CN117573852A - Task processing method, device, equipment and medium for intelligent office - Google Patents
Task processing method, device, equipment and medium for intelligent office Download PDFInfo
- Publication number
- CN117573852A CN117573852A CN202410065952.5A CN202410065952A CN117573852A CN 117573852 A CN117573852 A CN 117573852A CN 202410065952 A CN202410065952 A CN 202410065952A CN 117573852 A CN117573852 A CN 117573852A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- result
- semantic
- task
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 16
- 230000010354 integration Effects 0.000 claims description 9
- 230000006399 behavior Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 16
- 238000013473 artificial intelligence Methods 0.000 abstract description 11
- 230000006870 function Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 6
- 206010063385 Intellectualisation Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005065 mining 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
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/604—Tools and structures for managing or administering access control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- Bioethics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the field of artificial intelligence, and particularly discloses a task processing method, device, equipment and medium for intelligent office, wherein the task processing method for intelligent office comprises the following steps: pushing a corresponding user login interface based on the user ID; responding to a task request generated on a user login interface, and acquiring an interface processing mode corresponding to the task request; if the interface processing mode corresponds to the intelligent model end, acquiring a semantic extraction result of the task request and acquiring an internal matching result; responding to demand matching feedback generated by an internal matching result, and pushing at least one intelligent model to be selected if the demand matching feedback is continuous matching; responding to a target intelligent model generated by at least one intelligent model to be selected, so as to acquire an intelligent feedback result output by the target intelligent model; the method can effectively improve task solution efficiency, promote intelligent feedback results accurately corresponding to task requests, and achieve intelligentization of task processing.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a task processing method, apparatus, device, and medium for intelligent office.
Background
In recent years, the development of a series of AIGC (Artificial Intelligence Generated Content, content-generated artificial intelligence) achievements at home and abroad represents the arrival of the AI artificial intelligence era. The artificial intelligence technology is characterized in that through intelligent algorithm and big data analysis, an established AI model has application scenes far exceeding the category of conversation chat, and is deeply changing various industries such as office, electronic commerce, entertainment, education, media and the like, and leading the artificial intelligence to realize transition from perception to intelligent creation. Currently, enterprises face digital transformation, and how to control operation cost by adopting more advanced technological means such as artificial intelligence and the like and simplify enterprise architecture, so that improvement of production efficiency is a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a task processing method, device, equipment and medium for intelligent office, which are used for solving the problems of controlling operation cost by adopting more advanced technological means such as artificial intelligence and the like and simplifying enterprise architecture so as to improve production efficiency.
A task processing method for intelligent office, comprising:
acquiring a system login request carrying a user ID, and pushing a corresponding user login interface based on the user ID;
responding to a task request generated on a user login interface, and acquiring an interface processing mode corresponding to the task request;
if the interface processing mode corresponds to the intelligent model end, acquiring a semantic extraction result of the task request, and carrying out semantic matching on the semantic extraction result in an internal knowledge base to acquire an internal matching result;
responding to demand matching feedback generated by an internal matching result, and pushing at least one intelligent model to be selected if the demand matching feedback is continuous matching;
and responding to a target intelligent model generated by at least one intelligent model to be selected, and inputting a task request to the target intelligent model, so as to acquire an intelligent feedback result output by the target intelligent model and output the intelligent feedback result.
A task processing device for intelligent office, comprising:
the login request acquisition module is used for acquiring a system login request carrying a user ID and pushing a corresponding user login interface based on the user ID;
the processing mode acquisition module is used for responding to a task request generated on the user login interface and acquiring an interface processing mode corresponding to the task request;
the matching result acquisition module is used for acquiring a semantic extraction result of the task request if the interface processing mode corresponds to the intelligent model end, and carrying out semantic matching on the semantic extraction result in the internal knowledge base to acquire an internal matching result;
the intelligent model pushing module is used for responding to the demand matching feedback generated by the internal matching result, and pushing at least one intelligent model to be selected if the demand matching feedback is continuous matching;
and the feedback result output module is used for responding to the target intelligent model generated by the at least one intelligent model to be selected, inputting the task request into the target intelligent model, thereby acquiring an intelligent feedback result output by the target intelligent model and outputting the intelligent feedback result.
In some embodiments, the task processing device for intelligent office is further configured to input an intelligent feedback result and a task request into a problem integration model for processing, where the problem integration model is configured to output a semantic question-answer body in a question-answer form, and the semantic question-answer body includes a semantic problem corresponding to the task request; and saving the semantic question and answer to an internal knowledge base, and taking the semantic question as a query keyword.
