CN112434504A - Method and device for generating file information, electronic equipment and computer readable medium - Google Patents
Method and device for generating file information, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN112434504A CN112434504A CN202011320860.5A CN202011320860A CN112434504A CN 112434504 A CN112434504 A CN 112434504A CN 202011320860 A CN202011320860 A CN 202011320860A CN 112434504 A CN112434504 A CN 112434504A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- file
- keyword
- generation 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004891 communication Methods 0.000 claims description 19
- 238000001303 quality assessment method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000007115 recruitment Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for automatically generating file information, electronic equipment and a computer readable medium, and belongs to the technical field of machine learning. The method comprises the following steps: acquiring target keyword information and template category information in target information of target personnel; selecting a target file template matched with the template category information from a plurality of file templates; and inputting the target keyword information into a target file generation model to obtain target file information of the target personnel, which is output by the target file generation model and matched with the target file template. The method and the device improve the writing efficiency of the file content and ensure the quality of the resume.
Description
Technical Field
The present application relates to the field of machine learning technologies, and in particular, to a method and an apparatus for automatically generating document information, an electronic device, and a computer-readable medium.
Background
At present, in all aspects of life and work, paper files or electronic files are needed to assist life and work, but the contents in the files need to be written manually, and the writing pen is not a good person, even if the person knows about the contents to be written, the person cannot express the contents in smooth sentences, so that the difficulty of writing the contents of the files by the person is increased, and the writing efficiency is reduced.
For example, in writing a resume, a superior resume at post interview would be a good knock tile. The talent often cannot write a good resume due to lack of employment experience, some people with social experience cannot provide a festive resume due to lack of good writing pens, an excellent resume cannot be completed even if a large amount of time and energy are wasted, efficiency of manual resume writing is low, and quality cannot be guaranteed.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, an electronic device, and a computer-readable medium for automatically generating document information, so as to solve the problems that the efficiency of manually writing document information is low and the quality cannot be guaranteed. The specific technical scheme is as follows:
in a first aspect, a method for automatically generating file information is provided, where the method includes:
acquiring target keyword information and template category information in target information of target personnel;
selecting a target file template matched with the template category information from a plurality of file templates;
and inputting the target keyword information into a target file generation model to obtain target file information of the target personnel, which is output by the target file generation model and matched with the target file template.
Optionally, before obtaining the target keyword information in the target information, the method further includes:
acquiring sample file information and sample keyword information of the sample file information;
inputting the sample file information into an initial file generation model to obtain a keyword recognition result output by the initial file generation model;
and under the condition that the sample keyword information is inconsistent with the keyword recognition result, adjusting model parameters of the initial file generation model to obtain the target file generation model, wherein the keyword recognition result output by the target file generation model is consistent with the sample keyword information.
Optionally, before obtaining the sample file information and the sample keyword information of the sample file information, the method further includes:
acquiring information of a file to be selected and a quality assessment result of the information of the file to be selected;
and selecting file information with a quality assessment result meeting a preset assessment condition from the file information to be selected as the sample file information.
Optionally, the target information further includes target domain information, and the acquiring target keyword information in the target information includes:
acquiring the target field information and field keyword information, wherein the field keyword information is keyword information suitable for each field;
determining the determined meaning of the domain keyword information in the domain category to which the target domain belongs;
and taking the keyword information with the determined meaning as the target keyword information.
Optionally, before the obtaining the target domain information and the domain keyword information, the method further includes:
acquiring information of a file to be selected and information of a field to be selected in the information of the file to be selected;
and performing domain classification on the information of the domain to be selected to obtain a domain category.
Optionally, after the target keyword information is input into a target file generation model to obtain target file information of the target person, which is output by the target file generation model and matches with the target file template, the method further includes:
acquiring updated file information sent by the target personnel aiming at the target file information;
acquiring the update keyword information in the update file information;
and inputting the updated keyword information into the target file generation model to obtain the optimized file information output by the target file generation model.
Optionally, the adjusting model parameters of the initial file generation model includes:
and adjusting parameters in a natural language generation algorithm of the initial file generation model so as to enable the natural language generation algorithm to be more accurate.
