CN111160699A - Expert recommendation method and system - Google Patents
Expert recommendation method and system Download PDFInfo
- Publication number
- CN111160699A CN111160699A CN201911175078.6A CN201911175078A CN111160699A CN 111160699 A CN111160699 A CN 111160699A CN 201911175078 A CN201911175078 A CN 201911175078A CN 111160699 A CN111160699 A CN 111160699A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- expert
- keyword
- sequence
- existing
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The embodiment of the invention provides an expert recommendation method and system, wherein the method comprises the following steps: acquiring a keyword sequence according to the basic keywords; inputting the keyword sequence into a plurality of existing expert recommendation systems to obtain a recommendation result set; for any expert in any recommendation result sequence, acquiring the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence; and acquiring an expert recommendation result according to the recommendation score of each expert. The expert recommendation method and the expert recommendation system provided by the embodiment of the invention can present a more comprehensive and standard and more uniform recommendation result sequence to a user on the basis of a plurality of existing expert recommendation systems on the premise of not depending on a local database, thereby effectively reducing the project management difficulty of a scientific research project review manager and improving the management efficiency.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an expert recommendation method and an expert recommendation system.
Background
The evaluation efficiency and quality of scientific research projects have a significant influence on the overall scientific research development of the country. With the popularization of information-based system construction and use in recent years, network review of scientific research projects has gradually become mainstream. The network review of scientific research projects relates to the whole life cycle of project establishment, application, organization, demonstration, evaluation, acceptance and rewarding to filing, and the aim is to replace manpower by using an informatization system, thereby playing the roles of reducing the review cost and improving the review efficiency and quality.
Generally, in a complete scientific research project network review system, the implementation of an expert recommendation system is the core and difficulty of the review effect. However, in the existing expert recommendation systems in the market, such as expert search, Acemap and the like, there are cases where expert data are inconsistent between systems, such as different data languages, the same expert data is not recorded in all systems, and the adopted recommendation algorithm has no unified standard, so that the recommender candidate sequences given by the same keyword by different expert recommendation systems are greatly different.
When actual review expert recommendation is performed on scientific research projects, review managers often need to refer to results given by a plurality of expert recommendation systems. However, only under the subjective consciousness of the manager, a group of experts meeting the evaluation standard is screened from the candidate sequences of the recommenders given by the expert recommendation systems, and the final screening result is easily unreliable due to human subjective factors, so that the evaluation efficiency and the evaluation accuracy of scientific research projects are affected.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide an expert recommendation method and system.
In a first aspect, an embodiment of the present invention provides an expert recommendation method, including:
acquiring a keyword sequence according to basic keywords, wherein the keyword sequence comprises a plurality of keywords;
inputting the keyword sequences into a plurality of existing expert recommendation systems to obtain a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts for any recommendation result sequence, and any recommendation result sequence is obtained by searching any existing expert recommendation system according to any keyword in the keyword sequences;
for any expert in any recommendation result sequence, acquiring a recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and acquiring an expert recommendation result according to the recommendation score of each expert.
Preferably, the obtaining a keyword sequence according to the basic keyword specifically includes:
if the basic keyword is Chinese and the basic keyword is not an expert name, translating the basic keyword into English to obtain a plurality of English keywords;
if the basic keyword is Chinese and the basic keyword is an expert name, translating the basic keyword into English according to a preset format, and acquiring a plurality of English keywords;
and taking the basic keywords and the English keywords as the keyword sequence.
Preferably, the obtaining a keyword sequence according to the basic keyword further includes:
if the basic keyword is English and the basic keyword is not an expert name, translating the basic keyword into a plurality of Chinese keywords, acquiring a plurality of Chinese keywords, and taking the Chinese keywords and the basic keyword as the keyword sequence;
and if the basic keyword is English and the basic keyword is an expert name, taking the basic keyword as the keyword sequence.
