CN113806500A - Information processing method and device and computer equipment - Google Patents
Information processing method and device and computer equipment Download PDFInfo
- Publication number
- CN113806500A CN113806500A CN202110180461.1A CN202110180461A CN113806500A CN 113806500 A CN113806500 A CN 113806500A CN 202110180461 A CN202110180461 A CN 202110180461A CN 113806500 A CN113806500 A CN 113806500A
- Authority
- CN
- China
- Prior art keywords
- target
- candidate
- abstract
- keyword
- semantic model
- 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 37
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000000605 extraction Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 16
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000007115 recruitment Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000007704 transition Effects 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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Human Computer Interaction (AREA)
- Marketing (AREA)
- Machine Translation (AREA)
Abstract
The application provides an information processing method, an information processing device and computer equipment, wherein the method comprises the following steps: the method comprises the steps of obtaining a target question, obtaining an actual answer by answering the target question, inquiring a candidate label corresponding to the target question, wherein the candidate label is used for representing a key point of the target question, inputting the candidate label and the actual answer into a trained semantic model, extracting keywords from the actual answer by adopting the semantic model to obtain a target keyword semantically matched with the candidate label, and generating and displaying an evaluation report according to the target keyword. According to the method and the device, the keyword information is extracted from the actual answer obtained by answering the target question based on the candidate label, the evaluation report is automatically generated based on the analysis of the question and the answer, the information acquisition efficiency is improved, and further, the communication efficiency is improved based on the evaluation report.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an information processing method and apparatus, and a computer device.
Background
In the recruitment process, HR interview communication is an indispensable link, especially in the recruitment season or the school recruitment season, HR needs to communicate with more than ten candidates every day, and in a limited time, the communication between HR and the candidates may only exist on the surface layer, so that deep understanding and communication cannot be realized, and the communication efficiency is low.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present application is to provide an information processing method to improve communication efficiency.
A second object of the present application is to provide an information processing apparatus.
A third object of the present application is to propose a computer device.
A fourth object of the present application is to propose a non-transitory computer-readable storage medium.
A fifth object of the present application is to propose a computer program product.
In order to achieve the above object, an embodiment of a first aspect of the present application provides an information processing method, including:
obtaining a target question and an actual answer obtained by answering the target question;
querying a candidate label corresponding to the target problem, wherein the candidate label is used for representing a key point of the target problem;
inputting the candidate labels and the actual answers into a trained semantic model, and extracting keywords from the actual answers by adopting the semantic model to obtain target keywords semantically matched with the candidate labels;
and generating an evaluation report according to the target keywords and displaying the evaluation report.
To achieve the above object, an embodiment of a second aspect of the present application proposes an information processing apparatus, including:
the acquisition module is used for acquiring a target question and an actual answer obtained by answering the target question;
the query module is used for querying candidate tags corresponding to the target problem, wherein the candidate tags are used for representing key points of the target problem;
the processing module is used for inputting the candidate labels and the actual answers into a trained semantic model so as to extract keywords of the actual answers by adopting the semantic model to obtain target keywords semantically matched with the candidate labels;
and the generating module is used for generating and displaying the evaluation report according to the target keywords.
In order to achieve the above object, a third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method according to the first aspect is implemented.
In order to achieve the above object, a fourth aspect of the present application proposes a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method according to the first aspect.
To achieve the above object, an embodiment of a fifth aspect of the present application provides a computer program product, wherein when instructions of the computer program product are executed by a processor, the method according to the first aspect is performed.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
the method comprises the steps of obtaining a target question, obtaining an actual answer by answering the target question, inquiring a candidate label corresponding to the target question, wherein the candidate label is used for representing a key point of the target question, inputting the candidate label and the actual answer into a trained semantic model, extracting keywords from the actual answer by adopting the semantic model to obtain a target keyword semantically matched with the candidate label, and generating and displaying an evaluation report according to the target keyword. According to the method and the device, the keyword information is extracted from the actual answer obtained by answering the target question based on the candidate label, the evaluation report is automatically generated based on the analysis of the question and the answer, the information acquisition efficiency is improved, and further, the communication efficiency is improved based on the evaluation report.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of an information processing method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another information processing method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another information processing method according to an embodiment of the present application;
fig. 4 is a schematic flowchart of another information processing method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application;
FIG. 6 is a block diagram of an exemplary computer device of an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
An information processing method, an apparatus, and a computer device according to embodiments of the present application are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of an information processing method according to an embodiment of the present application.
As shown in fig. 1, the method comprises the steps of:
The target problem is related to a service scene, and the target problem is different in different service scenes. The target problem may be understood as a common problem, a high frequency problem, and the like in a corresponding service scenario, and is not limited in this embodiment.
For example, in an interview scenario, the target question is an interview question that is frequently asked by Human Resources (HR). For example, the HR target question is "what is a professional plan", and the actual answers obtained for different candidates are, for example, "familiarize all basic businesses a year" or "visit a professional agent within 2 years".
And 102, inquiring a candidate label corresponding to the target problem, wherein the candidate label is used for representing a key point of the target problem.
The candidate label corresponding to the target question is an expected label set manually for the target question, is used for representing a key point of the target question, and is used for determining a target keyword for an actual answer subsequently. The number of the candidate tags corresponding to each target question can be one or more.
For example, the target question of HR is "what is a career plan", and the corresponding candidate labels are "one year" or "three years" or "five years" or "technology" or "management", which are not listed in this embodiment.
The target keyword comprises key information of the actual answer, and indicates that the semantic relevance between the actual answer and the candidate label is higher than a threshold value.
In the embodiment, the semantic model is adopted to carry out content understanding and analysis on the input candidate labels and the actual answers by adopting a natural language processing technology so as to obtain output target keywords which are obtained by extracting keywords from the actual answers and are semantically matched with the candidate labels,
and 104, generating an evaluation report according to the target keywords and displaying the evaluation report.
In this embodiment, the evaluation report shows more information of the person who provides the actual answer, and further communication is performed based on the evaluation report, so that the communication efficiency can be improved.
For example, when the recruitment season or the school recruitment season comes, the candidate answers on line according to the target to generate an assessment report, so that the HR is helped to know the candidate, the communication time is saved, the HR can communicate more deeply and more meaningfully within a limited time, and the communication efficiency and depth are improved.
In the information processing method of the embodiment, a target question is acquired, an actual answer obtained by answering the target question is queried for a candidate tag corresponding to the target question, wherein the candidate tag is used for representing a key point of the target question, the candidate tag and the actual answer are input into a trained semantic model, a keyword is extracted from the actual answer by using the semantic model to obtain a target keyword semantically matched with the candidate tag, and an evaluation report is generated and displayed according to the target keyword. According to the method and the device, the keyword information is extracted from the actual answer obtained by answering the target question based on the candidate label, the evaluation report is automatically generated based on the analysis of the question and the answer, the information acquisition efficiency is improved, and further, the communication efficiency is improved based on the evaluation report.
Based on the previous embodiment, in this embodiment, another information processing method is provided, in order to improve the accuracy of keyword extraction, a keyword extraction network for performing keyword extraction is included in a semantic model, and fig. 2 is a schematic flow diagram of another information processing method provided in this embodiment.
As shown in fig. 2, the step 103 includes the following steps:
The keyword extraction network is used for performing word segmentation on an actual answer to obtain a plurality of candidate words, performing feature extraction on the candidate labels and the candidate words respectively to obtain semantic vectors of the candidate labels and semantic vectors of the candidate words, and determining a target keyword from the candidate words, wherein the similarity between the semantic vector of the target keyword and the semantic vector of at least one candidate label is greater than a similarity threshold value.
As a possible implementation manner, cosine values between semantic vectors of the candidate labels and semantic vectors of the multiple candidate words are calculated according to cosine similarity, and the size of the cosine values indicates the size of the similarity, so that the corresponding candidate words when the cosine values are greater than a similarity threshold are used as the target keywords.
In this embodiment, the actual answer is divided into a plurality of candidate words, and according to the candidate tags, the target keywords having semantic similarity greater than a similarity threshold with the candidate tags are determined from the plurality of candidate words corresponding to the actual answer, so that candidate words irrelevant to the target questions are screened out, and accuracy of determining the target keywords is improved, thereby improving accuracy of the generated evaluation report based on the target questions.
Based on the foregoing embodiments, in order to improve the amount of information included in the generated evaluation report, the evaluation report includes not only the target keyword but also an abstract of the actual answer, that is, the semantic model further includes an abstract generating network for extracting a core sentence representing a semantic meaning from the input actual answer, fig. 3 is a schematic flow chart of another information processing method provided in the embodiments of the present application, as shown in fig. 3, the method includes the following steps:
The explanation of steps 301 to 303 can be referred to in the above embodiments, and the principle is the same, which is not described herein again.
In this embodiment, in order to improve the amount of information and readability included in the subsequent evaluation report, the evaluation report further includes an abstract of the actual answer under the condition that the evaluation report includes the target key information of the actual answer, where the abstract of the actual answer is a sentence including the key information of the actual answer generated according to the actual answer of the user.
As a possible implementation manner of the embodiment of the present application, a summary generation network is adopted to execute a text sorting algorithm, and sentences as summaries are extracted from actual answers.
For example, the actual answer is: i are ready to use 2 years of time to concentrate on learning technology and develop, and learn related management experiences in the next 1 year, and hopefully, the system can be used as a project manager.
The sentences extracted as abstract from the actual answer are, for example: a gradual transition from technology development to project management.
And 305, generating and displaying an evaluation report according to the target keywords and the abstract of the actual answer.
In the embodiment, the evaluation report is generated and displayed through the target keywords and the abstract of the actual answer, so that the automatic generation of the evaluation report is realized, the quantity and readability of information contained in the evaluation report are increased, more information can be acquired based on the evaluation report, the follow-up deeper and targeted communication can be conveniently carried out, and the follow-up communication efficiency is improved.
Based on the foregoing embodiment, this embodiment further provides an implementation manner, and fig. 4 is a schematic flow chart of another information processing method provided in this embodiment of the application, as shown in fig. 4, the step 305 includes the following steps:
The labeled reference keywords and the labeled reference abstract more accurately indicate the key information contained in the actual answer.
In this embodiment, the target keywords and the abstract in the evaluation report generated based on the semantic model do not necessarily have higher accuracy, so that after the evaluation report is generated and displayed, the reference keywords labeled according to the actual answers to the target keywords in the evaluation report and the reference abstract are obtained in response to the user operation and serve as feedback of the accuracy of the currently generated evaluation report.
And 402, generating a training sample according to the reference keyword and the reference abstract.
And 403, training the semantic model by using the training samples.
In this embodiment, the obtained reference keywords and the reference abstract are used to generate a training sample, and then the training sample is used to train the semantic model, so that the semantic model is continuously optimized, and the accuracy of the target keywords and the abstract determined by the semantic model is improved.
As a possible implementation mode, the value of the loss function is determined according to the difference between the reference keyword and the target keyword output by the semantic model and the difference between the reference abstract and the abstract output by the semantic model, and the model parameter of the semantic model is adjusted according to the value of the loss function so as to minimize the value of the loss function, thereby improving the accuracy of the target keyword and the abstract determined by the semantic model.
In the information processing method in this embodiment, after an evaluation report is generated and displayed, a reference keyword and a reference abstract which are determined according to an actual answer and are used for labeling a target keyword in the evaluation report are obtained in response to a user operation, the reference keyword and the reference abstract are used as feedback for the accuracy of the currently generated evaluation report, and a semantic model is trained based on the labeled reference keyword and the reference abstract and used as a training sample, so that the semantic model is continuously optimized, and the accuracy of the target keyword and the abstract determined by the semantic model is improved.
