CN110413778A - Generation method, expert recommendation method and the electronic equipment of expert power - Google Patents
Generation method, expert recommendation method and the electronic equipment of expert power Download PDFInfo
- Publication number
- CN110413778A CN110413778A CN201910619736.XA CN201910619736A CN110413778A CN 110413778 A CN110413778 A CN 110413778A CN 201910619736 A CN201910619736 A CN 201910619736A CN 110413778 A CN110413778 A CN 110413778A
- Authority
- CN
- China
- Prior art keywords
- expert
- power
- recommended
- information
- expertise
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
-
- 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
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to data mining technology field more particularly to a kind of generation methods of expert power, expert recommendation method and electronic equipment.The generation method of the expert power includes: the network influence for obtaining expert, and the network influence includes negative effect power and positive influences power;Obtain the expertise of the expert;Expert power is generated according to the negative effect power, the positive influences power and the expertise.The embodiment collects expert info from multi-angle and generates expert power from multi-angle, and based on industry belonging to service content and specialist field, and expert power determines the expert recommended, thus the accuracy rate that the objectivity and expert when improving evaluation expert power are recommended.
Description
[technical field]
The present invention relates to data mining technology fields more particularly to a kind of generation method of expert power, expert to recommend
Method and electronic equipment.
[background technique]
Have in reality and various industries expert is supported to provide the IT system of service, user selects oneself in such IT system
Required expert.In the case that the increase of expert's quantity, expertise and experience become increasingly complex, how to be closed for lead referral
Suitable expert is the thing for having challenge.Change Management platform is that Change Management field realizes that customer demand and expert are matched
Place also faces for the challenge of the suitable expert of lead referral.
Currently, obtaining the influence power of expert generally according to Web content, recommend expert further according to the influence power of expert.Than
Such as, buyer evaluates seller after shopping in e-commerce website, recommends suitable seller according to the evaluation.For another example,
Expert power is obtained by the mechanism for integrating ranking, to recommend expert.
However, the relevant technologies have that objectivity is insufficient when obtaining expert power, thus cause to be recommended
Expert is not accurate enough, cannot meet the needs of users.
[summary of the invention]
The technical problem to be solved in the present invention is to provide a kind of generation method of expert power, expert recommendation method and electricity
Sub- equipment, solving the relevant technologies, there are the technical problems of objectivity deficiency when obtaining expert power.
The one aspect of the embodiment of the present invention provides a kind of generation method of expert power, which comprises
The network influence of expert is obtained, the network influence includes negative effect power and positive influences power;
Obtain the expertise of the expert;
Expert power is generated according to the negative effect power, the positive influences power and the expertise.
Optionally, the network influence for obtaining expert includes:
It is obtained and the associated Web content of the expert from internet;
The evaluation information of the expert is extracted from the Web content;
The evaluation information is analyzed, to obtain the negative information and positive information of the expert;
The negative information and the positive information are subjected to quantification treatment, with generate the expert negative effect power and
Positive influences power.
Optionally, described raw according to the negative effect power, the positive influences power and the expertise in execution
Before the step for expert power, the method also includes:
Confidence evaluation is carried out to the negative effect power and the positive influences power, with judge the negative effect power with
Whether the confidence evaluation result of the positive influences power meets preset condition, in the negative effect power and the positive influences
When the confidence evaluation result of power is all satisfied preset condition, just execute described according to the negative effect power, the positive influences
The step of power and the expertise generate expert power.
Optionally, the expertise for obtaining the expert includes:
The ability information of the expert is obtained from expert's logging platform, the ability information includes business experience and pipe
Reason experience;
The ability information of the expert is subjected to quantification treatment, to obtain the expertise of the expert.
Optionally, the method also includes:
Periodically update the network influence and the expertise;
Expert power is generated according to the updated network influence and the expertise.
The other side of the embodiment of the present invention provides a kind of expert recommendation method, which comprises
Determine industry belonging to service content and specialist field;
Expert to be recommended is determined according to the industry and the specialist field;
The expert power of the expert to be recommended is obtained according to the generation method of expert power as described above;
The expert recommended is determined from the expert to be recommended according to the expert power.
Optionally, the method also includes:
Obtain the regional information of the expert to be recommended;
The expert recommended is determined from the expert to be recommended according to the regional information and the expert power.
Optionally, the method also includes:
It is that the expert to be recommended labels according to the expert power of the expert to be recommended;
Region belonging to the corresponding expert of the label is highlighted on map, so that it is corresponding specially to analyze the label
The Regional Distribution situation of family.
Optionally, the expert to be recommended includes multiple, the method also includes:
Show multiple experts to be recommended and its corresponding expert power;
The select expert instruction for receiving user, to instruct the expert for determining and recommending according to the select expert.
The other side of the embodiment of the present invention, provides a kind of electronic equipment, comprising:
At least one processor;And the memory being connect at least one described processor communication;Wherein, the storage
Device is stored with the instruction that can be executed by least one described processor, and described instruction is executed by least one described processor, with
At least one described processor is set to be able to carry out the generation method and expert recommendation method of expert power as described above.