Preferably, the method for obtaining the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence further comprises:
judging whether any one of the existing expert recommendation systems contains ranking weight information or not, and if so, classifying any one of the existing expert recommendation systems into a first type;
otherwise, judging whether any one of the existing expert recommendation systems contains h factor information, and if so, classifying any one of the existing expert recommendation systems into a second class;
otherwise, judging whether any one of the existing expert recommendation systems contains thesis information, and if so, classifying any one of the existing expert recommendation systems into a third class;
otherwise, classifying any one of the existing expert recommendation systems into a fourth class.
Preferably, the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically includes:
if any one of the existing expert recommendation systems belongs to the first category, obtaining the ranking weight of any one of the experts;
and acquiring the recommendation score of any expert according to the ratio of the ranking weight of any expert to the maximum ranking weight of all experts in any recommendation structure sequence.
Preferably, the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically includes:
if any one of the existing expert recommendation systems belongs to the second category, acquiring an h factor value of any one of the experts;
and acquiring the recommendation score of any expert according to the ratio of the h factor value of any expert to the maximum h factor value of all experts in any recommendation structure sequence.
Preferably, the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically includes:
if any one of the existing expert recommendation systems belongs to the third category, acquiring the quantity of papers, patents and participating projects published by any one of the experts;
and acquiring the recommendation score of any expert according to the number of papers, patents and participating items published by any expert and the maximum number of papers, patents and participating items published by all experts in any recommendation sequence.
In a second aspect, an embodiment of the present invention provides an expert recommendation system, including:
the keyword module is used for acquiring a keyword sequence according to basic keywords, and the keyword sequence comprises a plurality of keywords;
the search module is used for inputting the keyword sequences into a plurality of existing expert recommendation systems to obtain a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts, and any recommendation result sequence is obtained by searching any existing expert recommendation system according to any keyword in the keyword sequences;
the scoring module is used for acquiring the recommendation score of any expert in any recommendation result sequence according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and the recommendation module is used for acquiring the expert recommendation result according to the recommendation score of each expert.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the expert recommendation method provided in the first aspect of the present invention.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of an expert recommendation method provided in the first aspect of the present invention.
The expert recommendation method and the expert recommendation system provided by the embodiment of the invention can present a more comprehensive and standard and more uniform recommendation result sequence to a user on the basis of a plurality of existing expert recommendation systems on the premise of not depending on a local database, thereby effectively reducing the project management difficulty of a scientific research project review manager and improving the management efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of an expert recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an expert recommendation system according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of an expert recommendation method according to an embodiment of the present invention, and as shown in fig. 1, an expert recommendation method according to an embodiment of the present invention includes:
s1, acquiring a keyword sequence according to the basic keywords, wherein the keyword sequence comprises a plurality of keywords;
s2, inputting the keyword sequences into a plurality of existing expert recommendation systems, obtaining a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts, and any recommendation result sequence is obtained by any existing expert recommendation system through searching according to any keyword in the keyword sequences;
s3, for any expert in any recommendation result sequence, obtaining the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and S4, acquiring expert recommendation results according to the recommendation scores of each expert.
Firstly, basic keywords which are also search keywords input into the existing expert recommendation system by a user are obtained, operations such as deformation and the like are carried out on the basic keywords according to the basic keywords, a plurality of expanded keywords are obtained by expanding the basic keywords, and the expanded keywords and the basic keywords form a keyword sequence.
And then inputting each keyword in the keyword sequence into the existing expert recommendation system, wherein the existing expert recommendation system is the existing expert recommendation system at present.
In addition, for any keyword, the keyword is input into any existing expert recommendation system, and the existing expert recommendation system can search for a plurality of recommended experts, namely obtain a recommendation result sequence, wherein the recommended experts are arranged according to the sequence of recommendation degrees from high to low or from low to high.
Then, according to the same method, each existing expert recommendation system searches each keyword, so that a plurality of recommendation result sequences are obtained, and all recommendation result sequences form a recommendation result set.
Because the types of the existing expert recommendation systems are different, for example, some existing expert recommendation systems attach importance to the number of papers published by experts, and some existing expert recommendation systems attach importance to the influence factors of the published papers, the same keyword can be considered by one existing expert recommendation system, and the expert cannot be considered comprehensively. And the standard of each existing expert recommendation system is not uniform, so that the user can difficultly decide.