In some embodiments, the task processing device for intelligent office is further configured to perform chapter point analysis on the semantic question answer to obtain a chapter analysis result, where the chapter analysis result includes at least one first-level directory and at least one second-level directory; according to at least one first-level directory and at least one second-level directory, the semantic question-answering body is stored to a directory position corresponding to the chapter analysis result for storage; if the chapter analysis result has a change effect on the directory number of the directory set, dynamically adjusting the directory number of the directory set; after the demand matching feedback generated in response to the internal matching result, further comprising: if the demand matching feedback is successful, acquiring a semantic answer in a semantic question-answer body corresponding to the task request; searching at least one semantic question-answer body associated with the directory position as a recommendation question-answer body according to the directory position corresponding to the semantic answer; the semantic answers are pushed as a main answer part, and the recommended questioning answers are pushed as a recommended part.
In some embodiments, the task processing device for intelligent office is further configured to obtain a module login request including a target function area, and push a corresponding function area page based on the target function area, where the target function area includes at least one of a social area, a financial area, a programming area, a document area, an image processing area, and a retrieval area.
In some embodiments, the task processing device for intelligent office is further configured to perform operation record on user operation, generate an operation log, and perform keyword scanning on the operation log to obtain a keyword scanning result; if the keyword scanning result is that the sensitive keyword exists, acquiring a user ID corresponding to the user operation as a target ID; performing security level analysis on the operation log to obtain an operation behavior grading result; and according to the operation behavior grading result, performing operation control on the user corresponding to the target ID.
In some embodiments, the task processing device for intelligent office is further configured to perform keyword scanning on the intelligent feedback result, and obtain a keyword scanning result; and if the keyword scanning result is that the sensitive keyword exists as the shielding keyword, re-inputting the task request into the target intelligent model, and prompting the target intelligent model to avoid adopting the shielding keyword in the intelligent feedback result.
In some embodiments, the task processing device for intelligent office is further configured to perform request hit rate analysis on each intelligent model at the intelligent model end periodically, and obtain a model hit rate ranking corresponding to the request hit rate analysis; pushing at least one candidate intelligent model, comprising: and pushing a specified number of intelligent models to be selected to the user according to the order of the model hit rate ranking from large to small.
An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the task processing method for intelligent offices as described above when executing the computer program.
A computer readable medium storing a computer program which, when executed by a processor, implements the task processing method for intelligent office as described above.
According to the task processing method, device, equipment and medium for intelligent office work, the task request is input into the internal knowledge base or the flexibly selected target intelligent model to obtain the intelligent feedback result accurately matched with the task request, so that the task solution efficiency can be effectively improved, the intelligent feedback result accurately corresponding to the task request is improved, the intellectualization of task processing is realized, and enterprises are helped to build digital ecology, thereby accelerating the digitizing process.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an application environment of a task processing method for intelligent office according to an embodiment of the invention;
FIG. 2 is a flow chart of a task processing method for intelligent office according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a task processing device for intelligent office according to an embodiment of the invention;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the invention.
Description of the embodiments
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The task processing method for intelligent office provided by the embodiment of the invention can be applied to an application environment as shown in fig. 1, and is applied to a task processing system for intelligent office, wherein the task processing system for intelligent office comprises a client and a server, and the client communicates with the server through a network. The client is also called a client, and refers to a program corresponding to a server and providing local services for the client. Further, the client is a computer-side program, an APP program of the intelligent device or a third party applet embedded with other APP. The client may be installed on, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, portable wearable devices, and other electronic devices. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a task processing method for intelligent office is provided, and the method is applied to the server in fig. 1 for illustration, and specifically includes the following steps:
s110, acquiring a system login request carrying a user ID, and pushing a corresponding user login interface based on the user ID.
Specifically, the user ID is a unique identity of the user logging in the task processing system for intelligent office. It is understood that different users may view different rights of content according to the job level or identity of the enterprise division.
The effect of this embodiment is that, according to the viewing authority corresponding to the user ID, the system can push the user login interface corresponding to the user authority to the user. Furthermore, the user login interface can also be set up and displayed on a page according to the individuation of the user. And the menu authority is reasonably controlled, the number of the user Token is limited, and the safety of the enterprise asset and the system is ensured.
S120, responding to a task request generated on a user login interface, and acquiring an interface processing mode corresponding to the task request.
Specifically, the user may generate various task requests, such as continuing a previous task, composing a new document, querying a file, etc., based on the user login interface.