In a second aspect, an apparatus for automatically generating file information is provided, the apparatus comprising:
the acquisition module is used for acquiring target keyword information and template category information in the target information of the target personnel;
the selecting module is used for selecting a target file template matched with the template category information from a plurality of file templates;
and the input and output module is used for inputting the target keyword information into a target file generation model to obtain the target file information of the target personnel, which is output by the target file generation model and matched with the target file template.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing any of the method steps described herein when executing the program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, having stored thereon a computer program which, when being executed by a processor, carries out any of the method steps.
The embodiment of the application has the following beneficial effects:
the embodiment of the application provides a method for automatically generating file information, wherein a server acquires target keyword information and template category information in target information of target personnel, then selects a target file template matched with the template category information from a plurality of file templates, and finally inputs the target keyword information into a target file generation model to obtain the target file information of the target personnel, which is output by the target file generation model and is matched with the target file template. According to the method and the device, the target file information is automatically generated through the target file generation model, the target person is not required to write complete file information, the time and the energy of the target person are saved, the writing efficiency of the file information is improved, and the resume quality is guaranteed.
Of course, not all of the above advantages need be achieved in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a flowchart of a method for automatically generating document information according to an embodiment of the present disclosure;
FIG. 2 is a flowchart of a method for generating optimized file information according to an embodiment of the present disclosure;
fig. 3 is a processing flow chart of a method for automatically generating document information according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for automatically generating document information according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides a method for automatically generating file information, which can be applied to a server and is used for automatically generating target file information aiming at target information provided by target personnel. The method and the device can be applied to scenes of various article writings such as resume writing, paper writing or composition writing.
The following describes in detail a method for automatically generating file information according to an embodiment of the present application with reference to a specific embodiment, and as shown in fig. 1, the specific steps are as follows:
step 101: and acquiring target keyword information and template category information in the target information of the target personnel.
In the embodiment of the application, if a target person wants to generate own file information through a server, the target person needs to provide target information first, and the target information includes target keyword information and template category information. The template type information can be work experience information, academic information, genre information and the like, and if the target file information is a resume, the server divides the target file template into a school and a social according to the work experience information in the target information; if the target file information is a thesis, the server divides the target file template into a subject thesis and a student thesis according to the academic information in the target information; if the target file information is composition, the server divides the target file information into a prose, a treatise and a narrative according to the genre information in the target information.
Illustratively, the target file information is a resume, the target person is a job seeker, and the target information is job hunting information. If a job seeker wants to generate a resume of the job seeker through a server, job hunting information needs to be provided first, and the job hunting information comprises target keyword information and work experience information. The work experience information is whether the job seeker has social work experience, the age limit of social work and the like, and the server can determine that the job seeker is a due student or a social person according to the work experience information. The target keyword information is a keyword in job hunting information, such as name, household register, gender and the like in personal basic information, school name, specialty, school calendar and the like in an education background, java, c + +, web front end and the like in technical skills.
Step 102: and selecting a target file template matched with the template category information from the plurality of file templates.
In the embodiment of the application, a plurality of templates are arranged in the server, and the server selects the target file template from the plurality of templates according to the acquired template category information.
Illustratively, the template category information is work experience information. The server is provided with a plurality of resume templates, the server can select a target resume template from the plurality of resume templates according to the obtained work experience information, and the target resume template is matched with the work experience information. The resume template comprises a school and recruitment template and a social bidding template, and the server selects the school and recruitment template if judging that the job seeker does not have work experience information.
Step 103: and inputting the target keyword information into the target file generation model to obtain target file information of the target personnel, which is output by the target file generation model and matched with the target file template.
In the embodiment of the application, after the server acquires the target keyword information, the target keyword information is input into the target file generation model, the target file generation model outputs the target file information of the target person matched with the target file template through a natural language generation algorithm, and the target file information is the full version of file information.
The natural language generation algorithm obtains target file information according to the target keyword information, and the knowledge graph of the target keyword information is used, so that the target resume information is more perfect and deep.
Specifically, the step of generating the target resume information by the natural language generation algorithm comprises: 1. and (4) determining the content. NLG systems need to decide which information should be included in the text being constructed and which should not, and often more information is included in the data than is ultimately conveyed. 2. And (5) text structure. After determining what information needs to be conveyed, the NLG system needs a reasonable order in which to organize the text. 3. And (5) sentence aggregation. Not every message needs a separate sentence to be expressed, and combining multiple messages into a sentence can be more fluent and easier to read. 4. And (5) syntax transformation. When the content of each sentence is determined, the information can be organized into natural language. This step adds some conjunctions between the various information, appearing more like a complete sentence. 5. And generating a reference expression. This step is very similar to grammar and selects words and phrases to form a complete sentence. However, he essentially differs from grammar in that "REG needs to identify the domain of the content and then use the vocabulary of that domain (but not other domains)". 6. And (4) language implementation. Finally, when all related words and phrases have been determined, they need to be combined to form a well-formed complete sentence.