In order to implement the above embodiments, the present application also proposes an information processing apparatus.
Fig. 5 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application.
As shown in fig. 5, the apparatus includes: an acquisition module 51, a query module 52, a processing module 53 and a generation module 54.
The obtaining module 51 is used for obtaining the target question and the actual answer obtained by answering the target question.
And the query module 52 is configured to query candidate tags corresponding to the target problem, where the candidate tags are used to represent key points of the target problem.
And the processing module 53 is configured to input the candidate labels and the actual answers into the trained semantic model, so as to extract keywords from the actual answers by using the semantic model to obtain target keywords semantically matched with the candidate labels.
And the generating module 54 is used for generating and displaying the evaluation report according to the target keyword.
Further, in a possible implementation manner of the embodiment of the present application, the semantic model includes a keyword extraction network; the processing module 53 is specifically configured to:
inputting the candidate labels and the actual answers into the trained keyword extraction network to obtain the target keywords output by the keyword extraction network;
the keyword extraction network is used for performing word segmentation on the actual answer to obtain a plurality of candidate words; respectively extracting the characteristics of the candidate labels and the candidate words to obtain semantic vectors of the candidate labels and semantic vectors of the candidate words; determining the target keyword from the plurality of candidate words, wherein the similarity between the semantic vector of the target keyword and the semantic vector of at least one candidate label is greater than a similarity threshold.
In a possible implementation manner of the embodiment of the present application, the semantic model further includes a digest generation network; the processing module 53 is further configured to input the actual answer into the abstract generation network to obtain an abstract of the actual answer; wherein, the evaluation report comprises the abstract of the actual answer.
In a possible implementation manner of the embodiment of the present application, the processing module 53 is further specifically configured to:
and adopting the abstract generation network to execute a text sequencing algorithm, and extracting sentences serving as the abstract from the actual answers.
In a possible implementation manner of the embodiment of the present application, the apparatus further includes:
the response module is used for responding to user operation to obtain reference keywords labeled on target keywords in the evaluation report and the reference abstract;
the generating module 54 is configured to generate a training sample according to the reference keyword and the reference abstract;
and the training module is used for training the semantic model by adopting the training samples.
In a possible implementation manner of the embodiment of the present application, the training module is specifically configured to:
determining the value of a loss function according to the difference between the reference keyword and the target keyword output by the semantic model and according to the difference between the reference abstract and the abstract output by the semantic model;
and adjusting the model parameters of the semantic model according to the value of the loss function so as to minimize the value of the loss function.
It should be noted that the foregoing explanation of the method embodiment is also applicable to the apparatus of this embodiment, and is not repeated herein.
In the information processing apparatus of this embodiment, a target question is acquired, an actual answer obtained by answering the target question is answered, a candidate tag corresponding to the target question is queried, where the candidate tag is used to represent a key point of the target question, the candidate tag and the actual answer are input into a trained semantic model, a keyword is extracted from the actual answer by using the semantic model to obtain a target keyword semantically matched with the candidate tag, and an evaluation report is generated and displayed according to the target keyword. According to the method and the device, the keyword information is extracted from the actual answer obtained by answering the target question based on the candidate label, the evaluation report is automatically generated based on the analysis of the question and the answer, the information acquisition efficiency is improved, and further, the communication efficiency is improved based on the evaluation report.
In order to implement the foregoing embodiments, the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the computer device implements the method according to the foregoing method embodiments.
In order to implement the above embodiments, the present application proposes a non-transitory computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the method as described in the foregoing method embodiments.
To implement the above embodiments, the present application provides a computer program product, wherein when the instructions in the computer program product are executed by a processor, the method according to the foregoing method embodiments is implemented.
FIG. 6 is a block diagram of an exemplary computer device of an embodiment of the present application. The computer device 12 shown in fig. 6 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present application.
As shown in FIG. 6, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via Network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by executing programs stored in the system memory 28.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
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 application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (15)
1. An information processing method characterized by comprising the steps of:
obtaining a target question and an actual answer obtained by answering the target question;
querying a candidate label corresponding to the target problem, wherein the candidate label is used for representing a key point of the target problem;
inputting the candidate labels and the actual answers into a trained semantic model, and extracting keywords from the actual answers by adopting the semantic model to obtain target keywords semantically matched with the candidate labels;
and generating an evaluation report according to the target keywords and displaying the evaluation report.
2. The information processing method according to claim 1, wherein the semantic model includes a keyword extraction network; the method for extracting the keywords from the actual answer by adopting the semantic model to obtain the target keywords semantically matched with the candidate labels comprises the following steps:
inputting the candidate labels and the actual answers into the trained keyword extraction network to obtain the target keywords output by the keyword extraction network;
the keyword extraction network is used for performing word segmentation on the actual answer to obtain a plurality of candidate words; respectively extracting the characteristics of the candidate labels and the candidate words to obtain semantic vectors of the candidate labels and semantic vectors of the candidate words; determining the target keyword from the plurality of candidate words, wherein the similarity between the semantic vector of the target keyword and the semantic vector of at least one candidate label is greater than a similarity threshold.
3. The information processing method according to claim 2, wherein the semantic model further includes a digest generation network; the method further comprises the following steps:
inputting the actual answer into the abstract generation network to obtain an abstract of the actual answer;
wherein, the evaluation report comprises the abstract of the actual answer.
4. The information processing method according to claim 3, wherein the inputting the actual answer into the digest generation network to obtain the digest of the actual answer includes:
and adopting the abstract generation network to execute a text sequencing algorithm, and extracting sentences serving as the abstract from the actual answers.
5. The information processing method according to claim 3, wherein after generating and displaying an evaluation report based on the target keyword, the method further comprises:
responding to user operation, and obtaining reference keywords labeled on target keywords in the evaluation report and the reference abstract;
generating a training sample according to the reference keyword and the reference abstract;
and training the semantic model by adopting the training samples.
6. The information processing method of claim 5, wherein the training the semantic model using the training samples comprises:
determining the value of a loss function according to the difference between the reference keyword and the target keyword output by the semantic model and according to the difference between the reference abstract and the abstract output by the semantic model;
and adjusting the model parameters of the semantic model according to the value of the loss function so as to minimize the value of the loss function.
7. An information processing apparatus characterized by comprising:
the acquisition module is used for acquiring a target question and an actual answer obtained by answering the target question;
the query module is used for querying candidate tags corresponding to the target problem, wherein the candidate tags are used for representing key points of the target problem;
the processing module is used for inputting the candidate labels and the actual answers into a trained semantic model so as to extract keywords of the actual answers by adopting the semantic model to obtain target keywords semantically matched with the candidate labels;
and the generating module is used for generating and displaying the evaluation report according to the target keywords.
8. The information processing apparatus according to claim 7, wherein the semantic model includes a keyword extraction network; the processing module is specifically configured to:
inputting the candidate labels and the actual answers into the trained keyword extraction network to obtain the target keywords output by the keyword extraction network;
the keyword extraction network is used for performing word segmentation on the actual answer to obtain a plurality of candidate words; respectively extracting the characteristics of the candidate labels and the candidate words to obtain semantic vectors of the candidate labels and semantic vectors of the candidate words; determining the target keyword from the plurality of candidate words, wherein the similarity between the semantic vector of the target keyword and the semantic vector of at least one candidate label is greater than a similarity threshold.
9. The information processing apparatus according to claim 8, wherein the semantic model further includes a digest generation network;
the processing module is further configured to input the actual answer into the abstract generation network to obtain an abstract of the actual answer; wherein, the evaluation report comprises the abstract of the actual answer.
10. The information processing apparatus according to claim 9, wherein the processing module is further specifically configured to:
and adopting the abstract generation network to execute a text sequencing algorithm, and extracting sentences serving as the abstract from the actual answers.
11. The information processing apparatus according to claim 9, characterized by further comprising:
the response module is used for responding to user operation to obtain reference keywords labeled on target keywords in the evaluation report and the reference abstract;
the generating module is used for generating a training sample according to the reference keyword and the reference abstract;
and the training module is used for training the semantic model by adopting the training samples.
12. The information processing apparatus of claim 11, wherein the training module is specifically configured to:
determining the value of a loss function according to the difference between the reference keyword and the target keyword output by the semantic model and according to the difference between the reference abstract and the abstract output by the semantic model;
and adjusting the model parameters of the semantic model according to the value of the loss function so as to minimize the value of the loss function.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to any one of claims 1-6 when executing the program.
14. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method of any one of claims 1-6.
15. A computer program product, characterized in that instructions in the computer program product, when executed by a processor, perform the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110180461.1A CN113806500B (en) | 2021-02-09 | 2021-02-09 | Information processing method, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110180461.1A CN113806500B (en) | 2021-02-09 | 2021-02-09 | Information processing method, device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113806500A true CN113806500A (en) | 2021-12-17 |
| CN113806500B CN113806500B (en) | 2024-05-28 |
Family
ID=78892796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110180461.1A Active CN113806500B (en) | 2021-02-09 | 2021-02-09 | Information processing method, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113806500B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114970470A (en) * | 2022-07-27 | 2022-08-30 | 中关村科学城城市大脑股份有限公司 | Method and device for processing file information, electronic equipment and computer readable medium |
| CN117708391A (en) * | 2024-02-05 | 2024-03-15 | 天开林源(天津)科技有限责任公司 | Data processing method, device, equipment and storage medium |
| CN117875908A (en) * | 2024-03-08 | 2024-04-12 | 蒲惠智造科技股份有限公司 | Work order processing method and system based on enterprise management software SAAS |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060277165A1 (en) * | 2005-06-03 | 2006-12-07 | Fuji Xerox Co., Ltd. | Question answering system, data search method, and computer program |
| KR101662450B1 (en) * | 2015-05-29 | 2016-10-05 | 포항공과대학교 산학협력단 | Multi-source hybrid question answering method and system thereof |
| CN107491655A (en) * | 2017-08-31 | 2017-12-19 | 康安健康管理咨询（常熟）有限公司 | Liver diseases information intelligent consultation method and system based on machine learning |
| US20170364586A1 (en) * | 2016-06-20 | 2017-12-21 | International Business Machines Corporation | Contextual Content Graph for Automatic, Unsupervised Summarization of Content |
| CN108681574A (en) * | 2018-05-07 | 2018-10-19 | 中国科学院合肥物质科学研究院 | A kind of non-true class quiz answers selection method and system based on text snippet |
| CN109522486A (en) * | 2018-11-30 | 2019-03-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for match information |
| CN109978339A (en) * | 2019-02-27 | 2019-07-05 | 平安科技（深圳）有限公司 | AI interviews model training method, device, computer equipment and storage medium |
| CN110569356A (en) * | 2019-08-14 | 2019-12-13 | 中国平安人寿保险股份有限公司 | interviewing method and device based on intelligent interviewing interaction system and computer equipment |
-
2021
- 2021-02-09 CN CN202110180461.1A patent/CN113806500B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060277165A1 (en) * | 2005-06-03 | 2006-12-07 | Fuji Xerox Co., Ltd. | Question answering system, data search method, and computer program |
| KR101662450B1 (en) * | 2015-05-29 | 2016-10-05 | 포항공과대학교 산학협력단 | Multi-source hybrid question answering method and system thereof |