The interface processing mode is a processing mode of the task request, for example, the task request may be processed in a conventional task processing manner, or the interface processing mode may be processed through a mode of an AIGC (Artificial Intelligence Generated Content, content-generating artificial intelligence) interface, that is, an intelligent model side.
S130, if the interface processing mode corresponds to the intelligent model end, acquiring a semantic extraction result of the task request, and carrying out semantic matching on the semantic extraction result in an internal knowledge base to acquire an internal matching result.
Specifically, in this embodiment, after the task request is subjected to voice analysis and processing through the natural language processing model to be in a problem format, the problem is searched in the internal knowledge base owned by the enterprise, so as to obtain a search result, that is, an internal matching result.
S140, responding to demand matching feedback generated by the internal matching result, and pushing at least one intelligent model to be selected if the demand matching feedback is continuous matching.
Specifically, the user may match the feedback based on whether the internal match result feedback meets the requirements of his intended reply. When the feedback of the internal matching result does not meet the expected reply of the user, the user can generate a continuous matching requirement based on the task request. At this time, the system flexibly calls a plurality of embedded intelligent models to be selected.
Current commercially available generated AI models include: the system can be associated with the generated AI models, and the user can flexibly select the AI models in the system.
S150, responding to a target intelligent model generated by at least one intelligent model to be selected, inputting a task request into the target intelligent model, thereby obtaining an intelligent feedback result output by the target intelligent model, and outputting the intelligent feedback result.
Specifically, the target intelligent model determines an intelligent model to be used based on a plurality of intelligent models to be selected; the intelligent feedback result is a corresponding task solution that the intelligent model pushes according to the task request, for example, a transcoding result, a grammar correction result, a data generation result, a Bug repair result or a code interpretation result, etc.
According to the task processing method for intelligent office, the task request is input to the internal knowledge base or the flexibly selected target intelligent model, the intelligent feedback result accurately matched with the task request is obtained, the task solving efficiency can be effectively improved, the intelligent feedback result accurately corresponding to the task request is improved, the intellectualization of task processing is realized, and enterprises are helped to build digital ecology so that the digitizing process is accelerated.
In a specific embodiment, after step S150, that is, after obtaining the smart feedback result output by the target smart model, the method further specifically includes the following steps:
s1501, inputting an intelligent feedback result and a task request into a problem integration model for processing, wherein the problem integration model is used for outputting a semantic question-answering body conforming to a question-answering form, and the semantic question-answering body comprises a semantic problem corresponding to the task request.
S1502, saving the semantic question and answer to an internal knowledge base, and taking the semantic question as a query keyword.
Specifically, the question integration model is a model for converting a task request into a question and converting an intelligent feedback result into an answer corresponding to the question, so as to generate a model of a speech segment of a pair of questions and answers (semantic questions and answers); it can be understood that the task of the user is realized by the task request, so that the semantic problem corresponding to the task request is used as the query keyword corresponding to the internal knowledge base, and the solution corresponding to the problem corresponding to the user requirement can be accurately and rapidly found.
Preferably, the semantic question-answer body further comprises a semantic answer; in step S1502, the semantic question and answer is saved to an internal knowledge base, which specifically includes the following steps:
s5021, analyzing chapter points of the semantic question answer to obtain chapter analysis results, wherein the chapter analysis results comprise at least one first-level catalogue and at least one second-level catalogue.
S5022, according to at least one first-level catalogue and at least one second-level catalogue, the semantic question-answering body is stored to a catalogue position corresponding to the chapter analysis result to be stored.
S5023, if the chapter analysis result has a change effect on the directory number of the directory set, dynamically adjusting the directory number of the directory set.
Specifically, analyzing chapter points, namely performing similarity matching on the characters in the semantic question-answering body and the characters in the internal knowledge base through a natural language model; the paragraphs with high similarity are subjected to semantic comparison to obtain text arrangement sequences, namely chapter analysis results, including a first-level catalog and a second-level catalog, such as the section of the chapter, the section of the section, and the like, which are not particularly limited herein; for example, the task request is:
step X comprises which refining steps, and the catalogue corresponding to the chapter related to the step X is a third section of the second chapter; the step related to the third section of the second chapter is the step X-1, so the catalog corresponding to the step X is the fourth section of the second chapter; it can be understood that if the original directory has the fourth section of the second chapter, the fourth section of the original second chapter should be dynamically updated to the fifth section of the second chapter as a new directory number, and other chapters are handled in the same manner, which is not described in detail. And storing the refinement step corresponding to the step X to the directory position corresponding to the fourth section of the second chapter.