In embodiments of the present invention, pass through the network influence and expertise of acquisition expert, wherein network influence packet
Negative effect power and positive influences power are included, expert is generated according to the negative effect power, positive influences power and expertise of expert
Influence power.When carrying out expert's recommendation, its corresponding industry and specialist field are determined according to service content, thus according to described
Industry and specialist field determine expert to be recommended, and finally according to the influence power of expert, determination is pushed away from the expert to be recommended
The expert recommended.The embodiment collects expert info from multi-angle and generates expert power from multi-angle, and based on clothes
Industry and specialist field belonging to content of being engaged in and expert power determine the expert recommended, to improve evaluation expert's shadow
The accuracy rate that objectivity and expert when ringing power are recommended.
[Detailed description of the invention]
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element in attached drawing with same reference numbers label are expressed as similar element, remove
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is a kind of flow chart of the generation method of expert power provided in an embodiment of the present invention;
Fig. 2 is the network influence that expert is obtained in a kind of generation method of expert power provided in an embodiment of the present invention
Method flow chart;
Fig. 3 is a kind of flow chart of expert recommendation method provided in an embodiment of the present invention;
Fig. 4 is a kind of schematic diagram in showing interface expert info provided in an embodiment of the present invention;
Fig. 5 is a kind of schematic diagram in showing interface network influence provided in an embodiment of the present invention;
Fig. 6 is another schematic diagram in showing interface network influence provided in an embodiment of the present invention;
Fig. 7 is a kind of structural block diagram of the generating means of expert power provided in an embodiment of the present invention;
Fig. 8 is a kind of structural block diagram of expert's recommendation apparatus provided in an embodiment of the present invention;
Fig. 9 is the hardware structural diagram of a kind of electronic equipment provided in an embodiment of the present invention.
[specific embodiment]
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
It should be noted that each feature in the embodiment of the present invention can be combined with each other, in this hair if do not conflicted
Within bright protection scope.In addition, though having carried out the division of functional module in schematic device, show in flow charts
Logical order, but in some cases, it can be with the sequence in the module division being different from schematic device or flow chart
Execute shown or described step.
Referring to Fig. 1, Fig. 1 is a kind of flow chart of the generation method of expert power provided in an embodiment of the present invention, such as
Shown in Fig. 1, this method comprises:
Step S101, the network influence of expert is obtained, the network influence includes negative effect power and positive influences
Power.
The network influence refers to that the information of expert is appeared on network with diversified forms such as article, news in brief, models,
These contents are by readers ' reading, praise, criticism, to form network influence.The network influence includes negative effect power
With positive influences power.The negative effect power refers to effect brought by negative content relevant to the expert, for example criticizes
It comments.The positive influences power refers to effect brought by positive content relevant to the expert, for example praise etc..It is described
Expert refers to possessing the people of professional technique and knowledge in a certain field.It can be obtained in the present embodiment by following methods special
The network influence of family, referring to Fig. 2, step S101 includes:
Step S1011, it is obtained and the associated Web content of the expert from internet;
Step S1012, the evaluation information of the expert is extracted from the Web content;
Step S1013, the evaluation information is analyzed, to obtain the negative information and positive information of the expert;
Step S1014, the negative information and the positive information are subjected to quantification treatment, to generate the negative of the expert
Face influence power and positive influences power.
Wherein it is possible to based on internet from the model in news release, news in brief, forum, paper, patent, books, the note delivered
The information sources such as the website of volume obtain and the associated Web content of the expert.It is collected into and the associated Web content of the expert
Afterwards, the evaluation information to expert is isolated based on these information, wherein the process for extracting the evaluation information of expert that is to say text
The result of the process of classification, classification can also can also be arranged by system automatically by user's customized setting according to demand.For example,
It still " negates " that more complicated classification results can be evaluation expert to expert's " affirmative " that simple classification results, which can be,
" expression is clear ", " expression is unintelligible ", " attitude is good ", " attitude is bad " etc..More complicated classification results can be evaluation again
Expert's " profession ", " unprofessional " etc..The result of the classification is the evaluation information.
Wherein, the preset algorithm can be machine learning algorithm, such as support vector machines, Bayesian Classification Arithmetic, certainly
Plan tree, neural network etc..Include by the detailed process that preset algorithm obtains the evaluation information, for example, using there is supervision
Equal machine learning mode, first stage article/model etc. of selected a batch description expert are manually marked;Second stage makes
With the new article/model etc. of the mathematics model analysis of generation, classify to these article/models etc., to obtain institute's commentary
Valence information.In some embodiments, the evaluation information acquired can also be inspected by random samples, it, then can be with if there is error
Training set is added after artificial mark, re-starts training, obtains new mathematical model.
It is understood that the classification results have sorted out and the associated positive information of the expert and negative letter
Therefore breath can obtain the negative information and the positive information according to the classification results.For example, the negative information
Including " negative ", " expression is unintelligible ", " attitude is bad ", " unprofessional " etc., the positive information includes " affirmative ", " expression is clear
It is clear ", " attitude is good " " profession " etc..