In the method and the device, the target person only needs to input the simplified target information, the server can automatically generate the target file information according to the target keyword information in the target information, the target person does not need to write complete file information by himself, and time and energy of the target person are saved. In addition, because the target file generation model adopts a natural language generation algorithm and a knowledge graph at the same time, the information content of the target file is more perfect, and the language is smooth.
As an optional implementation manner, before obtaining the target keyword information in the target information, the method further includes: acquiring sample file information and sample keyword information of the sample file information; inputting sample file information into an initial file generation model to obtain a keyword recognition result output by the initial file generation model; and under the condition that the sample keyword information is inconsistent with the keyword recognition result, adjusting the model parameters of the initial file generation model to obtain a target file generation model, wherein the keyword recognition result output by the target file generation model is consistent with the sample keyword information.
In the embodiment of the application, the server needs to train the initial file generation model to obtain the target file generation model. The training process is as follows: the method comprises the steps that a server obtains sample file information and sample keyword information of the sample file information, then the sample file information is input into an initial file generation model, a keyword recognition result output by the initial file generation model is obtained, under the condition that the sample keyword information is inconsistent with the keyword recognition result, model parameters of the initial file generation model are adjusted, and a target file generation model is obtained, wherein the keyword recognition result output by the target file generation model is consistent with the sample keyword information.
Illustratively, the target information is job hunting information, the server collects resumes in a manual mode before acquiring target keyword information in the job hunting information, sources including network resources, internal recruitment departments of a company and the like are collected, then keywords in the resumes are labeled manually, and the keywords include keywords in contents such as but not limited to basic information, education backgrounds, professional skills, business skills, project experiences and the like, so that keyword information is obtained.
As an optional implementation, adjusting the model parameters of the initial file generation model includes: and adjusting parameters in a natural language generation algorithm of the initial file generation model so as to enable the natural language generation algorithm to be more accurate.
In the embodiment of the application, the initial file generation model adopts a natural language generation algorithm, and the model parameters of the adjusted file resume generation model are the parameters in the adjusted natural language generation algorithm.
As an optional implementation manner, before obtaining the sample file information and the sample keyword information of the sample file information, the method further includes: acquiring the information of the files to be selected and the quality assessment results of the information of the files to be selected; and selecting file information with a quality assessment result meeting a preset assessment condition from the file information to be selected as sample file information.
In the embodiment of the application, the information of the files to be selected is manually collected in advance, the collected files to be selected are manually marked with quality assessment results, the quality assessment results reflect the quality of the files to be selected, the server obtains the information of the files to be selected and the quality assessment results of the information of the files to be selected, and then the file information of which the quality assessment results meet preset assessment conditions is selected from the information of the files to be selected and used as the sample file information. The preset assessment condition can be an assessment grade.
Illustratively, the information of the file to be selected is the resume to be selected, the collected resume to be selected needs to be labeled with a quality assessment result manually, and the quality assessment result reflects the quality of the resume to be selected, including the statement fluency, the information integrity, the skill richness and the like of the resume to be selected. The server acquires the resume information to be selected and the quality assessment results of the resume information to be selected, and then selects resume information of which the quality assessment results meet preset assessment conditions from the resume information to be selected as sample resume information.
In the application, the server selects the file information of which the quality assessment result meets the preset assessment condition as the sample file information, so that the quality of the training sample is improved, and the quality of the target file information output by the target file generation model is also improved.
As an optional implementation manner, the job hunting information further includes target domain information, and the manner of acquiring the target keyword information in the target information is as follows: the server pushes the associated keyword information according to the target field information, and the target personnel select the target keyword information which accords with the actual situation of the target personnel from the associated keyword information.
According to the method and the device, the target person does not need to think the target keyword information by himself, only needs to input the target field information by the target person, and then selects the target keyword information from the associated keyword information, so that the time and the energy of the target person are saved.