After step S140, i.e. after the demand matching feedback generated in response to the internal matching result, further comprises:
s1401, if the demand matching feedback is successful, acquiring a semantic answer in a semantic question-answer body corresponding to the task request.
S1402, searching at least one semantic question-answering body associated with the directory location according to the directory location corresponding to the semantic answer as a recommendation question-answering body.
S1403, pushing the semantic answer as a main answer part, and pushing the recommendation question answer as a recommendation part.
Specifically, if the user task requests the semantic answer acquired by the internal knowledge base to be an accurate solution, that is, the requirement matching feedback is successful.
Preferably, according to the embodiment, according to the catalog position corresponding to the semantic answer in the catalog, the content closely related to the semantic answer is obtained as a recommendation question-answering body and is simultaneously fed back to the user, so that the user can intelligently expand knowledge about the peripheral knowledge of the task request as a recommendation part, and the user can comprehensively understand the task request.
In a specific embodiment, between steps S110 and S120, i.e. after pushing the corresponding user login interface, and before responding to the task request generated on the user login interface, the method further specifically comprises the following steps:
s1101, acquiring a module login request comprising a target functional area, and pushing a corresponding functional area page based on the target functional area, wherein the target functional area comprises at least one of a social area, a financial area, a programming area, a document area, an image processing area and a retrieval area.
The system can integrate various requirements inside enterprises, such as social, financial and audit, programming, document writing, image processing and retrieval and the like, comprehensively provide intelligent support, realize more efficient document writing, code writing, picture design and the like, and store in an internal knowledge base;
for the writing of the text: document processing may be performed, such as: translation, abstract, outline, conversion, keyword extraction, meeting summary, comment, paragraph generator, recipe generator, product description and the like, so that the document processing efficiency is improved;
in terms of business socialization: the answer applicable to the enterprise can be obtained no matter what the user asks;
in the case of picture design: the product LOGO is given to intelligently generate a picture creative by clear description, and the description is perfected for a plurality of times until a satisfactory picture is generated; informing GPT of theme and description to quickly generate and export file and creative material of the graphic and text;
in the case of an internal knowledge base: uploading file data, establishing a file index, forming an enterprise knowledge base, and constructing an enterprise internal knowledge mining and question-answering system;
in terms of code writing: code conversion, grammar correction, data generator, address extractor, code annotation generation, SQL generation, bug repair, code interpreter, etc.;
the method provided in this embodiment is for an internal knowledge base: the method can realize professional knowledge communication, proposal, decision analysis and the like, and accumulate experience into an enterprise internal knowledge base; further, the target function area may further include: self-service customer service, voice processing, automatic process arrangement, automatic bid document writing and the like.
In a specific embodiment, the task processing method for intelligent office further specifically includes the following steps:
s211, performing operation record on user operation, generating an operation log, and performing keyword scanning on the operation log to obtain a keyword scanning result.
S212, if the keyword scanning result is a sensitive keyword, acquiring a user ID corresponding to the user operation as a target ID.
S213, performing security level analysis on the operation log to obtain an operation behavior grading result.
S214, performing operation control on the user corresponding to the target ID according to the operation behavior grading result.
Specifically, the security level analysis is to confirm whether the authority corresponding to the user can view the sensitive keyword according to the target ID; and according to the grading result obtained by the security level analysis, matching how to perform operation control on the user corresponding to the target ID, including: warning, reminding that account numbers cannot be checked or blocked, and the like, so that the use safety of the system is improved.
The embodiment can record user operation and limit sensitive keywords so that the system is safe and compliant in use.
In a specific embodiment, after step S150, that is, after obtaining the smart feedback result output by the target smart model, the method further specifically includes the following steps:
s5021, performing keyword scanning on the intelligent feedback result to obtain a keyword scanning result.
S5022, if the keyword scanning result is that the sensitive keyword exists as the shielding keyword, the task request is input into the target intelligent model again, and the target intelligent model is prompted to avoid adopting the shielding keyword in the intelligent feedback result.
Specifically, the embodiment can flexibly inform the target intelligent model of which sensitive keywords are avoided, so that the method is more suitable for enterprises, and the safety, the intelligence and the flexibility of task requests are improved.
In a specific embodiment, the task processing method for intelligent office further specifically includes the following steps:
s5031, carrying out request hit rate analysis on each intelligent model at the intelligent model end at regular intervals, and obtaining a model hit rate ranking corresponding to the request hit rate analysis.
Preferably, in step S140, pushing at least one smart model to be selected includes:
s141, pushing a designated number of intelligent models to be selected to a user according to the order of the model hit rate ranking from large to small.