After obtaining the negative information and positive information, in order to intuitively reflect the network influence of the expert,
Therefore it needs the negative information and the positive information carrying out quantification treatment.Wherein, by the negative information and it is described just
It includes: that the negative information and the positive information are converted into specific numerical value respectively that face information, which carries out quantification treatment, by phase
Numerical value corresponding to same negative information or positive information is integrated, etc..For example, the evaluation information is to certain expert
It is " affirmative " or " negating ", obtaining the negative information based on sorting algorithm is " negative ", and obtaining the positive information is " to agree
It is fixed " when, it can indicate " to affirm " with 1, count the number of " affirmative " in article/model, finally the number of statistics is summed
Processing, acquired results are to react the positive influences power that positive information is " affirmative " Shi Suoshu expert;It indicates " to negate " with -1, count
The number of " negative " in article/model, finally carries out summation process for the number of statistics, and acquired results react negative information and are
The negative effect power of " negative " Shi Suoshu expert.The size of result value can be used for characterizing the degree of network influence, for example,
" affirmative " corresponding numerical value is bigger, then illustrates that the positive influences power of expert is bigger, or " negative " corresponding numerical value is smaller, then says
The negative effect power of bright expert is bigger, wherein " affirmative " corresponding numerical value is bigger, and " negative " corresponding numerical value is got over hour, then says
The case where bright expert is affirmed and is denied is all very much, and the network influence of the expert is bigger.
In some embodiments, before executing the step S1011, the method also includes obtaining the base of the expert
This information, thus, the step S1011 is specially to be obtained to close with the expert from internet according to the essential information of the expert
The Web content of connection.The essential information can be essential information when expert's registration comprising the name of expert, correspondent party
Formula, locating region, research field, research direction etc..When obtaining the Web content according to the essential information, mesh can be reduced
Range is marked, it is more acurrate and more fully find the Web content.
It obtains above by internet with the associated Web content of expert, the net based on expert described in the network-content acquisition
Network influence power, it should be noted that in addition to this kind obtains the mode of network influence, other modes can also be used, for example, also
The relevant information of expert can be obtained from the Internal Management System of Client Enterprise, Change Management platform of enterprise etc., described in analysis
Relevant information, to obtain the network influence of the expert.
It is worth noting that the above-mentioned network influence got is mainly derived from internet, and on internet with it is described
Inevitably there is some and incongruent information of fact of case in the associated information of expert, if obtained based on these information
Network influence is taken, inevitably will cause that the expert power ultimately generated is not accurate enough, the result for causing subsequent expert to recommend is not
It is able to satisfy the demand of user.Therefore, it is necessary to judge the authenticity of the network influence.It is specific:
In some embodiments, after obtaining the network of experts influence power, the method also includes: to the negative shadow
It rings power and the positive influences power carries out confidence evaluation, to judge the confidence of the negative effect power and the positive influences power
Whether degree evaluation result meets preset condition, equal in the confidence evaluation result of the negative effect power and the positive influences power
When meeting preset condition, the following methods step of the present embodiment is just executed.
Wherein, carrying out confidence evaluation to the negative effect power and the positive influences power includes: according to negative effect
The corresponding sample information of power and the corresponding sample information of positive influences power carry out confidence calculations respectively, obtain the first confidence
Degree and the second confidence level, when resulting first confidence level is greater than default confidence threshold value, then the confidence of the negative effect power
Degree evaluation result meets preset condition, is otherwise unsatisfactory for;When resulting second confidence level is greater than default confidence threshold value, then institute
The confidence evaluation result for stating positive influences power meets preset condition, is otherwise unsatisfactory for.Wherein, the detailed process of confidence level is calculated
The prior art can be referred to.
Wherein, it when thering is a side to be unsatisfactory for preset condition in above-mentioned negative effect power and positive influences power, can hold again
Row obtains the step of network influence of expert, that is, obtains the new or more and associated Web content of the expert, base
In the negative effect power and positive influences power of network-content acquisition expert, alternatively, again to the Web content of above-mentioned acquisition into
Row analysis, weed out the negative information not being inconsistent with fact of case or positive information, then calculate again the negative effect power with
Positive influences power.When having a side to be unsatisfactory for preset condition in above-mentioned negative effect power and positive influences power, it is also based on full
One side of sufficient preset condition continues to execute the following step of the present embodiment.
Step S102, the expertise of the expert is obtained.
The expertise is a kind of information for reacting expert domain skill level.In order to than more objective acquisition institute
Expertise is stated, the expertise can be obtained by following methods, specifically, step S102 includes: to work to remember from expert
Record platform obtains the ability information of the expert, and the ability information includes business experience, managerial experiences;By the energy of the expert
Force information carries out quantification treatment, to obtain the expertise of the expert.
Wherein, expert's logging platform refers to carrying out the whole work process of expert on one platform of record,
The content recorded include the work of preparation stage, working condition and work in the process after result feedback etc..
Expert's logging platform specifically can be Change Management platform.The ability information further includes change experience.
Wherein, the Change Management platform is to realize customer demand and the matched place of expert, specifically can be operation
Change Management system at the terminal, the terminal include computer, smart phone, tablet computer, laptop, Intelligent bracelet
Equal terminal devices.The Change Management platform is for statisticalling analyze business experience, managerial experiences, change experience of expert etc..When
Enterprise or organizational growth are slow, and when internal problem is prominent, expert must make organizational change strategy, by intra-level, workflow
Journey and corporate culture etc. carry out necessary adjustment and improve management, to reach enterprise or tissue clean transformation.Wherein, specially
The organizational change strategy that family is done is the change experience of the expert.
Wherein, the ability information of the expert is carried out quantification treatment includes: the energy using specific numerical representation method expert
Force information.For example, the experience of change is " 1 ", managerial experiences are " 5 ", and business experience is " 2 ".Plan can be changed according to expert body
Number slightly determines that change experience, such as expert have only organized a change strategy within a preset time, then the change
Empirically determined is 1.The managerial experiences can be determined according to the position of expert is corresponding, for example, expert belongs to leadership, it is determined that
Managerial experiences are 2, and expert belongs to office worker's layer, it is determined that managerial experiences 0.5, etc..When can also be according to position, the tenure of expert
Between determine the managerial experiences of the expert, for example, expert belongs to leadership, and the time of holding a post was greater than 5 years, it is determined that described
The managerial experiences of expert are 10, etc..The business experience can be according to the length of service of expert, business achievement, others'evaluation etc.
To be determined, wherein the different weights such as length of service, business achievement, others'evaluation can be assigned, obtained finally by summation
Take the business experience of the expert.
It is above-mentioned mainly according to change warp, managerial experiences, business experience these three because usually determining expert expertise.When
So, in practical applications, the expertise of expert can also be determined according to other factors.
Step S103, expert's shadow is generated according to the negative effect power, the positive influences power and the expertise
Ring power.
It, can will be described after obtaining the negative effect power, the positive influences power and expertise through the above way
Negative effect power, the positive influences power and the expertise are integrated, and a numerical value, the numerical value, that is, expert are obtained
Influence power.Specifically, an expert power database can be pre-established, the expert power database includes multiple negative
Influence power numerical intervals, multiple positive influences power numerical intervals and multiple expertise numerical intervals, each section are right respectively
Answer an influence power weight parameter, wherein the corresponding network influence of heterogeneous networks influence power numerical intervals is different, different expert's warps
It is different to test the corresponding expertise of numerical intervals.Currently get the negative effect power, the positive influences power and described
It after expertise, is searched in the expert power database respectively, searches its corresponding numerical intervals, it is right according to its
The numerical intervals answered obtain influence power weight parameter, and expert's shadow of the expert is finally obtained according to the influence power weight parameter
Ring power.
For example, the corresponding negative effect power of expert A is 7, corresponding negative effect power numerical intervals are [6,10], this is negative
The corresponding influence power weight parameter of face influence power numerical intervals be 0.8, the corresponding positive influences power of expert A be 3, it is corresponding just
Face influence power numerical intervals are [0,5], which is 0.2, expert A's
Expertise is 2, and corresponding expertise numerical intervals are [0,3], the corresponding influence power power of the expertise numerical intervals
Weight parameter is 0.1, and the expert power of last technical specialist A is 0.8++0.2+0.1=1.1.
Certainly, after getting the network influence and the corresponding numerical value of the expertise, expert power is calculated
Mode be not limited in aforesaid way, can also be calculated using other modes.
In some embodiments, the network influence and the expertise can be merged in a table, the table
In data information directly reacted the expert power of the expert.For example, can indicate expert's shadow of expert with following table 1
Ring power.
Table 1
Above-described embodiment obtains expert power according to the network influence and expertise of expert, improves evaluation expert
Objectivity when influence power.
In some embodiments, same referring to Fig. 1, the method also includes:
Step S104, the network influence and the expertise are periodically updated.
Step S105, expert power is generated according to the updated network influence and the expertise.
After obtaining the network influence and the expertise through the foregoing embodiment, can also dynamically update described in
Network influence and expertise.The concrete mode for obtaining updated network influence and expertise can refer to above-mentioned reality
Apply example.For example, it is right " praise " can be updated according to this when increasing according to " praise " information that article or model get expert
The numerical values recited answered.At the same time, change experience, managerial experiences and the business experience that monitoring expert can be continued, according to it
Respective situation of change updates the expertise of the expert.
Wherein, the size in the period can be customized by the user setting, can also be arranged by system.
Wherein, the specific of the expert power is obtained according to updated network influence and updated expertise
Process can refer to the process of above-mentioned acquisition expert power.
The present embodiment can dynamically update network influence and expertise, and the expert power finally obtained is to be also
What dynamic updated, to keep the expert power obtained more acurrate.
It can be user based on expert power therefore according to the expert power of the available expert of above-described embodiment
Recommend suitable expert.Specifically, referring to Fig. 3, Fig. 3 is a kind of process of expert recommendation method provided in an embodiment of the present invention
Figure.As shown in figure 3, this method comprises:
Step S201, industry belonging to service content and specialist field are determined.
The service content refers to that the expert provides the particular content of service for user, for example, it is mutual for needing expert
Networking company provides performance management training service, then the service content is performance management training, corresponding industry is
Internet, corresponding specialist field are human resources.
Step S202, expert to be recommended is determined according to the industry and the specialist field.
The expert to be recommended can be to be multiple, and comforming to filter out in multi-expert according to industry and specialist field meets institute
State the expert of industry and the specialist field.Wherein, when screening expert, it can be based on preset expert database and carry out
Screening, include the expert of all trades and professions different field in the expert database.
Step S203, the expert power of the expert to be recommended is obtained.
The concrete mode for obtaining the expert power of the expert to be recommended can refer to the life of above-mentioned expert power
At embodiment of the method, details are not described herein.
Step S204, the expert recommended is determined from the expert to be recommended according to the expert power.
Wherein it is possible to the highest expert of expert power is recommended into user, it can also be according to the network influence of expert
Recommend multidigit expert to user with expertise, for example, including that network influence is strong but expertise is weak in multidigit expert
Expert and network influence is weak but expertise is strong expert and network influence is general and expertise is also general
Expert, expert is selected from multiple experts to be recommended according to personal preference by user.
It is above-mentioned to come to recommend expert also to more accurately obtain the expert of recommendation for user from industry and specialist field
To consider the regional information where expert.
In some embodiments, same referring to Fig. 3, the method also includes:
Step S205, the regional information of the expert to be recommended is obtained.
Step S206, it determines and recommends from the expert to be recommended according to the regional information and the expert power
Expert.
It is understood that as expert much the same including two expert powers in expert to be recommended, wherein one
Position expert and user are in the same city, then the expert for being located at same city with the user is paid the utmost attention to, so as to reduce
User asks the cost of expert.Therefore, the present embodiment considers the regional information that expert to be recommended is presently in, according to the regional information
Expert to be recommended is obtained at a distance from user, comes to recommend suitable expert for the user in conjunction with the expert power.
In some embodiments, same referring to Fig. 3, the method also includes:
It step S207, is that the expert to be recommended labels according to the expert power of the expert to be recommended.
It labels for the expert to be recommended and is, assessed according to the size of the expert power of expert to be recommended special
The rank of family, for example, whether assessment experts are advanced experts, if so, sticking the label of " advanced expert " for the expert.Its
In, it can be when the expert power be greater than preset threshold, it is determined that the expert is advanced expert.
Step S208, region belonging to the corresponding expert of the label is highlighted on map, to analyze the mark
Sign the Regional Distribution situation of corresponding expert.
The map denotation can be in the display interface for the electronic equipment for executing this method for reacting regional information
Map, for example, map of China, world map etc..It is described highlight including with one of figure, color, brightness etc. or
It is several to be highlighted.
For example, as shown in figure 4, Fig. 4 includes that service module, alternative network of experts influence power module and mapping module,
In, service module, which can choose expert, needs service content to be offered, and alternative network of experts influences power module for determining expert
Label, such as " advanced ", after user determines that service module and alternative network of experts influence the content of power module, in ground artwork
Region belonging to the corresponding expert of the label is highlighted on block, for example, can be prominent aobvious on map of China by dot
Show the region where " advanced expert ", according to the quantity and concentration of dot, it is corresponding " advanced special that certain region can be reflected
Family " situation.
In some embodiments, user can carry out the map for showing region belonging to the corresponding expert of the label
Operation, for example, when user wants to count some region of expert's quantity, it can be with mouse or finger or writing pencil in institute
It states and marks the region on map, after system captures the region that user is marked, the corresponding expert's quantity in the programming count region,
And it is shown in the display interface of electronic equipment.
Further, the adjustable service module of user and the alternative network of experts influence the content of power module,
According to the adjustment, the mapping module makes corresponding adjustment.Wherein it is possible to realize institute by modes such as hand-written, voice inputs
State adjustment.
Thus, on the one hand, user intuitively can recognize alternative experts at different levels geographically from mapping module
Distribution situation recommends expert to provide reference for user;On the other hand, user can based on the expert info that is shown on map with
Electronic equipment interacts operation, and simple, convenient.
In some embodiments, the expert to be recommended includes multiple, it is same referring to Fig. 3, the method also includes:
Step S209, multiple experts to be recommended and its corresponding expert power are shown.
Wherein, the multiple experts to be recommended of the display and its corresponding expert power include: that display is described wait push away
The name of the expert recommended, the corresponding assessed value of network influence and the corresponding assessed value of the expertise;Alternatively,
Show the name and the corresponding assessed value of the expert power of the expert to be recommended.
Wherein, the network influence assessed value and the expertise assessed value are referred to for reaction network influence power
Or the numerical value of accounting situation of the expertise in whole numerical value.For example, as shown in figure 5, the network influence of expert Zhang San
In, " praise " occupies 70%, and " criticism " occupies 30%, and in the network influence of expert Li Si, " praise " occupies 40%, " criticism "
Occupy 60%.It should be noted that Fig. 5 is not limited in Fig. 5, may be used also only as a kind of illustration for showing network influence
By be it is as shown in FIG. 6 in a manner of be shown.
Wherein, the corresponding assessed value of the expert power refers to the accounting feelings of network influence and expertise respectively
Condition, for example, the network influence of expert A is 80%, expertise 20%, etc..
Wherein it is possible to execute this method electronic equipment display interface on preset mode show it is above-mentioned it is multiple to
Recommend the corresponding relevant information of expert, in display, the strong expert of network influence can be put in the first place, or by expert's shadow
Ring that power is highest puts in the first place, or put in the first place expertise is strongest, etc..
Step S210, the select expert instruction for receiving user, determines the special of recommendation to instruct according to the select expert
Family.
Multiple expert infos to be recommended that user can show according to above-mentioned display interface therefrom select suitable expert.
User is when display interface selects expert, including the modes such as voice input, finger slidably input, keyboard inputs, gesture input are come
Selection.
A kind of expert recommendation method is present embodiments provided, this method can be according to the implementation of above-mentioned generation expert power
Example obtains expert power, then recommends expert to user according to expert power, and user can be according to the knot of recommendation
Fruit actively selects expert.The expert recommendation method improves the accuracy rate of expert's recommendation, is more able to satisfy user demand.
Referring to Fig. 7, Fig. 7 is a kind of structural block diagram of the generating means of expert power provided in an embodiment of the present invention,
As shown in fig. 7, the device 30 includes: that the first acquisition module 301, second obtains module 302, the first generation module 303.
Wherein, the network that the first acquisition module 301 is used to obtain expert influences, and the network influence includes negative
Influence power and positive influences power;The second acquisition module 302 is used to obtain the expertise of the expert;Described first generates
Module 303 is used to generate expert power according to the negative effect power, the positive influences power and the expertise.
Wherein, the first acquisition module 301 is specifically used for: out of internet acquisition and the associated network of the expert
Hold;The evaluation information of the expert is extracted from the Web content;The evaluation information is analyzed, to obtain the negative of the expert
Information and positive information;The negative information and the positive information are subjected to quantification treatment, to generate the negative of the expert
Influence power and positive influences power.
Wherein, the second acquisition module 302 is specifically used for: the ability of the expert is obtained from expert's logging platform
Information, the ability information include business experience, managerial experiences and change experience;By the ability information amount of progress of the expert
Change processing, to obtain the expertise of the expert.
In some embodiments, described device 30 further includes confidence evaluation module, and the confidence evaluation module is used for
Confidence evaluation is carried out to the negative effect power and the positive influences power, to judge the negative effect power and the front
Whether the confidence evaluation result of influence power meets preset condition.The confidence evaluation module can obtain mould described first
After block 301 gets the network influence of the expert, to it is described negative effect power and positive influences power confidence level respectively into
Row evaluation.
In some embodiments, equally referring to Fig. 7, described device 30 further includes that update module 304 and second generate mould
Block 305.The update module 304 is for periodically updating the network influence and the expertise;Described second is raw
It is used to generate expert power according to the updated network influence and the expertise at module 305.
It should be noted that expert's shadow provided by the embodiment of the present invention can be performed in the generating means of above-mentioned expert power
The generation method for ringing power, has the corresponding functional module of execution method and beneficial effect.Not in the generating means of expert power
The technical detail of the detailed description of embodiment, reference can be made to the generation method of expert power provided by the embodiment of the present invention.
Referring to Fig. 8, Fig. 8 is a kind of structural block diagram of expert's recommendation apparatus provided in an embodiment of the present invention, such as Fig. 8 institute
It states, which includes: the first determining module 401, the second determining module 402, first acquisition module 403 and the first recommendation mould
Block 404.
Wherein, first determining module 401 is for determining industry belonging to service content and specialist field;Described second
Determining module 402 is used to determine expert to be recommended according to the industry and the specialist field;Described first obtains module 403
For obtaining the expert power of the expert to be recommended;First recommending module 404 is used to be influenced according to the expert
Power determines the expert recommended from the expert to be recommended.
In some embodiments, same referring to Fig. 8, described device 40 further includes that the second acquisition module 405 and second push away
Recommend module 406.The second acquisition module 405 is used to obtain the regional information of the expert to be recommended;Described second recommends
Module 406 is used to determine the special of recommendation from the expert to be recommended according to the regional information and the expert power
Family.
In some embodiments, equally referring to Fig. 8, described device 40 further includes processing module 407 and the first display mould
Block 408.The processing module 407 is used to according to the influence power of the expert to be recommended be expert's mark to be recommended
Label;First display module 408 on map for highlighting region belonging to the corresponding expert of the label, to divide
Analyse the Regional Distribution situation of the corresponding expert of the label.
In some embodiments, same referring to Fig. 8, described device 40 further includes that the second display module 409 and instruction connect
Receive module 410.Second display module 409 is for showing multiple experts to be recommended and its corresponding expert power;
Described instruction receiving module 410 is used to receive the select expert instruction of user, to be pushed away according to select expert instruction determination
The expert recommended.
It should be noted that expert recommendation method provided by the embodiment of the present invention can be performed in above-mentioned expert's recommendation apparatus,
Have the corresponding functional module of execution method and beneficial effect.It is thinless in the technology of the detailed description of expert's recommendation apparatus embodiment
Section, reference can be made to expert recommendation method provided by the embodiment of the present invention.
Referring to Fig. 9, Fig. 9 is the hardware structural diagram of a kind of electronic equipment provided in an embodiment of the present invention, such as Fig. 9 institute
Show, which includes:
One or more processors 501 and memory 502, in Fig. 9 by taking a processor 501 as an example.
Processor 501 can be connected with memory 502 by bus or other modes, to be connected by bus in Fig. 9
For.
Memory 502 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module, such as the generation method pair of the expert power in the embodiment of the present invention
Program instruction/the module answered is (for example, attached shown in Fig. 7 first obtains the acquisition generation mould of module 302, first of module 301, second
Block 303, update module 304 and the second generation module 305).Processor 501 is stored in non-in memory 502 by operation
Volatibility software program, instruction and module are realized thereby executing the various function application and data processing of server
State the generation method and expert recommendation method of the expert power of embodiment of the method.
