CN113343116A - Intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse - Google Patents
Intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse Download PDFInfo
- Publication number
- CN113343116A CN113343116A CN202110763113.7A CN202110763113A CN113343116A CN 113343116 A CN113343116 A CN 113343116A CN 202110763113 A CN202110763113 A CN 202110763113A CN 113343116 A CN113343116 A CN 113343116A
- Authority
- CN
- China
- Prior art keywords
- data
- information
- user
- chat
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012216 screening Methods 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse, wherein the method comprises the following steps: acquiring characteristic information and input information of a user; retrieving related data in the data warehouse through a recommendation system according to the input information, screening the retrieved data by combining with the characteristic information, and recommending the data to a user; and feeding back the retrieval result and the screening result to the chat system, and sending corresponding reply terms to the user through the chat system according to the fed-back information. The invention combines the chat system and the recommendation system, realizes automatic reply to the problem and simultaneously recommends the most appropriate data which can solve the user problem, can greatly increase the efficiency of knowing the company and acquiring the target product information by the client, saves the labor cost and further realizes intelligent office.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse counting.
Background
With the development of the internet, social networking tools (such as WeChat, enterprise WeChat and the like) have become more and more popular in daily life and work of people, and meanwhile, great convenience is brought to life and work of people. Then, with the circulation of a large amount of information, effective filtering of information, and organization of information have become topics of high social interest at present. Especially, in the daily work process, many large-scale enterprises can format and construct their own data (such as theme cards and databases) so as to conveniently query the required data in the using process. However, effective scheduling and use of such data is still a short board for enterprises today, and many relevant data need to be retrieved manually to obtain the required results. Meanwhile, the current intelligent question-answering system only stays at a dialogue level and simply searches relevant data from a search engine and feeds the relevant data back to a user.
Disclosure of Invention
Aiming at the technical problem that the scheduling and the use of the data in the database are not convenient enough, the invention provides an intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse.
In a first aspect, an embodiment of the present application provides an intelligent chat recommendation method based on enterprise warehouse, including:
an information acquisition step: acquiring characteristic information and input information of a user;
a data recommendation step: retrieving relevant data in a data warehouse through a recommendation system according to the input information, screening the retrieved data by combining the characteristic information, and recommending the data to the user;
and (3) automatic reply step: and feeding back the retrieval result and the screening result to a chat system, and sending a corresponding reply term to the user through the chat system according to the fed-back information.
The intelligent chatting recommendation method comprises the following steps:
and keyword retrieval: extracting key words in the input information, and retrieving in the data warehouse according to the key words;
data recall step: if the relevant data is searched out, recalling a certain amount of the data; if the relevant data is not searched out, the search result is fed back to the chat system;
a data screening step: and filtering and sorting the recalled data by combining the characteristic information, and recommending the data to the user according to a sorting result.
The intelligent chatting recommendation method comprises the following steps:
and (3) encoding and fusing: encoding and fusing the characteristic information and the input information;
a data sorting step: sorting the data according to the matching degree of the recalled data and the fused feature codes;
a feedback step: and selecting a certain amount of the data according to the sorting sequence, recommending the data to the user, and feeding back the data names to the chat system.
The intelligent chat recommendation method comprises the following steps of:
information classification step: classifying the input information in a text classification mode, and selecting different predefined answer operation frameworks according to different classes;
a speaking operation recovery step: and outputting a corresponding reply term according to the reply dialogue framework and the information fed back by the recommendation system.
In a second aspect, an embodiment of the present application provides an intelligent chat recommendation system based on enterprise warehouse, including:
an information acquisition unit: acquiring characteristic information and input information of a user;
the data recommending unit: retrieving relevant data in a data warehouse through a recommendation system according to the input information, screening the retrieved data by combining the characteristic information, and recommending the data to the user;
an automatic reply unit: and feeding back the retrieval result and the screening result to a chat system, and sending a corresponding reply term to the user through the chat system according to the fed-back information.
The above-mentioned intelligent chat recommendation system, wherein, the material recommendation unit includes:
a keyword retrieval module: extracting key words in the input information, and retrieving in the data warehouse according to the key words;
the data recall module: if the relevant data is searched out, recalling a certain amount of the data; if the relevant data is not searched out, the search result is fed back to the chat system;
the data screening module: and filtering and sorting the recalled data by combining the characteristic information, and recommending the data to the user according to a sorting result.
Above-mentioned intelligent chat recommendation system, wherein, the data screening module includes:
and a coding fusion module: encoding and fusing the characteristic information and the input information;
a data sorting module: sorting the data according to the matching degree of the recalled data and the fused feature codes;
a feedback module: and selecting a certain amount of the data according to the sorting sequence, recommending the data to the user, and feeding back the data names to the chat system.
The above-mentioned intelligent chat recommendation system, wherein, the automatic reply unit includes:
an information classification module: classifying the input information in a text classification mode, and selecting different predefined answer operation frameworks according to different classes;
a dialoging reply module: and outputting a corresponding reply term according to the reply dialogue framework and the information fed back by the recommendation system.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the intelligent chat recommendation method according to the first aspect is implemented.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the intelligent chat recommendation method according to the first aspect.
Compared with the prior art, the invention has the advantages and positive effects that:
1. the invention relates to the technical field of recommendation, and the scheme of combining a chat system and a recommendation system and constructing the chat system and the recommendation system in an enterprise warehouse can effectively utilize data resources of a company to a great extent, conveniently increase the acquisition efficiency of internal staff on related information, greatly increase the understanding of customers on the company and the acquisition efficiency of target product information, save labor cost and further realize intelligent office.
2. The invention provides a method for recommending the intelligent chatting based on the enterprise warehouse by combining a natural language processing technology and a recommending algorithm, which can recommend the required data and information for the user according to the characteristics of the user and the chatting content in the chatting process, improve the efficiency of acquiring the information by the staff and the effectiveness of the information, provide an effective and efficient channel for the client to know the condition of the company products and the related information, and save the labor cost to a certain extent.
Drawings
FIG. 1 is a schematic diagram illustrating steps of an intelligent chat recommendation method based on enterprise warehouse provided by the present invention;
FIG. 2 is a schematic flow chart based on step S2 in FIG. 1 according to the present invention;
FIG. 3 is a schematic flowchart based on step S23 in FIG. 2 according to the present invention;
FIG. 4 is a schematic flowchart based on step S3 in FIG. 1 according to the present invention;
FIG. 5 is a framework diagram of an intelligent chat recommendation system based on enterprise warehouse provided by the present invention;
FIG. 6 is a block diagram of an intelligent chat recommendation system provided by the present invention;
fig. 7 is a block diagram of a computer device according to an embodiment of the present application.
Wherein the reference numerals are:
1. an information acquisition unit; 2. a data recommending unit; 21. a keyword retrieval module; 22. a data recall module; 23. a data screening module; 231. a code fusion module; 232. a data sorting module; 233. a feedback module; 3. an automatic reply unit; 31. an information classification module; 32. a dialoging reply module; 81. a processor; 82. a memory; 83. a communication interface; 80. a bus.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The present invention is described in detail with reference to the embodiments shown in the drawings, but it should be understood that these embodiments are not intended to limit the present invention, and those skilled in the art should understand that functional, methodological, or structural equivalents or substitutions made by these embodiments are within the scope of the present invention.
Before describing in detail the various embodiments of the present invention, the core inventive concepts of the present invention are summarized and described in detail by the following several embodiments.
The invention mainly obtains the user requirement through the chat system and generates the corresponding reply dialect; and recommending required data and information for the user through a recommendation system according to the acquired requirements and the characteristics of the user.