As an optional implementation manner, the target information further includes target domain information, and acquiring the target keyword information in the target information includes: acquiring target field information and field keyword information, wherein the field keyword information is keyword information suitable for each field; determining the determined meaning of the domain keyword information in the domain category to which the target domain belongs; the keyword information having a certain meaning is taken as target keyword information.
In the embodiment of the present application, the target information further includes target domain information, and the domain keyword information is keyword information applicable to each domain. The server determines the determined meaning of the domain keyword information in the domain category to which the target domain belongs according to the preset domain category, and takes the keyword information with the determined meaning as the target keyword information.
Illustratively, the target field information is job hunting post information, the field keyword information is job hunting keyword information, the job hunting post information of the job seeker further comprises the job hunting post information and the job hunting keyword information, and the job hunting keyword information is keyword information applicable to each post. The server determines the determined meaning of the job hunting keyword information in the post category of the job hunting post according to the preset post category, and takes the keyword information with the determined meaning as target keyword information.
For example, if job hunting keyword information is management, then managing the keyword is applicable to many positions and has different definite meanings at different positions, for example, for a personnel position, personnel management is a series of management activities such as selecting, using, cultivating, examining, awarding and punishing the personnel belonging to the country or a certain department to achieve a certain goal. For financial position, financial management is the management of the acquisition (investment) of assets, the financing (financing) and the in-business cash flow (operating funds), and the allocation of profits, with a certain overall objective. Therefore, the server needs to take the keyword information having a certain meaning as the target keyword information.
As an optional implementation manner, before obtaining the target domain information and the domain keyword information, the method further includes: acquiring information of a file to be selected and information of a field to be selected in the information of the file to be selected; and carrying out domain classification on the domain information to be selected to obtain a domain category.
In the embodiment of the application, the information of the file to be selected and the information of the field to be selected in the information of the file to be selected are manually obtained, and then the information of the field to be selected is subjected to field classification to obtain the field type.
Illustratively, the domain category is a position category. Manually acquiring resume information to be selected and post information to be selected in the resume information to be selected, and then classifying the posts of the post information to be selected to obtain post categories. Illustratively, the classification of the positions into position categories includes, but is not limited to; personnel posts, administrative posts, management posts, technical posts, and the like.
As an alternative implementation, as shown in fig. 2, after inputting the target keyword information into the target document generation model to obtain the target document information of the target person output by the target document generation model and matching with the target document template, the method further includes:
step 201: and acquiring the updated file information sent by the target personnel aiming at the target file information.
In the embodiment of the application, after the server obtains the target file information of the target person, the target person sends the target file information to the target person, the target person can match with the actual situation of the target person according to the content in the target file information, if the target person finds that some content in the target file information is not matched with the target person, the target person can appropriately add or delete the content to the target file information to obtain the updated file information, then the updated file information is sent to the server, and the server obtains the updated file information sent by the target person aiming at the target file information.
Illustratively, the update file information is update resume information. The server obtains target resume information of a job seeker, and then sends the target resume information to the job seeker, the job seeker can match with the actual situation of the job seeker according to the content in the target resume information, if the job seeker finds that some content in the target resume information is not matched with the job seeker, in order to guarantee smooth conduct of an interview, the job seeker can appropriately add or delete the content to the target resume information to obtain updated resume information, then the updated resume information is sent to the server, and the server obtains the updated resume information sent by the job seeker according to the target resume information.
Step 202: and acquiring the update keyword information in the update file information.
In the embodiment of the application, after the server acquires the updated file information sent by the target person, the server determines the updated keyword information in the updated file information so as to regenerate the file information aiming at the updated keyword information.
Step 203: and inputting the updated keyword information into the target file generation model to obtain the optimized file information output by the target file generation model.
In the embodiment of the application, the server inputs the updated keyword information into the target file generation model, and obtains the optimized file information output by the target file generation model through a natural language generation algorithm.
In the method and the device, the target personnel feed back the target file information, and the server regenerates the optimized file information according to the fed-back updated keyword information, so that the file content is more suitable for the situation of the target personnel, and the authenticity and the suitability of the file content are improved.
Optionally, an embodiment of the present application further provides a processing flow of a method for automatically generating file information, as shown in fig. 3, and the specific steps are as follows.
Step 301: and obtaining information of the files to be selected, and selecting the files with quality assessment results meeting preset assessment conditions from the information of the files to be selected as sample file information.
Step 302: and obtaining template category information, target field information and field keyword information in the sample file information.
Step 303: and determining a target file template according to the template category information, and determining target keyword information according to the target field information.
The server can select a target file template from the multiple file information templates according to the acquired template category information, and the target file template is matched with the template category information. The server determines the determined meaning of the domain keyword information in the domain category to which the job hunting domain belongs according to the preset domain category, and takes the keyword information with the determined meaning as target keyword information.
Step 304: and outputting target file information matched with the target file template through the target file generation model.
And inputting the target keyword information into the target file generation model to obtain target file information of the target personnel, which is output by the target file generation model and matched with the target file template.
Step 305: and acquiring the update keyword information in the update file information.
The target personnel can add or delete the content of the target file information appropriately to obtain the updated file information, then the updated file information is sent to the server, and the server obtains the updated keyword information in the updated file information.
Step 306: and obtaining optimized file information through the target file generation model.
And the server inputs the updated keyword information into the target file generation model to obtain the optimized file information output by the target file generation model.
Based on the same technical concept, an embodiment of the present application further provides an apparatus for automatically generating file information, as shown in fig. 4, the apparatus includes:
a first obtaining module 401, configured to obtain target keyword information and template category information in target information of a target person;
a selecting module 402, configured to select a target file template matching the template category information from multiple file information templates;
and an input/output module 403, configured to input the target keyword information into the target file generation model, to obtain target file information of the target person, which is output by the target file generation model and matches with the target file template.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring the sample file information and the sample keyword information of the sample file information;
the first input module is used for inputting the sample file information into the initial file generation model to obtain a keyword recognition result output by the initial file generation model;
and the adjusting module is used for adjusting the model parameters of the initial file generation model to obtain a target file generation model under the condition that the sample keyword information is inconsistent with the keyword recognition result, wherein the keyword recognition result output by the target file generation model is consistent with the sample keyword information.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring the information of the files to be selected and the quality assessment results of the information of the files to be selected;
and the selecting module is used for selecting the file information of which the quality assessment result meets the preset assessment condition from the file information to be selected as the sample file information.
Optionally, the first obtaining module 401 includes:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring target field information and field keyword information, and the field keyword information is keyword information suitable for each field;
a determining unit configured to determine a determination meaning of the domain keyword information in a domain category to which the target domain belongs;
as a unit, keyword information having a certain meaning is taken as target keyword information.
Optionally, the apparatus further comprises:
the fourth acquisition module is used for acquiring the information of the file to be selected and the information of the field to be selected in the information of the file to be selected;
and the classification module is used for performing domain classification on the information of the domain to be selected to obtain the domain category.
Optionally, the apparatus further comprises:
the fifth acquisition module is used for acquiring the updated file information sent by the target personnel aiming at the target file information;
the sixth acquisition module is used for acquiring the updating keyword information in the updating file information;
and the second input module is used for inputting the updated keyword information into the target file generation model to obtain the optimized file information output by the target file generation model.
Optionally, the adjusting module comprises:
and the adjusting unit is used for adjusting parameters in the natural language generation algorithm of the initial file generation model so as to enable the natural language generation algorithm to be more accurate.
Based on the same technical concept, the embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504,
a memory 503 for storing a computer program;
the processor 501 is configured to implement the above steps when executing the program stored in the memory 503.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In a further embodiment provided by the present invention, there is also provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of any of the methods described above.
In a further embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the methods of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for automatically generating file information, the method comprising:
acquiring target keyword information and template category information in target information of target personnel;
selecting a target file template matched with the template category information from a plurality of file templates;
and inputting the target keyword information into a target file generation model to obtain target file information of the target personnel, which is output by the target file generation model and matched with the target file template.
2. The method of claim 1, wherein before obtaining the target keyword information in the target information, the method further comprises:
acquiring sample file information and sample keyword information of the sample file information;
inputting the sample file information into an initial file generation model to obtain a keyword recognition result output by the initial file generation model;
and under the condition that the sample keyword information is inconsistent with the keyword recognition result, adjusting model parameters of the initial file generation model to obtain the target file generation model, wherein the keyword recognition result output by the target file generation model is consistent with the sample keyword information.