Memory 502 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function;Storage data area can be stored according to the generating means of expert power and specially
Family's recommendation apparatus uses created data etc..In addition, memory 502 may include high-speed random access memory, may be used also
To include nonvolatile memory, a for example, at least disk memory, flush memory device or the storage of other nonvolatile solid states
Device.In some embodiments, it includes the memory remotely located relative to processor 501 that memory 502 is optional, these are long-range
Memory can be by being connected to the network to the generating means and expert's recommendation apparatus of expert power.The example of above-mentioned network includes
But be not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 502, when by one or more of processors
When 501 execution, the method in above-mentioned any means embodiment is executed, for example, executing the method and step in Fig. 1 described above
Method and step S201 to step S210 in method and step S1011 to step S1014 in S101 to step S105, Fig. 2, Fig. 3,
Realize the function of the module 401-410 in the module 301-305, Fig. 8 in Fig. 7.
Method provided by the embodiment of the present invention can be performed in the said goods, has the corresponding functional module of execution method and has
Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present invention.
The electronic equipment of the embodiment of the present invention exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(4) other electronic devices with data interaction function.
The embodiment of the invention provides a kind of non-volatile computer readable storage medium storing program for executing, and the non-volatile computer can
It reads storage medium and is stored with computer executable instructions, which executes above-mentioned any means by electronic equipment
Method in embodiment, for example, the method and step S101 to step S105 in Fig. 1 described above is executed, the method step in Fig. 2
Method and step S201 to step S210 in rapid S1011 to step S1014, Fig. 3, is realized in the module 301-305, Fig. 8 in Fig. 7
Module 401-410 function.
The embodiment of the invention provides a kind of computer program products, including are stored in non-volatile computer readable storage
Calculation procedure on medium, the computer program include program instruction, are computer-executed constantly, make when described program instructs
The computer executes the method in above-mentioned any means embodiment, for example, executing the method and step in Fig. 1 described above
Method and step S201 to step S210 in method and step S1011 to step S1014 in S101 to step S105, Fig. 2, Fig. 3,
Realize the function of the module 401-410 in the module 301-305, Fig. 8 in Fig. 7.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.
Through the above description of the embodiments, those of ordinary skill in the art can be understood that each embodiment
The mode of general hardware platform can be added to realize by software, naturally it is also possible to realize by hardware.Ordinary skill
Personnel are understood that realize that all or part of the process in above-described embodiment method is can to instruct phase by computer program
The hardware of pass is completed, and the program can be stored in a computer-readable storage medium, which when being executed, can wrap
Include the process of the embodiment such as above-mentioned each method.Wherein, the storage medium can be magnetic disk, CD, read-only memory
(Read-Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;At this
It under the thinking of invention, can also be combined between the technical characteristic in above embodiments or different embodiment, step can be with
It is realized with random order, and there are many other variations of different aspect present invention as described above, for simplicity, they do not have
Have and is provided in details;Although the present invention is described in detail referring to the foregoing embodiments, the ordinary skill people of this field
Member is it is understood that it is still possible to modify the technical solutions described in the foregoing embodiments, or to part of skill
Art feature is equivalently replaced;And these are modified or replaceed, each reality of the present invention that it does not separate the essence of the corresponding technical solution
Apply the range of a technical solution.
Claims (10)
1. a kind of generation method of expert power, which is characterized in that the described method includes:
The network influence of expert is obtained, the network influence includes negative effect power and positive influences power;
Obtain the expertise of the expert;
Expert power is generated according to the negative effect power, the positive influences power and the expertise.
2. the method according to claim 1, wherein the network influence for obtaining expert includes:
It is obtained and the associated Web content of the expert from internet;
The evaluation information of the expert is extracted from the Web content;
The evaluation information is analyzed, to obtain the negative information and positive information of the expert;
The negative information and the positive information are subjected to quantification treatment, to generate negative effect power and the front of the expert
Influence power.
3. the method according to claim 1, wherein execute it is described according to the negative effect power, it is described just
Before the step for face influence power and the expertise generate expert power, the method also includes:
Confidence evaluation is carried out to the negative effect power and the positive influences power, to judge the negative effect power and described
Whether the confidence evaluation result of positive influences power meets preset condition, in the negative effect power and the positive influences power
When confidence evaluation result is all satisfied preset condition, just execute it is described according to the negative effect power, the positive influences power with
And the expertise generates the step of expert power.
4. according to the method in any one of claims 1 to 3, which is characterized in that the expert's warp for obtaining the expert
It tests and includes:
The ability information of the expert is obtained from expert's logging platform, the ability information includes business experience and management warp
It tests;
The ability information of the expert is subjected to quantification treatment, to obtain the expertise of the expert.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
Periodically update the network influence and the expertise;
Expert power is generated according to the updated network influence and the expertise.
6. a kind of expert recommendation method, which is characterized in that the described method includes:
Determine industry belonging to service content and specialist field;
Expert to be recommended is determined according to the industry and the specialist field;
The method according to any one of claims 1 to 5 obtains the expert power of the expert to be recommended;
The expert recommended is determined from the expert to be recommended according to the expert power.
7. according to the method described in claim 6, it is characterized in that, the method also includes:
Obtain the regional information of the expert to be recommended;
The expert recommended is determined from the expert to be recommended according to the regional information and the expert power.