The first embodiment is as follows:
fig. 1 is a schematic step diagram of an intelligent chat recommendation method based on enterprise warehouse provided by the invention. As shown in fig. 1, this embodiment discloses a specific implementation of an intelligent chat recommendation method (hereinafter referred to as "method") based on enterprise warehouse.
At present, a scheme of combining an intelligent question-answering system and an intelligent recommendation system to construct an enterprise warehouse is still a very new scheme, meanwhile, data resources of the enterprise can be utilized to a great extent, the acquisition efficiency of internal staff on related information can be increased, the acquisition efficiency of clients on company knowledge and target product information can be increased, the labor cost is saved, and intelligent office is further achieved.
Specifically, the method disclosed in this embodiment mainly includes the following steps:
step S1: acquiring characteristic information and input information of a user;
specifically, after the user registers, the feature information of the user can be obtained, the user feature information includes basic feature information of the user, related work information, input data of the user personalized recommendation module and the like, then the user interacts with the user through a top-level chat system data interface to obtain input information of the user, and the input information refers to information such as related requirements needed to be known by the user.
Step S2: retrieving relevant data in a data warehouse through a recommendation system according to the input information, screening the retrieved data by combining the characteristic information, and recommending the data to the user;
specifically, input information of a user is transmitted to a chat system and a recommendation system; the chat system mainly generates corresponding reply terms through a question-answering system in natural language processing, meanwhile, a recommendation system can search relevant information in sentences in a data warehouse, search relevant data and information, and recommend the most suitable information to a user (if the information is recommended, if the information is not recommended).
As shown in fig. 2, step S2 specifically includes the following contents:
step S21: extracting key words in the input information, and retrieving in the data warehouse according to the key words;
step S22: if the relevant data is searched out, recalling a certain amount of the data; if the relevant data is not searched out, the search result is fed back to the chat system;
step S23: and filtering and sorting the recalled data by combining the characteristic information, and recommending the data to the user according to a sorting result.
Specifically, firstly, the keywords in the conversation are extracted to carry out corresponding search in a plurality of bins, if files meeting the keyword search exist, a certain number of files are recalled, and then rough/fine/re-ranking operation is carried out on the files by combining with the characteristic information of the user, so that one or more files most suitable for the user are obtained and recommended to the user. Finally, the information is fed back to the user through the interactive window in a mode of replying dialect and related data, so that the related problems of the user are automatically and pertinently solved.
As shown in fig. 3, step S23 includes the following steps:
step S231: encoding and fusing the characteristic information and the input information;
step S232: sorting the data according to the matching degree of the recalled data and the fused feature codes;
step S233: and selecting a certain amount of the data according to the sorting sequence, recommending the data to the user, and feeding back the data names to the chat system.
Specifically, the method comprises the steps of acquiring feature data and input data of a user, encoding and fusing the two information, sorting files according to the matching degree of the files and the fused feature codes, selecting the files with the top sorting for recommendation, transmitting file names to a chat system, and sending the files to the user by the recommendation system.
Step S3: and feeding back the retrieval result and the screening result to a chat system, and sending a corresponding reply term to the user through the chat system according to the fed-back information.
Referring to fig. 4, step S3 includes the following:
step S31: classifying the input information in a text classification mode, and selecting different predefined answer operation frameworks according to different classes;
step S32: and outputting a corresponding reply term according to the reply dialogue framework and the information fed back by the recommendation system.
Specifically, a text classification form (for example, a TextCNN model) is adopted to classify the intention of the client, different predefined answer-to-speech frames are selected according to different categories, and feedback information of a recommendation system end is combined to form a suitable output statement, if a matching output file is found at the recommendation system end, the name of the file is extracted, and a corresponding speech is output for the user, such as: recommending < filename > data for you to answer the question, and simultaneously sending the file to the user by a recommendation system; if no result is returned from the recommending system, the user can select a word, and if the problem can be solved, the user can be recommended to the staff who can solve the problem.