Specifically, due to the difference of the analysis capability of each intelligent model, the system can flexibly analyze the hit rate according to the adoption degree of the intelligent model in a certain period to the result of the feedback of the request task, so that the hit rate of the model is ranked for all the referenced intelligent models in a period, and then the result is pushed to the user, and the task processing accuracy and the processing efficiency of the system are further improved.
The task processing method for intelligent office provided by the embodiment can be privately deployed in an enterprise, and the integrated machine is installed in the enterprise intranet to prevent information leakage and comprises the following steps: sensitive word filtering, auditing record and other functions, thereby becoming a 24-hour task assistant for enterprise users and becoming a knowledge document management platform for enterprises.
According to the task processing method for intelligent office, the task request is input to the internal knowledge base or the flexibly selected target intelligent model, the intelligent feedback result accurately matched with the task request is obtained, the task solving efficiency can be effectively improved, the intelligent feedback result accurately corresponding to the task request is improved, the intellectualization of task processing is realized, and enterprises are helped to build digital ecology so that the digitizing process is accelerated.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, a task processing device for intelligent office is provided, where the task processing device for intelligent office corresponds to the task processing method for intelligent office in the above embodiment one by one; as shown in fig. 3, the task processing device for intelligent office includes a login request acquiring module 110, a processing mode acquiring module 120, a matching result acquiring module 130, an intelligent model pushing module 140, and a feedback result outputting module 150; the functional modules are described in detail as follows:
the login request obtaining module 110 is configured to obtain a system login request carrying a user ID, and push a corresponding user login interface based on the user ID.
The processing mode obtaining module 120 is configured to obtain an interface processing mode corresponding to the task request in response to the task request generated on the user login interface.
The matching result obtaining module 130 is configured to obtain a semantic extraction result of the task request if the interface processing mode corresponds to the intelligent model end, and perform semantic matching on the semantic extraction result in the internal knowledge base to obtain an internal matching result.
The intelligent model pushing module 140 is configured to respond to a demand matching feedback generated by the internal matching result, and if the demand matching feedback is continuous matching, push at least one intelligent model to be selected.
And the feedback result output module 150 is configured to input a task request to the target intelligent model in response to the target intelligent model generated by the at least one intelligent model to be selected, thereby obtaining an intelligent feedback result output by the target intelligent model, and outputting the intelligent feedback result.
Preferably, the task processing device for intelligent office further comprises:
the semantic question-answering body output module is used for inputting the intelligent feedback result and the task request into the question integration model for processing, and outputting the semantic question-answering body conforming to the question-answering form by the question integration model, wherein the semantic question-answering body comprises a semantic question corresponding to the task request.
And the question-answer body storage module is used for storing the semantic question-answer body into an internal knowledge base and taking the semantic problem as a query keyword.
Preferably, the question and answer saving module includes:
and the chapter result analysis sub-module is used for analyzing the chapter points of the semantic question and answer to obtain chapter analysis results, wherein the chapter analysis results comprise at least one first-level catalogue and at least one second-level catalogue.
And the questioning and answering body storage sub-module is used for storing the semantic questioning and answering body to the directory position corresponding to the chapter analysis result for storage according to at least one first-level directory and at least one second-level directory.
And the catalog number adjustment sub-module is used for dynamically adjusting the catalog number of the catalog set if the chapter analysis result has a change influence on the catalog number of the catalog set.
Preferably, the task processing device for intelligent office further comprises:
and the semantic answer acquisition module is used for acquiring the semantic answer in the semantic question-answer body corresponding to the task request if the demand matching feedback is successful.
And the questioning and answering body searching module is used for searching at least one semantic questioning and answering body associated with the directory position as a recommended questioning and answering body according to the directory position corresponding to the semantic answer.
And the recommendation part pushing module is used for pushing the semantic answer as a main answer part and pushing the recommendation question-answer body as a recommendation part.
Preferably, the task processing device for intelligent office further comprises:
the module login acquisition module is used for acquiring a module login request comprising a target functional area, pushing a corresponding functional area page based on the target functional area, wherein the target functional area comprises at least one of a social area, a financial area, a programming area, a document area, an image processing area and a retrieval area.
Preferably, the task processing device for intelligent office further comprises:
the operation log generation module is used for carrying out operation record on user operation, generating an operation log, and carrying out keyword scanning on the operation log to obtain a keyword scanning result.
And the target ID acquisition module is used for acquiring a user ID corresponding to the user operation as a target ID if the keyword scanning result is a sensitive keyword.