8. the method according to the description of claim 7 is characterized in that the method also includes:
It is that the expert to be recommended labels according to the expert power of the expert to be recommended;
Region belonging to the corresponding expert of the label is highlighted on map, to analyze the corresponding expert's of the label
Regional Distribution situation.
9. the method according to any one of claim 6 to 8, which is characterized in that the expert to be recommended include it is multiple,
The method also includes:
Show multiple experts to be recommended and its corresponding expert power;
The select expert instruction for receiving user, to instruct the expert for determining and recommending according to the select expert.
10. a kind of electronic equipment characterized by comprising
At least one processor;And
The memory being connect at least one described processor communication;
Wherein, the memory be stored with can by least one described processor execute instruction, described instruction by it is described at least
One processor executes, so that at least one described processor is able to carry out method described in any one of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910619736.XA CN110413778A (en) | 2019-07-10 | 2019-07-10 | Generation method, expert recommendation method and the electronic equipment of expert power |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910619736.XA CN110413778A (en) | 2019-07-10 | 2019-07-10 | Generation method, expert recommendation method and the electronic equipment of expert power |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110413778A true CN110413778A (en) | 2019-11-05 |
Family
ID=68360936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910619736.XA Pending CN110413778A (en) | 2019-07-10 | 2019-07-10 | Generation method, expert recommendation method and the electronic equipment of expert power |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110413778A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113140298A (en) * | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Remote doctor evaluation method, system, equipment and storage medium thereof |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060282336A1 (en) * | 2005-06-08 | 2006-12-14 | Huang Ian T | Internet search engine with critic ratings |
CN105095408A (en) * | 2015-07-09 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for judging reliability of network expert |
CN105809488A (en) * | 2016-03-29 | 2016-07-27 | 联想(北京)有限公司 | Information processing method and electronic device |
CN105843934A (en) * | 2016-03-30 | 2016-08-10 | 知集市科技成都有限公司 | Expert map generation method and device |
CN108550065A (en) * | 2018-04-10 | 2018-09-18 | 百度在线网络技术(北京)有限公司 | comment data processing method, device and equipment |
CN108960686A (en) * | 2018-08-20 | 2018-12-07 | 杜林蔚 | Influence power appraisal procedure and system |
-
2019
- 2019-07-10 CN CN201910619736.XA patent/CN110413778A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060282336A1 (en) * | 2005-06-08 | 2006-12-14 | Huang Ian T | Internet search engine with critic ratings |
CN105095408A (en) * | 2015-07-09 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for judging reliability of network expert |
CN105809488A (en) * | 2016-03-29 | 2016-07-27 | 联想(北京)有限公司 | Information processing method and electronic device |
CN105843934A (en) * | 2016-03-30 | 2016-08-10 | 知集市科技成都有限公司 | Expert map generation method and device |
CN108550065A (en) * | 2018-04-10 | 2018-09-18 | 百度在线网络技术(北京)有限公司 | comment data processing method, device and equipment |
CN108960686A (en) * | 2018-08-20 | 2018-12-07 | 杜林蔚 | Influence power appraisal procedure and system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113140298A (en) * | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Remote doctor evaluation method, system, equipment and storage medium thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106530010B (en) | The collaborative filtering method and device of time of fusion factor | |
CN108229590B (en) | Method and device for acquiring multi-label user portrait | |
CN110321477A (en) | Information recommendation method, device, terminal and storage medium | |
CN109409528A (en) | Model generating method, device, computer equipment and storage medium | |
CN109934619A (en) | User's portrait tag modeling method, apparatus, electronic equipment and readable storage medium storing program for executing | |
CN110163234A (en) | A kind of model training method, device and storage medium | |
Sun et al. | Contextual intent tracking for personal assistants | |
CN108132961B (en) | Reference recommendation method based on citation prediction | |
CN106959998B (en) | Test question recommendation method and device | |
CN109817312A (en) | A kind of medical bootstrap technique and computer equipment | |
Tai et al. | Effective e‐learning recommendation system based on self‐organizing maps and association mining | |
CN111639988B (en) | Broker recommendation method, device, electronic equipment and storage medium | |
CN103262118A (en) | Attribute value estimation device, attribute value estimation method, program, and recording medium | |
CN104346408B (en) | A kind of method and apparatus being labeled to the network user | |
CN110580489B (en) | Data object classification system, method and equipment | |
CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
CN110046889A (en) | A kind of detection method, device and the server of abnormal behaviour main body | |
CN108228684A (en) | Training method, device, electronic equipment and the computer storage media of Clustering Model | |
Muñoz-Leiva et al. | Detecting salient themes in financial marketing research from 1961 to 2010 | |
CN109191167A (en) | A kind of method for digging and device of target user | |
CN108804564A (en) | The combined recommendation method and terminal device of financial product | |
CN113918806A (en) | Method for automatically recommending training courses and related equipment | |
CN109345201A (en) | Human Resources Management Method, device, electronic equipment and storage medium | |
CN104778388A (en) | Method and system for identifying same user under two different platforms | |
CN110413778A (en) | Generation method, expert recommendation method and the electronic equipment of expert power |
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 |
Application publication date: 20191105 |
|
RJ01 | Rejection of invention patent application after publication |