3. The method according to claim 2, wherein before obtaining the sample file information and the sample key information of the sample file information, the method further comprises:
acquiring information of a file to be selected and a quality assessment result of the information of the file to be selected;
and selecting file information with a quality assessment result meeting a preset assessment condition from the file information to be selected as the sample file information.
4. The method according to claim 1, wherein the target information further includes target domain information, and the obtaining target keyword information in the target information includes:
acquiring the target field information and field keyword information, wherein the field keyword information is keyword information suitable for each field;
determining the determined meaning of the domain keyword information in the domain category to which the target domain belongs;
and taking the keyword information with the determined meaning as the target keyword information.
5. The method of claim 4, wherein prior to obtaining the target domain information and domain keyword information, the method further comprises:
acquiring information of a file to be selected and information of a field to be selected in the information of the file to be selected;
and performing domain classification on the information of the domain to be selected to obtain a domain category.
6. The method of claim 1, wherein after inputting the target keyword information into a target document generation model, obtaining target document information of the target person output by the target document generation model that matches the target document template, the method further comprises:
acquiring updated file information sent by the target personnel aiming at the target file information;
acquiring the update keyword information in the update file information;
and inputting the updated keyword information into the target file generation model to obtain the optimized file information output by the target file generation model.
7. The method of claim 2, wherein said adjusting model parameters of said initial file generation model comprises:
and adjusting parameters in a natural language generation algorithm of the initial file generation model so as to enable the natural language generation algorithm to be more accurate.
8. An apparatus for automatically generating document information, the apparatus comprising:
the acquisition module is used for acquiring target keyword information and template category information in the target information of the target personnel;
the selecting module is used for selecting a target file template matched with the template category information from a plurality of file templates;
and the input and output module is used for inputting the target keyword information into a target file generation model to obtain the target file information of the target personnel, which is output by the target file generation model and matched with the target file template.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 7 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011320860.5A CN112434504B (en) | 2020-11-23 | Method, apparatus, electronic device and computer readable medium for generating file information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011320860.5A CN112434504B (en) | 2020-11-23 | Method, apparatus, electronic device and computer readable medium for generating file information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112434504A true CN112434504A (en) | 2021-03-02 |
| CN112434504B CN112434504B (en) | 2024-07-16 |
Family
ID=
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743884A (en) * | 2021-08-05 | 2021-12-03 | 核动力运行研究所 | Production experience management method and device for nuclear power plant |
| CN114187605A (en) * | 2021-12-13 | 2022-03-15 | 苏州方兴信息技术有限公司 | Data integration method and device and readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120084633A1 (en) * | 2010-10-04 | 2012-04-05 | King Fahd University Of Petroleum And Minerals | Method of generating a graphical resume |
| CN104050532A (en) * | 2014-06-19 | 2014-09-17 | 高海逵 | Resume generating method and resume generating system |
| US20160124933A1 (en) * | 2014-10-30 | 2016-05-05 | International Business Machines Corporation | Generation apparatus, generation method, and program |
| CN106021389A (en) * | 2016-05-12 | 2016-10-12 | 新华通讯社 | System and method for automatically generating news based on template |
| CN107957984A (en) * | 2016-10-14 | 2018-04-24 | 深圳梵摩健康科技有限公司 | The resume generation method and system of job hunter |
| CN108897726A (en) * | 2018-05-03 | 2018-11-27 | 平安科技（深圳）有限公司 | A kind of creation method, storage medium and the server of electronics resume |
| CN109446505A (en) * | 2018-10-31 | 2019-03-08 | 广东小天才科技有限公司 | Model essay generation method and system |
| US20190156292A1 (en) * | 2006-03-31 | 2019-05-23 | Monster Worldwide, Inc. | Apparatuses, methods and Systems for Automated Online Data Submission |
| CN110162623A (en) * | 2019-04-15 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Soft text automatic generation method, device, computer equipment and storage medium |
| CN110390086A (en) * | 2018-04-19 | 2019-10-29 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and storage medium generating text |
| CN110399476A (en) * | 2019-06-18 | 2019-11-01 | 平安科技（深圳）有限公司 | Generation method, device, equipment and the storage medium of talent's portrait |
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190156292A1 (en) * | 2006-03-31 | 2019-05-23 | Monster Worldwide, Inc. | Apparatuses, methods and Systems for Automated Online Data Submission |
| US20120084633A1 (en) * | 2010-10-04 | 2012-04-05 | King Fahd University Of Petroleum And Minerals | Method of generating a graphical resume |
| CN104050532A (en) * | 2014-06-19 | 2014-09-17 | 高海逵 | Resume generating method and resume generating system |
| US20160124933A1 (en) * | 2014-10-30 | 2016-05-05 | International Business Machines Corporation | Generation apparatus, generation method, and program |
| CN106021389A (en) * | 2016-05-12 | 2016-10-12 | 新华通讯社 | System and method for automatically generating news based on template |
| CN107957984A (en) * | 2016-10-14 | 2018-04-24 | 深圳梵摩健康科技有限公司 | The resume generation method and system of job hunter |
| CN110390086A (en) * | 2018-04-19 | 2019-10-29 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and storage medium generating text |
| CN108897726A (en) * | 2018-05-03 | 2018-11-27 | 平安科技（深圳）有限公司 | A kind of creation method, storage medium and the server of electronics resume |
| CN109446505A (en) * | 2018-10-31 | 2019-03-08 | 广东小天才科技有限公司 | Model essay generation method and system |
| CN110162623A (en) * | 2019-04-15 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Soft text automatic generation method, device, computer equipment and storage medium |
| CN110399476A (en) * | 2019-06-18 | 2019-11-01 | 平安科技（深圳）有限公司 | Generation method, device, equipment and the storage medium of talent's portrait |
Non-Patent Citations (1)
| Title |
|---|
| 张雨雨;李嘉明;汪鑫飞;赖长权;邹超;: "基于Web的简历自动生成***的设计与实现", 电脑知识与技术, no. 34 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743884A (en) * | 2021-08-05 | 2021-12-03 | 核动力运行研究所 | Production experience management method and device for nuclear power plant |
| CN114187605A (en) * | 2021-12-13 | 2022-03-15 | 苏州方兴信息技术有限公司 | Data integration method and device and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cobey et al. | What is a predatory journal? A scoping review | |
| CN112631997B (en) | Data processing method, device, terminal and storage medium | |
| US9268766B2 (en) | Phrase-based data classification system | |
| Capuano et al. | Sentiment analysis for customer relationship management: an incremental learning approach | |
| US20200050620A1 (en) | Artificially intelligent system employing modularized and taxonomy-based classifications to generated and predict compliance-related content | |
| WO2019043381A1 (en) | Content scoring | |
| US20160246772A1 (en) | Systems and methods for advanced grammar checking | |
| US20230136368A1 (en) | Text keyword extraction method, electronic device, and computer readable storage medium | |
| Ahasanuzzaman et al. | CAPS: a supervised technique for classifying Stack Overflow posts concerning API issues | |
| CN109101489B (en) | Text automatic summarization method and device and electronic equipment | |
| KR20200139008A (en) | User intention-analysis based contract recommendation and autocomplete service using deep learning | |
| Lozano | Ethics of using language editing services in an era of digital communication and heavily multi-authored papers | |
| Lind et al. | Greasing the wheels for comparative communication research: Supervised text classification for multilingual corpora | |
| CN115309885A (en) | Knowledge graph construction, retrieval and visualization method and system for scientific and technological service | |
| Anastasiei et al. | Automated vs manual content analysis–A retrospective look | |
| Liu et al. | Supporting features updating of apps by analyzing similar products in App stores | |
| Procko et al. | Towards Improved Scientific Knowledge Proliferation: Leveraging Large Language Models on the Traditional Scientific Writing Workflow | |
| Dong et al. | A Scoping Review of ChatGPT Research in Accounting and Finance | |
| Owda et al. | Financial discussion boards irregularities detection system (fdbs-ids) using information extraction | |
| Moorkens | Measuring consistency in translation memories: a mixed-methods case study | |
| Saldaña | Sentiment analysis for exploratory data analysis | |
| CN110717008A (en) | Semantic recognition-based search result ordering method and related device | |
| US20200202074A1 (en) | Semsantic parsing | |
| CN112434504B (en) | Method, apparatus, electronic device and computer readable medium for generating file information | |
| CN112434504A (en) | Method and device for generating file information, electronic equipment and computer readable medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Technology Holding Co.,Ltd. Address before: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant before: Jingdong Digital Technology Holding Co.,Ltd. |
|
| GR01 | Patent grant |