And the grading result acquisition module is used for carrying out security level analysis on the operation log and acquiring an operation behavior grading result.
And the user operation control module is used for performing operation control on the user corresponding to the target ID according to the operation behavior grading result.
Preferably, the task processing device for intelligent office further comprises:
and the scanning result acquisition module is used for carrying out keyword scanning on the intelligent feedback result to acquire a keyword scanning result.
And the intelligent model lifting module is used for re-inputting the task request into the target intelligent model if the keyword scanning result is that the sensitive keyword exists as the shielding keyword, and prompting the target intelligent model to avoid adopting the shielding keyword in the intelligent feedback result.
Preferably, the task processing device for intelligent office further comprises:
the hit rate ranking module is used for periodically carrying out request hit rate analysis on each intelligent model at the intelligent model end and obtaining a model hit rate ranking corresponding to the request hit rate analysis.
Further, the smart model pushing module 140 includes:
and the intelligent module pushing sub-module is used for pushing the appointed number of the intelligent models to be selected to the user according to the order of the model hit rate ranking from large to small.
For specific limitations on the task processing device for intelligent office, reference may be made to the above limitation on the task processing method for intelligent office, and detailed description thereof will be omitted herein; the above-mentioned various modules in the task processing device for intelligent office may be implemented in whole or in part by software, hardware, and combinations thereof; the above modules may be embedded in hardware or independent of a processor in the electronic device, or may be stored in software in a memory in the electronic device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, an electronic device is provided, which may be a server, and an internal structure thereof may be as shown in fig. 4; the electronic device comprises a processor, a memory, a network interface and a database which are connected through a system bus; wherein the processor of the electronic device is configured to provide computing and control capabilities; the memory of the electronic device includes a non-volatile medium, an internal memory; the nonvolatile medium stores an operating system, computer programs, and a database; the internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile media; the database of the electronic equipment is used for data related to the task processing method of intelligent office; the network interface of the electronic equipment is used for communicating with an external terminal through network connection; the computer program, when executed by a processor, implements a task processing method for intelligent office.
In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the computer program to implement the task processing method for intelligent office according to the above embodiment, for example, S110 to S150 shown in fig. 2; alternatively, the processor may implement the functions of each module/unit of the task processing device for intelligent office in the above embodiment, such as the functions of the modules 110 to 150 shown in fig. 3, when executing the computer program; to avoid repetition, no further description is provided here.
In one embodiment, a computer readable medium is provided, on which a computer program is stored, which when executed by a processor implements the task processing method for intelligent office according to the above embodiment, for example, S110 to S150 shown in fig. 2; alternatively, the computer program when executed by the processor implements the functions of the modules/units in the task processing device for intelligent office in the above-described device embodiment, for example, the functions of the modules 110 to 150 shown in fig. 3; to avoid repetition, no further description is provided here.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable medium, which when executed, may comprise the steps of embodiments of the methods described above; any reference to memory, storage, database, or other medium used in embodiments of the present application may include non-volatile and/or volatile memory; the nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory; volatile memory can include Random Access Memory (RAM) or external cache memory; by way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. A task processing method for intelligent office, comprising:
acquiring a system login request carrying a user ID, and pushing a corresponding user login interface based on the user ID;
responding to a task request generated on the user login interface, and acquiring an interface processing mode corresponding to the task request;
if the interface processing mode corresponds to the intelligent model end, acquiring a semantic extraction result of the task request, and carrying out semantic matching on the semantic extraction result in an internal knowledge base to acquire an internal matching result;
responding to demand matching feedback generated by the internal matching result, and pushing at least one intelligent model to be selected if the demand matching feedback is continuous matching;
and responding to a target intelligent model generated by at least one intelligent model to be selected, inputting the task request into the target intelligent model, thereby acquiring an intelligent feedback result output by the target intelligent model, and outputting the intelligent feedback result.
2. The task processing method for intelligent office according to claim 1, further comprising, after obtaining the intelligent feedback result output by the target intelligent model:
the intelligent feedback result and the task request are input into a problem integration model for processing, so that the problem integration model outputs a semantic question-answering body conforming to a question-answering form, wherein the semantic question-answering body comprises a semantic problem corresponding to the task request;
and storing the semantic question and answer to the internal knowledge base, and taking the semantic question as a query keyword.