| US20170364586A1 (en) * | 2016-06-20 | 2017-12-21 | International Business Machines Corporation | Contextual Content Graph for Automatic, Unsupervised Summarization of Content |
| CN107491655A (en) * | 2017-08-31 | 2017-12-19 | 康安健康管理咨询（常熟）有限公司 | Liver diseases information intelligent consultation method and system based on machine learning |
| CN108681574A (en) * | 2018-05-07 | 2018-10-19 | 中国科学院合肥物质科学研究院 | A kind of non-true class quiz answers selection method and system based on text snippet |
| CN109522486A (en) * | 2018-11-30 | 2019-03-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for match information |
| CN109978339A (en) * | 2019-02-27 | 2019-07-05 | 平安科技（深圳）有限公司 | AI interviews model training method, device, computer equipment and storage medium |
| CN110569356A (en) * | 2019-08-14 | 2019-12-13 | 中国平安人寿保险股份有限公司 | interviewing method and device based on intelligent interviewing interaction system and computer equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114970470A (en) * | 2022-07-27 | 2022-08-30 | 中关村科学城城市大脑股份有限公司 | Method and device for processing file information, electronic equipment and computer readable medium |
| CN117708391A (en) * | 2024-02-05 | 2024-03-15 | 天开林源(天津)科技有限责任公司 | Data processing method, device, equipment and storage medium |
| CN117708391B (en) * | 2024-02-05 | 2024-05-17 | 天开林源(天津)科技有限责任公司 | Data processing method, device, equipment and storage medium |
| CN117875908A (en) * | 2024-03-08 | 2024-04-12 | 蒲惠智造科技股份有限公司 | Work order processing method and system based on enterprise management software SAAS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113806500B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111858859B (en) | Automatic question-answering processing method, device, computer equipment and storage medium | |
| CN109815487B (en) | Text quality inspection method, electronic device, computer equipment and storage medium | |
| CN113806500B (en) | Information processing method, device and computer equipment | |
| CN111767366B (en) | Question and answer resource mining method and device, computer equipment and storage medium | |
| CN108090043B (en) | Error correction report processing method and device based on artificial intelligence and readable medium | |
| CN110543592A (en) | Information searching method and device and computer equipment | |
| US11461613B2 (en) | Method and apparatus for multi-document question answering | |
| CN110020163B (en) | Search method and device based on man-machine interaction, computer equipment and storage medium | |
| CN109616101B (en) | Acoustic model training method and device, computer equipment and readable storage medium | |
| CN111241230A (en) | Method and system for identifying string mark risk based on text mining | |
| CN111930792A (en) | Data resource labeling method and device, storage medium and electronic equipment | |
| CN111144079A (en) | Method and device for intelligently acquiring learning resources, printer and storage medium | |
| CN107844531B (en) | Answer output method and device and computer equipment | |
| CN109815500A (en) | Management method, device, computer equipment and the storage medium of unstructured official document | |
| WO2023236253A1 (en) | Document retrieval method and apparatus, and electronic device | |
| CN111143517B (en) | Human selection label prediction method, device, equipment and storage medium | |
| CN113807096A (en) | Text data processing method and device, computer equipment and storage medium | |
| CN115964484A (en) | Legal multi-intention identification method and device based on multi-label classification model | |
| CN111738009B (en) | Entity word label generation method, entity word label generation device, computer equipment and readable storage medium | |
| CN112699671B (en) | Language labeling method, device, computer equipment and storage medium | |
| CN112559711A (en) | Synonymous text prompting method and device and electronic equipment | |
| CN114862141A (en) | Method, device and equipment for recommending courses based on portrait relevance and storage medium | |
| CN109299294B (en) | Resource searching method and device in application, computer equipment and storage medium | |
| CN110276001B (en) | Checking page identification method and device, computing equipment and medium | |
| CN113901793A (en) | Event extraction method and device combining RPA and AI |
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 |