Example two:
in combination with the intelligent chat recommendation method based on enterprise warehouse disclosed in the first embodiment, the present embodiment discloses a specific implementation example of an intelligent chat recommendation system (hereinafter referred to as "system") based on enterprise warehouse.
The intelligent chat recommendation system mainly comprises a chat system and a recommendation system, and is mainly used for acquiring user requirements through the chat system and generating corresponding reply dialogues; the recommendation system is mainly used for recommending required data and information for the user based on the acquired requirements and in combination with the characteristics of the user.
Referring to fig. 5, the system includes:
the information acquisition unit 1: acquiring characteristic information and input information of a user;
the data recommending unit 2: retrieving relevant data in a data warehouse through a recommendation system according to the input information, screening the retrieved data by combining the characteristic information, and recommending the data to the user;
the automatic reply unit 3: and feeding back the retrieval result and the screening result to a chat system, and sending a corresponding reply term to the user through the chat system according to the fed-back information.
Specifically, the material recommending unit 2 includes:
the keyword search module 21: extracting key words in the input information, and retrieving in the data warehouse according to the key words;
the data recall module 22: if the relevant data is searched out, recalling a certain amount of the data; if the relevant data is not searched out, the search result is fed back to the chat system;
the data screening module 23: and filtering and sorting the recalled data by combining the characteristic information, and recommending the data to the user according to a sorting result.
Specifically, the material screening module 23 includes:
the encoding fusion module 231: encoding and fusing the characteristic information and the input information;
the data sorting module 232: sorting the data according to the matching degree of the recalled data and the fused feature codes;
the feedback module 233: and selecting a certain amount of the data according to the sorting sequence, recommending the data to the user, and feeding back the data names to the chat system.
Specifically, the automatic reply unit 3 includes:
the information classification module 31: classifying the input information in a text classification mode, and selecting different predefined answer operation frameworks according to different classes;
the dialoging reply module 32: and outputting a corresponding reply term according to the reply dialogue framework and the information fed back by the recommendation system.
Please refer to the description of the first embodiment, which will not be repeated herein, in this embodiment, a system for intelligent chat recommendation based on enterprise warehouse and a technical solution of the same parts in a method for intelligent chat recommendation based on enterprise warehouse disclosed in the first embodiment are disclosed.
The following describes, with reference to fig. 6, a specific implementation of the intelligent chat recommendation system based on enterprise warehouse according to the present invention in further detail.
When the user uses the system, the user needs to register first, and relevant basic characteristic information (such as the gender, the age, the region and the like of the user) of the user can be obtained through registration, so that the input data of the user personalized recommendation module can be obtained. Then, interacting with the user through a top-level chatting system data interface to acquire input information of the user, and transmitting the input data of the user to a chatting system module and a recommending system module by the system; the chat system module mainly generates corresponding reply terms through a question-answering system in natural language processing, meanwhile, the recommendation system module can retrieve relevant information in sentences (if the relevant information is recommended, if the relevant information is not recommended), relevant data and information are retrieved in a data warehouse, and the most suitable information is recommended to a user.
As shown in fig. 6, the basic characteristic information (sex, age, etc.) and the related work information (company, position, etc.) of the user are acquired before the user uses the system for searching and recommending the related useful information according to the characteristics of the user; the user input data is related demands (for example, ask about how products of the company. The recommendation system searches whether the data warehouse has data or data which can answer the user question through the input data of the user, and simultaneously filters and sorts the data by combining the characteristics of the user to find the data which is most suitable for the characteristics of the user so as to solve the problem of the user really needing to be solved with the maximum probability; the process is mainly divided into a recalling process of relevant data and data based on user input data, and the recalling process can recall relevant data (such as PDF documents, subject cards and the like) with larger magnitude, and then coarse/fine/re-ranking operations are carried out on the data by combining with the characteristic information of the user, so that one or more data which are finally most suitable for the user are obtained and recommended to the user. Finally, the information is fed back to the user through the interactive window in a mode of replying dialogs and related data. Finally, the related problems of the user are solved automatically and pertinently.