3. The task processing method for intelligent office according to claim 2, wherein the semantic question-answering body further includes a semantic answer;
the saving the semantic question-answer body to the internal knowledge base comprises the following steps:
performing chapter analysis on the semantic question answer to obtain chapter analysis results, wherein the chapter analysis results comprise at least one first-level catalogue and at least one second-level catalogue;
according to at least one first-level directory and at least one second-level directory, the semantic question-answering body is stored to a directory position corresponding to the chapter analysis result for storage;
if the chapter analysis result has a change influence on the directory number of the directory set, dynamically adjusting the directory number of the directory set;
after the demand matching feedback generated in response to the internal matching result, further comprising:
if the demand matching feedback is successful, acquiring a semantic answer in a semantic question-answer body corresponding to the task request;
searching at least one semantic question-answer body associated with the directory position as a recommended question-answer body according to the directory position corresponding to the semantic answer;
pushing the semantic answer as a main answer part, and pushing the recommended questioning answer as a recommended part.
4. The task processing method for intelligent office according to claim 1, further comprising, after said pushing the corresponding user login interface and before said responding to the task request generated on the user login interface:
and acquiring a module login request comprising a target functional area, and pushing a corresponding functional area page based on the target functional area, wherein the target functional area comprises at least one of a social area, a financial area, a programming area, a document area, an image processing area and a retrieval area.
5. The task processing method for intelligent office according to claim 1, further comprising:
performing operation record on user operation, generating an operation log, and performing keyword scanning on the operation log to obtain a keyword scanning result;
if the keyword scanning result is that a sensitive keyword exists, acquiring a user ID corresponding to user operation as a target ID;
performing security level analysis on the operation log to obtain an operation behavior grading result;
and according to the operation behavior grading result, performing operation control on the user corresponding to the target ID.
6. The task processing method for intelligent office according to claim 1, further comprising, after the obtaining the intelligent feedback result output by the target intelligent model:
keyword scanning is carried out on the intelligent feedback result, and a keyword scanning result is obtained;
and if the keyword scanning result is that the sensitive keyword exists as a shielding keyword, re-inputting the task request into the target intelligent model, and prompting the target intelligent model to avoid adopting the shielding keyword in an intelligent feedback result.
7. The task processing method for intelligent office according to claim 1, further comprising:
carrying out request hit rate analysis on each intelligent model of the intelligent model end at regular intervals, and obtaining a model hit rate ranking corresponding to the request hit rate analysis;
the pushing at least one intelligent model to be selected comprises the following steps:
and pushing a designated number of the intelligent models to be selected to a user according to the order of the hit rate ranking of the models from large to small.
8. A task processing device for intelligent office, comprising:
the login request acquisition module is used for acquiring a system login request carrying a user ID and pushing a corresponding user login interface based on the user ID;
the processing mode acquisition module is used for responding to the task request generated on the user login interface and acquiring an interface processing mode corresponding to the task request;
the matching result acquisition module is used for acquiring a semantic extraction result of the task request if the interface processing mode corresponds to the intelligent model end, carrying out semantic matching on the semantic extraction result in an internal knowledge base, and acquiring an internal matching result;
the intelligent model pushing module is used for responding to the demand matching feedback generated by the internal matching result, and pushing at least one intelligent model to be selected if the demand matching feedback is continuous matching;
and the feedback result output module is used for responding to a target intelligent model generated by at least one intelligent model to be selected, inputting the task request to the target intelligent model, thereby obtaining an intelligent feedback result output by the target intelligent model and outputting the intelligent feedback result.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the task processing method for intelligent offices according to any of claims 1 to 7 when executing the computer program.