According to the recommendation score of each expert in each recommendation result sequence, comprehensive consideration is carried out on each expert to obtain the final expert recommendation result. Here, for any one expert, because the expert order in the recommendation result sequence is arranged from small to large or from large to small, the recommendation score of the expert is determined according to the type of the corresponding existing expert recommendation result and the recommendation degree of the expert in the recommendation result sequence.
It should be noted that, in the embodiment of the present invention, the recommendation degrees of each expert in the recommendation result sequence are different, the recommendation degree of the expert ranked at the top is the highest, the recommendation degree of the expert ranked at the back is lower, the recommendation result sequence is ranked according to the recommendation degree of each expert from large to small, and the recommendation degree of the expert can be obtained according to the position of the expert in the recommendation result sequence. For example, the recommended degree of the expert ranked at the forefront is 100%, the recommended degree of the expert ranked in the middle is 50%, and the recommended degree of the expert ranked at the last is 0.
In the embodiment of the invention, the recommendation score can be obtained by multiplying the recommendation degree by 100, so that the recommendation score can be set between 0 and 100, and a user can intuitively know the condition of each expert through the recommendation score, thereby being more convenient for the user to make a selection.
The expert recommendation method provided by the embodiment of the invention can present a more comprehensive and standard and more uniform recommendation result sequence to a user on the basis of a plurality of existing expert recommendation systems on the premise of not depending on a local database, thereby effectively reducing the project management difficulty of scientific research project review managers and improving the management efficiency.
On the basis of the foregoing embodiment, preferably, the obtaining a keyword sequence according to a basic keyword specifically includes:
if the basic keyword is Chinese and the basic keyword is not an expert name, translating the basic keyword into English to obtain a plurality of English keywords;
if the basic keyword is Chinese and the basic keyword is an expert name, translating the basic keyword into English according to a preset format, and acquiring a plurality of English keywords;
and taking the basic keywords and the English keywords as the keyword sequence.
Specifically, if the basic keyword input by the user is chinese and the basic keyword is not the name of an expert, in the embodiment of the present invention, the basic keyword is translated into at most three related english keywords, and all the english keywords and the basic keyword are used as a keyword sequence.
If the basic keyword input by the user is Chinese and the basic keyword is the name of an expert, in the embodiment of the invention, the name of the Chinese expert is translated according to a plurality of common English formats, and the Chinese name and the translated Chinese expert name are added into the keyword sequence to obtain a plurality of possible English names, namely all Chinese keywords and the basic keyword are used as the keyword sequence.
On the basis of the foregoing embodiment, preferably, the obtaining a keyword sequence according to a basic keyword further includes:
if the basic keyword is English and the basic keyword is not an expert name, translating the basic keyword into a plurality of Chinese keywords, acquiring a plurality of Chinese keywords, and taking the Chinese keywords and the basic keyword as the keyword sequence;
and if the basic keyword is English and the basic keyword is an expert name, taking the basic keyword as the keyword sequence.
Further, if the basic keyword is english and the basic keyword is not an expert name, the basic keyword is translated into a plurality of chinese keywords, and the translated chinese keywords and the basic keyword are used as a keyword sequence. If the basic keyword is English and the basic keyword is an expert name, the basic keyword is directly used as a keyword sequence without expanding the basic keyword.
In the embodiment of the invention, the basic keywords are directly expanded to obtain other expression modes of a plurality of basic keywords, and each keyword is searched, so that the accuracy of the search result is improved, and the possibility of missing detection is reduced.
On the basis of the above embodiment, preferably, the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence further includes:
judging whether any one of the existing expert recommendation systems contains ranking weight information or not, and if so, classifying any one of the existing expert recommendation systems into a first type;
otherwise, judging whether any one of the existing expert recommendation systems contains h factor information, and if so, classifying any one of the existing expert recommendation systems into a second class;
otherwise, judging whether any one of the existing expert recommendation systems contains thesis information, and if so, classifying any one of the existing expert recommendation systems into a third class;
otherwise, classifying any one of the existing expert recommendation systems into a fourth class.
Before calculating a recommendation score for an expert recommended by any one existing expert recommendation system, the existing expert recommendation system needs to be classified, in the embodiment of the present invention, the existing expert recommendation system is classified into a first class, a second class, a third class and a fourth class, and a specific classification method is as follows:
firstly, whether the existing expert recommendation system contains offline-calculated ranking weight information or not is judged, and if the existing expert recommendation system contains the offline-calculated ranking weight information, the existing expert recommendation system is classified into a first class.
And if the existing expert recommendation system does not contain offline calculated ranking weight information, judging whether the existing expert recommendation system contains h factor information, and if so, dividing the existing expert recommendation system into a second class.
If the existing expert recommendation system does not contain h factor information, judging whether the existing expert recommendation system contains thesis information, if so, dividing the existing expert recommendation system into a third class, otherwise, dividing the existing expert recommendation system into a fourth class.
It should be noted that the offline-computed ranking weight refers to a recommendation value comprehensively computed by the existing expert recommendation system according to the existing expert data (e.g., h factor, paper quantity, patent quantity) of the existing expert recommendation system before the existing expert recommendation system returns a recommendation result sequence, and reflects the importance of an expert in the whole recommendation result set returned by the existing expert recommendation system.
On the basis of the foregoing embodiment, preferably, the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically includes the following four calculation methods:
firstly, if the existing expert recommendation system belongs to the first category, that is, the existing expert recommendation system recommends experts according to offline ranking weight information, for any expert in a recommendation result sequence in the existing expert recommendation system, the ranking weight of the expert is obtained and is marked as wkAt this time, the maximum weight among all experts in the recommendation sequence is wmaxAt this time, the recommendation degree of the expert is the ratio of the ranking weight of the expert to the maximum ranking weight, that is
Then, according to the recommendation degree of the expert, calculating the recommendation score of the expert, wherein a specific calculation formula is as follows:
where r represents the recommendation score of the expert.
Secondly, if any one of the existing expert recommendation systems belongs to the second category, acquiring an h factor value of any one of the experts;
and acquiring the recommendation score of any expert according to the ratio of the h factor value of any expert to the maximum h factor value of all experts in any recommendation structure sequence.
Specifically, if the existing expert recommendation system belongs to the second category, that is, the existing expert recommendation system does not have available ranking weight information, but the recommendation structure sequence thereof contains h factor information, for any expert recommending the result sequence in the existing expert recommendation system, the h factor of the expert is obtained and recorded as hkAt this time, the maximum h factor among all experts in the recommendation sequence is hmaxCalculating the recommendation degree of the expert according to the h factor and the maximum h factor of the expert, wherein the recommendation degree of the expert is
Then, according to the recommendation degree of the expert, calculating the recommendation score of the expert, wherein a specific calculation formula is as follows:
thirdly, if any one of the existing expert recommendation systems belongs to the third category, acquiring the quantity of papers, the quantity of patents and the quantity of participating projects published by any one of the experts;
and acquiring the recommendation score of any expert according to the number of papers, patents and participating items published by any expert and the maximum number of papers, patents and participating items published by all experts in any recommendation sequence.
Specifically, if the existing expert recommendation system belongs to the third category, that is, the existing expert recommendation system does not belong to the first category or the second category, but the recommendation structure sequence thereof includes the papers published by the expertsThe quantity, optionally, the quantity of issued patents and the quantity of scientific research projects participated in, then for any expert in the recommendation result sequence in the existing expert recommendation system, the quantity of issued papers of the expert is obtained and is marked as paperkOptionally, the number of issued patents and the number of participating scientific research projects are obtained and recorded as patent respectivelyk、projectkAt this time, the maximum number of papers published in all experts in the recommendation sequence is recorded as papermaxOptionally, the maximum number of issued patents and the maximum number of participating scientific research projects are respectively denoted as patentmax、projectmaxCalculating the recommendation degree of the expert according to the number of published papers, published patents and the number of the excessive scientific research projects of the expert, as well as the maximum number of papers, the maximum number of published patents and the maximum number of the excessive scientific research projects, wherein the recommendation degree of the expert is
Then, according to the recommendation degree of the expert, obtaining the recommendation score of the expert, wherein a specific calculation formula is as follows:
α, β and gamma are weight parameters which can be designed according to the actual recommended situation, but it should be satisfied that α > 0, β > 0, gamma > 0, and α + β + gamma is 1.
Fourth, if the existing expert recommendation system belongs to the fourth category, the recommendation score of the expert is 0.
The recommendation scores for all experts will be between 0 and 100 points.
And (3) integrating the results of the existing expert recommendation systems, putting each expert into the final recommendation result sequence, and finally sorting the final recommendation result sequence in a descending order according to the recommendation scores of the recommended experts. And the final recommendation result sequence is the expert recommendation result.
Fig. 2 is a schematic structural diagram of an expert recommendation system according to an embodiment of the present invention, and as shown in fig. 2, the expert recommendation system includes: a keyword module 201, a search module 202, a scoring module 203, and a recommendation module 204, wherein:
the keyword module 201 is configured to obtain a keyword sequence according to a basic keyword, where the keyword sequence includes a plurality of keywords;
the search module 202 is configured to input the keyword sequences into a plurality of existing expert recommendation systems, and acquire a recommendation result set, where the recommendation result set includes a plurality of recommendation result sequences, and for any recommendation result sequence, the any recommendation result sequence includes a plurality of experts, and the any recommendation result sequence is obtained by searching, by any existing expert recommendation system, according to any keyword in the keyword sequences;
the scoring module 203 is configured to obtain, for any expert in any recommendation result sequence, a recommendation score of the any expert according to the type of the any existing expert recommendation system and the recommendation degree of the any expert in any recommendation structure sequence;
the recommendation module 204 is configured to obtain an expert recommendation result according to the recommendation score of each expert.
Specifically, the keyword module 201 expands the keywords according to the basic keywords input by the user to obtain a plurality of related keywords, and uses the related keywords and the basic keywords as a keyword sequence. The search module 202 searches each keyword in the keyword sequence using each existing expert recommendation system to obtain a plurality of sets of recommendation result sequences. The scoring module 203 scores the recommendations for each expert in all of the recommendation sequences. The recommendation module 204 obtains a final expert recommendation result according to the recommendation score of each expert.
The system embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the bus 304. The communication interface 302 may be used for information transfer of an electronic device. Processor 301 may call logic instructions in memory 303 to perform a method comprising:
acquiring a keyword sequence according to basic keywords, wherein the keyword sequence comprises a plurality of keywords;
inputting the keyword sequences into a plurality of existing expert recommendation systems to obtain a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts for any recommendation result sequence, and any recommendation result sequence is obtained by searching any existing expert recommendation system according to any keyword in the keyword sequences;
for any expert in any recommendation result sequence, acquiring a recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and acquiring an expert recommendation result according to the recommendation score of each expert.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-described method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method provided by the foregoing embodiments, for example, including:
acquiring a keyword sequence according to basic keywords, wherein the keyword sequence comprises a plurality of keywords;
inputting the keyword sequences into a plurality of existing expert recommendation systems to obtain a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts for any recommendation result sequence, and any recommendation result sequence is obtained by searching any existing expert recommendation system according to any keyword in the keyword sequences;
for any expert in any recommendation result sequence, acquiring a recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and acquiring an expert recommendation result according to the recommendation score of each expert.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An expert recommendation method, comprising:
acquiring a keyword sequence according to basic keywords, wherein the keyword sequence comprises a plurality of keywords;
inputting the keyword sequences into a plurality of existing expert recommendation systems to obtain a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts for any recommendation result sequence, and any recommendation result sequence is obtained by searching any existing expert recommendation system according to any keyword in the keyword sequences;
for any expert in any recommendation result sequence, acquiring a recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and acquiring an expert recommendation result according to the recommendation score of each expert.
2. The expert recommendation method according to claim 1, wherein the obtaining of the keyword sequence based on the basic keyword specifically comprises:
if the basic keyword is Chinese and the basic keyword is not an expert name, translating the basic keyword into English to obtain a plurality of English keywords;
if the basic keyword is Chinese and the basic keyword is an expert name, translating the basic keyword into English according to a preset format, and acquiring a plurality of English keywords;
and taking the basic keywords and the English keywords as the keyword sequence.
3. The expert recommendation method of claim 1 wherein the obtaining a sequence of keywords from the base keywords further comprises:
if the basic keyword is English and the basic keyword is not an expert name, translating the basic keyword into a plurality of Chinese keywords, acquiring a plurality of Chinese keywords, and taking the Chinese keywords and the basic keyword as the keyword sequence;
and if the basic keyword is English and the basic keyword is an expert name, taking the basic keyword as the keyword sequence.
4. The expert recommendation method according to claim 1, wherein the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence further comprises:
judging whether any one of the existing expert recommendation systems contains ranking weight information or not, and if so, classifying any one of the existing expert recommendation systems into a first type;
otherwise, judging whether any one of the existing expert recommendation systems contains h factor information, and if so, classifying any one of the existing expert recommendation systems into a second class;
otherwise, judging whether any one of the existing expert recommendation systems contains thesis information, and if so, classifying any one of the existing expert recommendation systems into a third class;
otherwise, classifying any one of the existing expert recommendation systems into a fourth class.
5. The expert recommendation method according to claim 4, wherein the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically comprises:
if any one of the existing expert recommendation systems belongs to the first category, obtaining the ranking weight of any one of the experts;
and acquiring the recommendation score of any expert according to the ratio of the ranking weight of any expert to the maximum ranking weight of all experts in any recommendation structure sequence.
6. The expert recommendation method according to claim 4, wherein the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically comprises:
if any one of the existing expert recommendation systems belongs to the second category, acquiring an h factor value of any one of the experts;
and acquiring the recommendation score of any expert according to the ratio of the h factor value of any expert to the maximum h factor value of all experts in any recommendation structure sequence.
7. The expert recommendation method according to claim 4, wherein the obtaining of the recommendation score of any expert according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence specifically comprises:
if any one of the existing expert recommendation systems belongs to the third category, acquiring the quantity of papers, patents and participating projects published by any one of the experts;
and acquiring the recommendation score of any expert according to the number of papers, patents and participating items published by any expert and the maximum number of papers, patents and participating items published by all experts in any recommendation sequence.
8. An expert recommendation system, comprising:
the keyword module is used for acquiring a keyword sequence according to basic keywords, and the keyword sequence comprises a plurality of keywords;
the search module is used for inputting the keyword sequences into a plurality of existing expert recommendation systems to obtain a recommendation result set, wherein the recommendation result set comprises a plurality of recommendation result sequences, any recommendation result sequence comprises a plurality of experts, and any recommendation result sequence is obtained by searching any existing expert recommendation system according to any keyword in the keyword sequences;
the scoring module is used for acquiring the recommendation score of any expert in any recommendation result sequence according to the type of any existing expert recommendation system and the recommendation degree of any expert in any recommendation structure sequence;
and the recommendation module is used for acquiring the expert recommendation result according to the recommendation score of each expert.
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 when executing the program performs the steps of the expert recommendation method as claimed in any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the expert recommendation method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911175078.6A CN111160699A (en) | 2019-11-26 | 2019-11-26 | Expert recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911175078.6A CN111160699A (en) | 2019-11-26 | 2019-11-26 | Expert recommendation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111160699A true CN111160699A (en) | 2020-05-15 |
Family
ID=70556141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911175078.6A Pending CN111160699A (en) | 2019-11-26 | 2019-11-26 | Expert recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160699A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111859156A (en) * | 2020-08-04 | 2020-10-30 | 上海风秩科技有限公司 | Method and device for determining release crowd, readable storage medium and electronic equipment |
| CN113343666A (en) * | 2021-06-29 | 2021-09-03 | 深圳前海微众银行股份有限公司 | Method, device and equipment for determining confidence degree of score and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110184926A1 (en) * | 2010-01-26 | 2011-07-28 | National Taiwan University Of Science & Technology | Expert list recommendation methods and systems |
| CN102855241A (en) * | 2011-06-28 | 2013-01-02 | 上海迈辉信息技术有限公司 | Multi-index expert suggestion system and realization method thereof |
| US20130006998A1 (en) * | 2011-06-29 | 2013-01-03 | International Business Machines Corporation | Interestingness of data |
| CN103605665B (en) * | 2013-10-24 | 2017-01-11 | 杭州电子科技大学 | Keyword based evaluation expert intelligent search and recommendation method |
| CN104361102B (en) * | 2014-11-24 | 2018-05-11 | 清华大学 | A kind of expert recommendation method and system based on group matches |
-
2019
- 2019-11-26 CN CN201911175078.6A patent/CN111160699A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110184926A1 (en) * | 2010-01-26 | 2011-07-28 | National Taiwan University Of Science & Technology | Expert list recommendation methods and systems |
| CN102855241A (en) * | 2011-06-28 | 2013-01-02 | 上海迈辉信息技术有限公司 | Multi-index expert suggestion system and realization method thereof |
| US20130006998A1 (en) * | 2011-06-29 | 2013-01-03 | International Business Machines Corporation | Interestingness of data |
| CN103605665B (en) * | 2013-10-24 | 2017-01-11 | 杭州电子科技大学 | Keyword based evaluation expert intelligent search and recommendation method |
| CN104361102B (en) * | 2014-11-24 | 2018-05-11 | 清华大学 | A kind of expert recommendation method and system based on group matches |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111859156A (en) * | 2020-08-04 | 2020-10-30 | 上海风秩科技有限公司 | Method and device for determining release crowd, readable storage medium and electronic equipment |
| CN111859156B (en) * | 2020-08-04 | 2024-02-02 | 上海秒针网络科技有限公司 | Method and device for determining distribution crowd, readable storage medium and electronic equipment |
| CN113343666A (en) * | 2021-06-29 | 2021-09-03 | 深圳前海微众银行股份有限公司 | Method, device and equipment for determining confidence degree of score and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107436875B (en) | Text classification method and device | |
| US8280886B2 (en) | Determining candidate terms related to terms of a query | |
| US8332439B2 (en) | Automatically generating a hierarchy of terms | |
| US8543380B2 (en) | Determining a document specificity | |
| CN107180093B (en) | Information searching method and device and timeliness query word identification method and device | |
| CN112667794A (en) | Intelligent question-answer matching method and system based on twin network BERT model | |
| US8949227B2 (en) | System and method for matching entities and synonym group organizer used therein | |
| US20150019951A1 (en) | Method, apparatus, and computer storage medium for automatically adding tags to document | |
| CN109033101B (en) | Label recommendation method and device | |
| CN109299344A (en) | The generation method of order models, the sort method of search result, device and equipment | |
| WO2018157625A1 (en) | Reinforcement learning-based method for learning to rank and server | |
| US20140379719A1 (en) | System and method for tagging and searching documents | |
| WO2013163062A1 (en) | Recommending keywords | |
| WO2014206151A1 (en) | System and method for tagging and searching documents | |
| KR20190128246A (en) | Searching methods and apparatus and non-transitory computer-readable storage media | |
| CN112100396A (en) | Data processing method and device | |
| CN108133058B (en) | Video retrieval method | |
| CN115905489B (en) | Method for providing bidding information search service | |
| CN111061954B (en) | Search result sorting method and device and storage medium | |
| US9058328B2 (en) | Search device, search method, search program, and computer-readable memory medium for recording search program | |
| CN111160699A (en) | Expert recommendation method and system | |
| CN114254615A (en) | Volume assembling method and device, electronic equipment and storage medium | |
| CN112559895B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113190593A (en) | Search recommendation method based on digital human knowledge graph | |
| CN108170664B (en) | Key word expansion method and device based on key words |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200515 |