The chat system mainly adopts a mode matching and slot filling mode, mainly judges which type an input question belongs to, mainly adopts a text classification mode (adopting a TextCNN model) to classify the intention of a client, selects different predefined answer-to-speech frames according to different categories, and combines feedback information of a recommendation system end to combine into a proper output statement; if no result is returned from the recommender, then a dialog may be selected (the problem may be solved in connection). The recommendation system mainly works on the principle that firstly, corresponding search is carried out in a plurality of bins by extracting keywords in a conversation, if files meeting keyword retrieval exist, a certain number of the files are recalled, then, the two kinds of information are coded and fused by acquiring characteristic data and input data of a user, the files are sorted according to the matching degree of the files and the fused characteristic codes, finally, a plurality of files which are sorted most in front are selected for recommendation, file names are transmitted to a chat system, and meanwhile, the recommendation system sends the files to the user.
Example three:
referring to FIG. 7, the embodiment discloses an embodiment of a computer device. The computer device may comprise a processor 81 and a memory 82 in which computer program instructions are stored.
Specifically, the processor 81 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory 82 may be used to store or cache various data files for processing and/or communication use, as well as possible computer program instructions executed by the processor 81.
The processor 81 reads and executes the computer program instructions stored in the memory 82 to implement any one of the intelligent chat recommendation methods in the above embodiments.
In some of these embodiments, the computer device may also include a communication interface 83 and a bus 80. As shown in fig. 7, the processor 81, the memory 82, and the communication interface 83 are connected via the bus 80 to complete communication therebetween.
The communication interface 83 is used for implementing communication between modules, devices, units and/or equipment in the embodiment of the present application. The communication port 83 may also be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.
In addition, in combination with the intelligent chat recommendation method in the foregoing embodiments, the embodiments of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the intelligent chat recommendation methods in the above embodiments.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
In summary, the beneficial effects of the invention are that the invention can efficiently and accurately provide the information needed by the user by constructing the intelligent chat system and the intelligent recommendation system by using the relevant data in the company warehouse, including the data of the staff, the data of the project, the data of the product, the data of the system architecture, and the like. An intelligent office tool can be formed inside a company, so that the working efficiency of staff is improved to a great extent, and the manpower of related departments is saved; outside the company, the problem that the customer knows complicated manual processes and flows in the process of the company product can be well solved, the related labor cost is saved to a certain extent, and the efficiency is improved.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An intelligent chat recommendation method based on enterprise warehouse is characterized by comprising the following steps:
an information acquisition step: acquiring characteristic information and input information of a user;
a data recommendation step: retrieving relevant data in a data warehouse through a recommendation system according to the input information, screening the retrieved data by combining the characteristic information, and recommending the data to the user;
and (3) automatic reply step: and feeding back the retrieval result and the screening result to a chat system, and sending a corresponding reply term to the user through the chat system according to the fed-back information.
2. The intelligent chat recommendation method according to claim 1, wherein the material recommendation step comprises:
and keyword retrieval: extracting key words in the input information, and retrieving in the data warehouse according to the key words;
data recall step: if the relevant data is searched out, recalling a certain amount of the data; if the relevant data is not searched out, the search result is fed back to the chat system;
a data screening step: and filtering and sorting the recalled data by combining the characteristic information, and recommending the data to the user according to a sorting result.
3. The intelligent chat recommendation method according to claim 2, wherein the data filtering step comprises:
and (3) encoding and fusing: encoding and fusing the characteristic information and the input information;
a data sorting step: sorting the data according to the matching degree of the recalled data and the fused feature codes;
a feedback step: and selecting a certain amount of the data according to the sorting sequence, recommending the data to the user, and feeding back the data names to the chat system.
4. The intelligent chat recommendation method in accordance with claim 3, wherein the automatically replying step comprises:
information classification step: classifying the input information in a text classification mode, and selecting different predefined answer operation frameworks according to different classes;
a speaking operation recovery step: and outputting a corresponding reply term according to the reply dialogue framework and the information fed back by the recommendation system.
5. An intelligent chat recommendation system based on enterprise warehouse, comprising:
an information acquisition unit: acquiring characteristic information and input information of a user;
the data recommending unit: retrieving relevant data in a data warehouse through a recommendation system according to the input information, screening the retrieved data by combining the characteristic information, and recommending the data to the user;
an automatic reply unit: and feeding back the retrieval result and the screening result to a chat system, and sending a corresponding reply term to the user through the chat system according to the fed-back information.
6. The intelligent chat recommendation system according to claim 5, wherein the profile recommendation unit comprises:
a keyword retrieval module: extracting key words in the input information, and retrieving in the data warehouse according to the key words;
the data recall module: if the relevant data is searched out, recalling a certain amount of the data; if the relevant data is not searched out, the search result is fed back to the chat system;
the data screening module: and filtering and sorting the recalled data by combining the characteristic information, and recommending the data to the user according to a sorting result.
7. The intelligent chat recommendation system according to claim 6, wherein the profile filtering module comprises:
and a coding fusion module: encoding and fusing the characteristic information and the input information;
a data sorting module: sorting the data according to the matching degree of the recalled data and the fused feature codes;
a feedback module: and selecting a certain amount of the data according to the sorting sequence, recommending the data to the user, and feeding back the data names to the chat system.
8. The intelligent chat recommendation system according to claim 7, wherein the automatic reply unit comprises:
an information classification module: classifying the input information in a text classification mode, and selecting different predefined answer operation frameworks according to different classes;
a dialoging reply module: and outputting a corresponding reply term according to the reply dialogue framework and the information fed back by the recommendation system.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the intelligent chat recommendation method of any of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the intelligent chat recommendation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763113.7A CN113343116A (en) | 2021-07-06 | 2021-07-06 | Intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763113.7A CN113343116A (en) | 2021-07-06 | 2021-07-06 | Intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113343116A true CN113343116A (en) | 2021-09-03 |
Family
ID=77482730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110763113.7A Pending CN113343116A (en) | 2021-07-06 | 2021-07-06 | Intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343116A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116340633A (en) * | 2023-03-30 | 2023-06-27 | 粤卫信息平台(广东)有限公司 | Information processing method and system for medical resource recommendation |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843962A (en) * | 2016-04-18 | 2016-08-10 | 百度在线网络技术（北京）有限公司 | Information processing and displaying methods, information processing and displaying devices as well as information processing and displaying system |
| CN105915439A (en) * | 2016-04-18 | 2016-08-31 | 百度在线网络技术（北京）有限公司 | Information pushing method, device and system |
| CN105989084A (en) * | 2015-02-11 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Question answering method and device |
| CN108733694A (en) * | 2017-04-18 | 2018-11-02 | 北京国双科技有限公司 | Method and apparatus are recommended in retrieval |
| CN109063204A (en) * | 2018-09-14 | 2018-12-21 | 郑州云海信息技术有限公司 | Log inquiring method, device, equipment and storage medium based on artificial intelligence |
| CN109817351A (en) * | 2019-01-31 | 2019-05-28 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, equipment and storage medium |
| CN109977215A (en) * | 2019-03-29 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | Sentence recommended method and device based on association point of interest |
| CN110245160A (en) * | 2019-06-03 | 2019-09-17 | 贝壳技术有限公司 | A kind of method and system of determining house decoration scheme |
| CN112182176A (en) * | 2020-09-25 | 2021-01-05 | 北京字节跳动网络技术有限公司 | Intelligent question answering method, device, equipment and readable storage medium |
| CN112818109A (en) * | 2021-02-25 | 2021-05-18 | 网易（杭州）网络有限公司 | Intelligent reply method, medium, device and computing equipment for mail |
-
2021
- 2021-07-06 CN CN202110763113.7A patent/CN113343116A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989084A (en) * | 2015-02-11 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Question answering method and device |
| CN105843962A (en) * | 2016-04-18 | 2016-08-10 | 百度在线网络技术（北京）有限公司 | Information processing and displaying methods, information processing and displaying devices as well as information processing and displaying system |
| CN105915439A (en) * | 2016-04-18 | 2016-08-31 | 百度在线网络技术（北京）有限公司 | Information pushing method, device and system |
| CN108733694A (en) * | 2017-04-18 | 2018-11-02 | 北京国双科技有限公司 | Method and apparatus are recommended in retrieval |
| CN109063204A (en) * | 2018-09-14 | 2018-12-21 | 郑州云海信息技术有限公司 | Log inquiring method, device, equipment and storage medium based on artificial intelligence |
| CN109817351A (en) * | 2019-01-31 | 2019-05-28 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, equipment and storage medium |
| CN109977215A (en) * | 2019-03-29 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | Sentence recommended method and device based on association point of interest |
| CN110245160A (en) * | 2019-06-03 | 2019-09-17 | 贝壳技术有限公司 | A kind of method and system of determining house decoration scheme |
| CN112182176A (en) * | 2020-09-25 | 2021-01-05 | 北京字节跳动网络技术有限公司 | Intelligent question answering method, device, equipment and readable storage medium |
| CN112818109A (en) * | 2021-02-25 | 2021-05-18 | 网易（杭州）网络有限公司 | Intelligent reply method, medium, device and computing equipment for mail |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116340633A (en) * | 2023-03-30 | 2023-06-27 | 粤卫信息平台(广东)有限公司 | Information processing method and system for medical resource recommendation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017097231A1 (en) | Topic processing method and device | |
| KR20200067180A (en) | Methods and systems for semantic search in large databases | |
| CN110909160A (en) | Regular expression generation method, server and computer readable storage medium | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| US20190179965A1 (en) | Method and apparatus for generating information | |
| CN106960030A (en) | Pushed information method and device based on artificial intelligence | |
| CN102999625A (en) | Method for realizing semantic extension on retrieval request | |
| CN108875065B (en) | Indonesia news webpage recommendation method based on content | |
| CN110210038B (en) | Core entity determining method, system, server and computer readable medium thereof | |
| CN105069112A (en) | Industry vertical search engine system | |
| CN103226601B (en) | A kind of method and apparatus of picture searching | |
| JP2005250980A (en) | Document retrieval system, retrieval condition input device, retrieval execution device, document retrieval method and document retrieval program | |
| CN111325033B (en) | Entity identification method, entity identification device, electronic equipment and computer readable storage medium | |
| CN109948154A (en) | A kind of personage's acquisition and relationship recommender system and method based on name | |
| US10114891B2 (en) | Method and system of audio retrieval and source separation | |
| CN111680152A (en) | Method and device for extracting abstract of target text, electronic equipment and storage medium | |
| CN109657043B (en) | Method, device and equipment for automatically generating article and storage medium | |
| CN113343116A (en) | Intelligent chat recommendation method, system, equipment and storage medium based on enterprise warehouse | |
| CN113886683A (en) | Label cluster construction method and system, storage medium and electronic equipment | |
| CN111625619B (en) | Query omission method, device, computer readable medium and electronic equipment | |
| CN111160007B (en) | Search method and device based on BERT language model, computer equipment and storage medium | |
| Viveros-Jiménez et al. | Improving the boilerpipe algorithm for boilerplate removal in news articles using html tree structure | |
| CN109918661B (en) | Synonym acquisition method and device | |
| KR20180059112A (en) | Apparatus for classifying contents and method for using the same | |
| CN116361428A (en) | Question-answer recall method, device 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 |