10. A computer readable medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the task processing method for intelligent office according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410065952.5A CN117573852B (en) | 2024-01-17 | 2024-01-17 | Task processing method, device, equipment and medium for intelligent office |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410065952.5A CN117573852B (en) | 2024-01-17 | 2024-01-17 | Task processing method, device, equipment and medium for intelligent office |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117573852A true CN117573852A (en) | 2024-02-20 |
| CN117573852B CN117573852B (en) | 2024-03-22 |
Family
ID=89886795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410065952.5A Active CN117573852B (en) | 2024-01-17 | 2024-01-17 | Task processing method, device, equipment and medium for intelligent office |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117573852B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180373782A1 (en) * | 2017-06-27 | 2018-12-27 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for recommending answer to question based on artificial intelligence |
| CN110233879A (en) * | 2019-05-22 | 2019-09-13 | 平安银行股份有限公司 | Intelligently pushing interfacial process, device, computer equipment and storage medium |
| CN112965804A (en) * | 2021-03-25 | 2021-06-15 | 深圳市优必选科技股份有限公司 | Method, device, terminal, system and storage medium for processing information |
| CN117056495A (en) * | 2023-10-08 | 2023-11-14 | 吉奥时空信息技术股份有限公司 | Automatic question-answering method and system for government affair consultation |
| CN117149967A (en) * | 2023-08-18 | 2023-12-01 | 中国电信股份有限公司技术创新中心 | Response generation method, device, server and computer readable storage medium |
| CN117234774A (en) * | 2023-09-14 | 2023-12-15 | 中国建设银行股份有限公司湖南省分行 | Intelligent fault processing method, device, equipment and medium based on information system |
| CN117290484A (en) * | 2023-10-10 | 2023-12-26 | 深圳市明睿数据科技有限公司 | Intelligent question-answering system and method for automobile fault positioning and maintenance suggestion |
| CN117371532A (en) * | 2023-10-27 | 2024-01-09 | 浪潮工创(山东)供应链科技有限公司 | Knowledge base management method, system, equipment and medium |
-
2024
- 2024-01-17 CN CN202410065952.5A patent/CN117573852B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180373782A1 (en) * | 2017-06-27 | 2018-12-27 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for recommending answer to question based on artificial intelligence |
| CN110233879A (en) * | 2019-05-22 | 2019-09-13 | 平安银行股份有限公司 | Intelligently pushing interfacial process, device, computer equipment and storage medium |
| CN112965804A (en) * | 2021-03-25 | 2021-06-15 | 深圳市优必选科技股份有限公司 | Method, device, terminal, system and storage medium for processing information |
| CN117149967A (en) * | 2023-08-18 | 2023-12-01 | 中国电信股份有限公司技术创新中心 | Response generation method, device, server and computer readable storage medium |
| CN117234774A (en) * | 2023-09-14 | 2023-12-15 | 中国建设银行股份有限公司湖南省分行 | Intelligent fault processing method, device, equipment and medium based on information system |
| CN117056495A (en) * | 2023-10-08 | 2023-11-14 | 吉奥时空信息技术股份有限公司 | Automatic question-answering method and system for government affair consultation |
| CN117290484A (en) * | 2023-10-10 | 2023-12-26 | 深圳市明睿数据科技有限公司 | Intelligent question-answering system and method for automobile fault positioning and maintenance suggestion |
| CN117371532A (en) * | 2023-10-27 | 2024-01-09 | 浪潮工创(山东)供应链科技有限公司 | Knowledge base management method, system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117573852B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3855324A1 (en) | Associative recommendation method and apparatus, computer device, and storage medium | |
| CN111666401B (en) | Document recommendation method, device, computer equipment and medium based on graph structure | |
| US10650818B2 (en) | Semi-supervised question answering machine | |
| CN112651236B (en) | Method and device for extracting text information, computer equipment and storage medium | |
| CN108090351B (en) | Method and apparatus for processing request message | |
| CN112181489B (en) | Code migration method, device, computer equipment and storage medium | |
| CN110135888B (en) | Product information pushing method, device, computer equipment and storage medium | |
| US10628530B1 (en) | Systems and methods for generating a plain English interpretation of a legal clause | |
| CN111324713A (en) | Automatic replying method and device for conversation, storage medium and computer equipment | |
| CN112182174A (en) | Business question-answer knowledge query method and device, computer equipment and storage medium | |
| CN112559526A (en) | Data table export method and device, computer equipment and storage medium | |
| CN113051389B (en) | Knowledge pushing method and device | |
| CN114356968A (en) | Query statement generation method and device, computer equipment and storage medium | |
| CN117573852B (en) | Task processing method, device, equipment and medium for intelligent office | |
| CN116414961A (en) | Question-answering method and system based on military domain knowledge graph | |
| CN114969544A (en) | Hot data-based recommended content generation method, device, equipment and medium | |
| CN113254624B (en) | Intelligent question-answering processing method, device, equipment and medium based on artificial intelligence | |
| CN114547059A (en) | Platform data updating method and device and computer equipment | |
| CN112579944A (en) | Page jump processing method and device and electronic equipment | |
| CN110780850B (en) | Requirement case auxiliary generation method and device, computer equipment and storage medium | |
| CN113504836B (en) | Information input method and electronic equipment | |
| CN116701615B (en) | Service document online management method and device, electronic equipment and readable storage medium | |
| CN117827802B (en) | Hbase-based data processing system, method and device | |
| CN110807089B (en) | Question answering method and device and electronic equipment | |
| CN112580309B (en) | Document data processing method, device, computer equipment and storage 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |