answer library based on the first question, and generating a plurality of question data sets comprises:
according to the first question, selecting a repeated access user accessing the first question from a question-answering library as a repeated user, and generating a plurality of repeated users;
and sequencing all the questions accessed by each repeated user in the multiple repeated users according to the access time to generate multiple question data sets.
6. The method of claim 5, wherein selecting, as the repeat user, the repeat user accessing the first question from a question and answer library according to the first question, and generating a plurality of repeat users comprises:
selecting all users accessing the first question from a question and answer library;
and selecting the repeated access user from all the users as a repeated user to generate a plurality of repeated users.
7. The method of claim 1 or 6, wherein feeding back the generated second question, first answer, and second answer comprises:
feeding back the generated first answer to the user while pushing the second question;
receiving a request of the user for the second question, and determining whether the user has the second question according to the request of the user;
and if the user has the second question, feeding back the generated second answer to the user.
8. An information processing apparatus characterized by comprising:
the acquisition module is used for acquiring a request problem of a user;
the artificial intelligence training module is used for processing the request problem by utilizing an artificial intelligence training model to obtain a first processing result;
a generating module, configured to determine that the requested question is a first question if the first processing result indicates that the requested question meets a specific condition, and generate a second question associated with the first question, and a first answer corresponding to the first question and a second answer corresponding to the second question;
and the feedback module feeds back the generated second question, the first answer and the second answer.
9. The apparatus of claim 8, wherein the generating module comprises:
the determining unit is used for determining that the request problem is a first problem if the first processing result represents that the request problem meets a specific condition;
a first generating unit, configured to generate a second question associated with the first question according to the first question;
the question-answering unit is used for processing the first question and the second question by using a question-answering model to obtain a second processing result;
and a second generating unit, configured to generate a first answer corresponding to the first question and a second answer corresponding to the second question if the second processing result indicates that both the first question and the second question pass the test.
10. An electronic device, comprising: one or more processors; a storage device to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010247348.6A CN111475630B (en) | 2020-03-31 | 2020-03-31 | Information processing method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010247348.6A CN111475630B (en) | 2020-03-31 | 2020-03-31 | Information processing method and device and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111475630A true CN111475630A (en) | 2020-07-31 |
CN111475630B CN111475630B (en) | 2024-06-21 |
Family
ID=71750384
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010247348.6A Active CN111475630B (en) | 2020-03-31 | 2020-03-31 | Information processing method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111475630B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107357855A (en) * | 2017-06-29 | 2017-11-17 | 北京神州泰岳软件股份有限公司 | Support the intelligent answer method and device of scene relating |
CN107800617A (en) * | 2017-11-07 | 2018-03-13 | 北京小米移动软件有限公司 | Question processing method and device |
CN108121800A (en) * | 2017-12-21 | 2018-06-05 | 北京百度网讯科技有限公司 | Information generating method and device based on artificial intelligence |
CN109697228A (en) * | 2018-12-13 | 2019-04-30 | 平安科技(深圳)有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
US20190147353A1 (en) * | 2017-11-15 | 2019-05-16 | International Business Machines Corporation | Watched hypothesis for deep question answering |
CN109829048A (en) * | 2019-01-23 | 2019-05-31 | 平安科技(深圳)有限公司 | Electronic device, interview householder method and computer readable storage medium |
CN110188205A (en) * | 2019-05-08 | 2019-08-30 | 三角兽(北京)科技有限公司 | A kind of update method and device of intelligent customer service system knowledge base |
-
2020
- 2020-03-31 CN CN202010247348.6A patent/CN111475630B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107357855A (en) * | 2017-06-29 | 2017-11-17 | 北京神州泰岳软件股份有限公司 | Support the intelligent answer method and device of scene relating |
CN107800617A (en) * | 2017-11-07 | 2018-03-13 | 北京小米移动软件有限公司 | Question processing method and device |
US20190147353A1 (en) * | 2017-11-15 | 2019-05-16 | International Business Machines Corporation | Watched hypothesis for deep question answering |
CN108121800A (en) * | 2017-12-21 | 2018-06-05 | 北京百度网讯科技有限公司 | Information generating method and device based on artificial intelligence |
CN109697228A (en) * | 2018-12-13 | 2019-04-30 | 平安科技(深圳)有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
CN109829048A (en) * | 2019-01-23 | 2019-05-31 | 平安科技(深圳)有限公司 | Electronic device, interview householder method and computer readable storage medium |
CN110188205A (en) * | 2019-05-08 | 2019-08-30 | 三角兽(北京)科技有限公司 | A kind of update method and device of intelligent customer service system knowledge base |
Also Published As
Publication number | Publication date |
---|---|
CN111475630B (en) | 2024-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
CN109190114B (en) | Method and device for generating reply information | |
CN109829164B (en) | Method and device for generating text | |
CN108933695B (en) | Method and apparatus for processing information | |
US11706172B2 (en) | Method and device for sending information | |
CN113971243A (en) | Data processing method, system, equipment and storage medium applied to questionnaire survey | |
CN110866040A (en) | User portrait generation method, device and system | |
CN111062572B (en) | Task allocation method and device | |
CN109992719B (en) | Method and apparatus for determining push priority information | |
CN107885872B (en) | Method and device for generating information | |
CN114297476A (en) | Questionnaire survey method, system, electronic equipment and storage medium based on user tags | |
KR20210080561A (en) | Consulting information processing method and device | |
CN111125502B (en) | Method and device for generating information | |
CN110971983B (en) | Video question answering method, equipment and storage medium | |
CN111475630B (en) | Information processing method and device and electronic equipment | |
CN111694932A (en) | Conversation method and device | |
CN111435381A (en) | Request distribution method and device | |
CN111131359A (en) | Method and apparatus for generating information | |
CN110881056A (en) | Method and device for pushing information | |
CN110888583B (en) | Page display method, system and device and electronic equipment | |
CN111176982B (en) | Test interface generation method and device | |
CN112307324B (en) | Information processing method, device, equipment and medium | |
WO2020078049A1 (en) | User information processing method and device, server, and readable medium | |
CN114610895A (en) | Work order pushing method and device, electronic equipment and storage medium | |
CN111125501B (en) | Method and device for processing information |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |