CN117556284A

CN117556284A - Expert extraction method, device, apparatus, medium and program product

Info

Publication number: CN117556284A
Application number: CN202311505291.5A
Authority: CN
Inventors: 邬文佳
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-11-13
Filing date: 2023-11-13
Publication date: 2024-02-13

Abstract

The disclosure provides an expert extraction method, which can be applied to the field of artificial intelligence and the field of financial technology. The method comprises the following steps: determining a target expert database; determining expert correlation characteristics; clustering and grouping the target expert database according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub expert groups; extracting an expert from each sub expert group respectively to obtain a target expert group; the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold. The present disclosure also provides an expert extraction apparatus, device, storage medium, and program product.

Description

Expert extraction method, device, apparatus, medium and program product

Technical Field

The present disclosure relates to the field of artificial intelligence and financial, and in particular to an expert extraction method, apparatus, device, medium and program product.

Background

The current bidding process, whether the bidding party or the bidding company is commissioned, is a preliminary opinion consisting of the negotiation expert group for the current project provided by the bidding party, including expert number, expert expertise, expert level, etc. And determining the corresponding person selection in the corresponding expert database by a random extraction method. And then sending negotiation invitation to the extracted expert, and if the expert chooses not to participate, continuing to randomly extract until the expert meeting the requirements of the number of people to participate in negotiation is reached. And the expert group is used for carrying out qualification auditing, negotiation, qualitative and quantitative scoring on the suppliers to finally obtain the score and the enclosing condition of each company participating in the negotiation.

Because the expert extracted by the random algorithm can not ensure that the association degree between the experts in the expert group is as low as possible, if the expert has very high association, the negotiation result can be influenced, and the disclosure, fairness and fairness of purchase negotiation work can not be ensured.

Based on the analysis, the extraction work of the purchasing experts not only meets the basic requirement of the bidding party, but also ensures that the association degree between the experts of the expert group is as low as possible.

Disclosure of Invention

In view of the above, the present disclosure provides an expert extraction method, apparatus, device, medium, and program product for improving the reliability of expert extraction, for at least partially solving the above technical problems.

According to a first aspect of the present disclosure, there is provided an expert extraction method, comprising: determining a target expert database; determining expert correlation characteristics; clustering and grouping the target expert database according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub expert groups; extracting an expert from each sub expert group respectively to obtain a target expert group; the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold.

According to an embodiment of the present disclosure, clustering a target expert library according to a required number of experts and an expert correlation feature, obtaining a plurality of sub-expert groups includes: quantifying expert correlation characteristics to obtain a plurality of coordinate points; and clustering and grouping the coordinate points by adopting a Kmeans algorithm according to the number of required experts to obtain a plurality of sub-expert groups.

According to an embodiment of the present disclosure, the expert correlation feature includes a current working address and/or an address, quantizing the expert correlation feature, and obtaining a plurality of coordinate points includes: mapping longitude and latitude coordinates of a current working address and/or an address to a multidimensional coordinate space to obtain a plurality of coordinate points; the multidimensional coordinate space comprises a plurality of coordinate axes, and the coordinate axes are in one-to-one correspondence with expert correlation characteristics.

According to an embodiment of the present disclosure, the expert correlation feature further includes a learning experience and/or a work experience, quantizing the expert correlation feature, and obtaining the plurality of coordinate points further includes: and mapping longitude and latitude coordinates of the school address and/or the historical work address to a multidimensional coordinate space to obtain a plurality of coordinate points.

According to an embodiment of the present disclosure, the expert correlation feature further includes an age and/or a sex, and the quantifying the expert correlation feature to obtain a plurality of coordinate points further includes: mapping the age and/or sex to a multidimensional coordinate space to obtain a plurality of coordinate points; wherein, the coordinate axis scales corresponding to the sexes are male and female.

According to an embodiment of the present disclosure, extracting an expert from each sub-expert group, respectively, to obtain a target expert group includes: randomly sequencing the experts in each sub expert group to obtain a plurality of random expert sequences; extracting an expert from each random expert sequence to obtain a target expert group; wherein extracting an expert from a single random expert sequence comprises: and sequentially extracting the experts according to the random expert sequence order according to the expert participation wish.

According to an embodiment of the present disclosure, clustering the target expert database according to the number of required experts and the expert correlation feature, obtaining a plurality of sub-expert groups further includes: clustering and grouping a plurality of coordinate points by adopting a Kmeans algorithm according to the preset expert number to obtain a plurality of sub-expert groups; wherein the preset expert number is greater than the required expert number.

A second aspect of the present disclosure provides an expert extraction apparatus comprising: the first determining module is used for determining a target expert database; the second determining module is used for determining expert correlation characteristics; the grouping module is used for clustering and grouping the target expert database according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub-expert groups; the extraction module is used for extracting one expert from each sub expert group respectively to obtain a target expert group; the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold.

A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of the embodiments described above.

A fourth aspect of the present disclosure also provides a computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any of the embodiments described above.

A fifth aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the embodiments described above.

Compared with the prior art, the expert extraction method, the expert extraction device, the electronic equipment, the storage medium and the program product have at least the following beneficial effects:

(1) According to the expert extraction method, a plurality of to-be-selected experts are clustered and grouped according to the correlation characteristics of the experts, so that the experts with larger similarity are in the same group, wherein the grouping number is the number of required experts. And then, extracting one expert from each group to form a target expert group, so that the similarity among the experts in the target expert group is reduced, and the credibility of the expert extraction result is improved.

(2) According to the expert extraction method, through quantifying the correlation characteristics of various experts, coordinate points in a multidimensional space are obtained, and then the coordinate points are clustered by adopting a kmeans algorithm, so that the similarity among the experts in the target expert group is reduced, and the method is simple, convenient and quick.

(3) The expert extraction method disclosed by the invention has the advantages that the expert correlation characteristics comprise work addresses, learning experiences, ages, sexes and the like, and the correlation of the experts among different groups is reduced from multiple dimensions, so that the method is practical and effective.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of expert extraction methods, apparatus, devices, media, and program products according to embodiments of the present disclosure;

FIG. 2 schematically illustrates a flow chart of an expert extraction method according to an embodiment of the disclosure;

FIG. 3 schematically illustrates a flow chart of a method of clustering a target expert library in accordance with an embodiment of the disclosure;

FIG. 4 schematically illustrates a flow chart of a method of quantifying expert correlation features, in accordance with an embodiment of the present disclosure;

FIG. 5 schematically illustrates a flow chart of a method of quantifying expert correlation features, according to another embodiment of the disclosure;

FIG. 6 schematically illustrates a flow chart of a method of quantifying expert correlation features in accordance with yet another embodiment of the present disclosure;

FIG. 7A schematically illustrates a flow chart of a method of extracting one expert from each sub-expert group in accordance with an embodiment of the present disclosure; FIG. 7B schematically illustrates a flow chart of an expert extraction method according to another embodiment of the present disclosure;

FIG. 8 schematically illustrates a flow chart of a method of clustering a target expert library in accordance with another embodiment of the present disclosure;

fig. 9 schematically shows a block diagram of the expert extraction apparatus according to an embodiment of the present disclosure; and

fig. 10 schematically illustrates a block diagram of an electronic device adapted to implement the expert extraction method according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

The disclosed embodiments provide an expert extraction method, apparatus, device, medium and program product, which can be used in the financial field or other fields. It should be noted that the expert extraction method, apparatus, device, medium and program product of the present disclosure may be used in the financial field, and may also be used in any field other than the financial field, and the application fields of the expert extraction method, apparatus, device, medium and program product of the present disclosure are not limited.

In the technical scheme of the invention, the related user information (including but not limited to user personal information, user image information, user equipment information, such as position information and the like) and data (including but not limited to data for analysis, stored data, displayed data and the like) are information and data authorized by a user or fully authorized by all parties, and the processing of the related data such as collection, storage, use, processing, transmission, provision, disclosure, application and the like are all conducted according to the related laws and regulations and standards of related countries and regions, necessary security measures are adopted, no prejudice to the public welfare is provided, and corresponding operation inlets are provided for the user to select authorization or rejection.

The embodiment of the disclosure provides an expert extraction method, which comprises the following steps: determining a target expert database; determining expert correlation characteristics; clustering and grouping the target expert database according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub expert groups; extracting an expert from each sub expert group respectively to obtain a target expert group; the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold. The method reduces the similarity among the experts in the target expert group and improves the credibility of the expert extraction result.

Fig. 1 schematically illustrates an application scenario diagram of expert extraction methods, apparatuses, devices, media and program products according to embodiments of the present disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the expert extraction method provided in the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the expert extraction apparatus provided by the embodiments of the present disclosure may be generally provided in the server 105. The expert extraction method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the expert extraction apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The expert extraction method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 8 based on the scenario described in fig. 1.

Fig. 2 schematically illustrates a flow chart of an expert extraction method according to an embodiment of the disclosure.

As shown in fig. 2, the expert extraction method of this embodiment includes, for example, operations S210 to S240, and the expert extraction method may be executed by a computer program on corresponding computer hardware.

In operation S210, a target expert database is determined.

In operation S220, an expert correlation characteristic is determined.

In operation S230, the target expert database is clustered according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub-expert groups. The distance between the clustering centers of any two sub-expert groups is larger than a preset threshold.

In operation S240, one expert is extracted from each sub-expert group, respectively, to obtain a target expert group.

For example, it is first necessary to determine a target expert database, that is, information about the professional field, institution, region, etc. from which the expert is to be extracted. And determining an expert library generated by the expert, screening the expert meeting the requirement of the bidding party in the expert library, and determining the randomly extracted expert range. The target expert database is assumed to be an expert in the field of engineering project management, including experts from different regions and different institutions. Expert correlation features may include their educational background, work experience, professional fields, research projects, and the like. For example, two experts may have a high degree of relevance in the same university graduation, engaged in similar engineering project management areas. And clustering and grouping the experts in the target expert library by using a clustering algorithm to obtain a plurality of sub-expert groups. During the grouping process, a threshold may be set such that the distance between any two sub-expert groups exceeds the threshold. The purpose of this is to minimize expert correlation between different groups to increase the randomness and fairness of the extracted expert. One expert is randomly extracted from each sub expert group to form a target expert group. Because the distance between different sub expert groups is larger, the extracted expert can be ensured to come from different backgrounds and fields, and the extracted expert has larger diversity and representativeness.

Wherein, during the clustering process, the center point of each sub-expert group, i.e. the cluster center, can be calculated. If the distance between the clustering centers of any two sub-expert groups is larger than the preset threshold value, the distance between the two sub-expert groups is larger, and the represented fields and the background are also larger different. This ensures that the expert in the extraction is not too focused on a particular area or institution, thereby increasing fairness and broad representativeness.

Through the steps, fairness and fairness of bidding process can be increased. The method can reduce the correlation degree among different groups of experts as much as possible, so that the extracted experts have larger diversity and representativeness, and the requirement of a signer is better met.

It will be appreciated that the above-described target expert database is merely illustrative of the field of study of the expert. Different bidding projects require different areas of expertise, for example, the target expert base may include, but is not limited to, relevant institutions and experts engaged in environmental protection, information technology, medical, and the like.

In embodiments of the present disclosure, the user's consent or authorization may be obtained prior to obtaining the user's information. For example, before operation S220, a request to acquire user information may be issued to the user. In case that the user agrees or authorizes that the user information can be acquired, the operation S220 is performed.

Fig. 3 schematically illustrates a flow chart of a method of clustering a target expert library according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, as shown in fig. 3, the target expert libraries are clustered, for example, through operations S331 to S332.

In operation S331, the expert correlation feature is quantized to obtain a plurality of coordinate points.

In operation S332, a plurality of coordinate points are clustered and grouped by Kmeans algorithm according to the number of required experts, so as to obtain a plurality of sub-expert groups.

For example, an M-dimensional coordinate axis is established, which represents each expert correlation feature, respectively, so that each expert is placed into the coordinate axis. Because the characteristic value is fixed, the expert only has one point position in the coordinate axis established by the characteristic value, and the distance between the points can be calculated.

For example, first, the correlation feature of each expert needs to be quantized, which is expressed as a plurality of coordinate points. For example, for each expert, its educational background (e.g., graduation, specialty), work experience (e.g., company, job position, time of day), professional field (e.g., civil engineering, electro-mechanical engineering, etc.), and research project (e.g., research direction, published paper, etc.) may be quantified as features. Some common quantization methods, such as TF-IDF, textRank, etc., can be used in this process. Next, according to the number of required experts, a Kmeans algorithm may be used to cluster and group a plurality of coordinate points of all the experts. In this process, a suitable distance measure (e.g., euclidean distance, cosine similarity, etc.) may be selected to measure similarity between experts. All the experts can be divided into several clusters by Kmeans algorithm, each cluster representing a sub-group of experts.

For example, assuming a required number of experts of 7, all the experts may be divided into 7 clusters, each containing one or more experts. Each cluster represents a sub-group of experts, the experts in the sub-group having a high degree of similarity over a plurality of coordinate points. In this way, a lower degree of correlation between the extracted experts can be ensured, thereby improving the credibility of the constructed expert group.

Meanwhile, clustering grouping is carried out on a plurality of coordinate points through a Kmeans algorithm, so that expert groups in different fields can be obtained. This ensures that the extracted specialists cover different areas and contexts, thereby increasing the fairness and broad representativeness of the bidding process.

Based on Kmeans algorithm, dividing the experts into N groups, firstly placing all the experts into coordinate axes according to characteristic values, and randomly framing N groups of data. Calculating initial clustering center points of each group of data, respectively calculating distances between the point positions of each expert and N initial clustering centers, finishing grouping again according to the distances, calculating the clustering center points after grouping again, and repeating the steps until the clustering centers are not changed. The specific implementation is as follows:

determining the expert group sample { a }, which is extracted at this time and meets the conditions ₁ ，...，a _m }. Wherein a is a coordinate point corresponding to an expert in the target expert database.

Randomly selecting N initial cluster centers u ₁ ，u ₂ ，...，u _n ∈{a ₁ ，....，a _m }. Wherein u is a coordinate point which is initially selected as a clustering center.

And calculating the distance between each object and the initial cluster center, and selecting the cluster center closest to the initial cluster center.

c ⁽ⁱ⁾ ＝argmin||a ⁽ⁱ⁾ -u _j || ² (1)

Wherein c ⁽ⁱ⁾ Is one of 1 to n, indicating the nearest cluster center group from the object.

For each class j, the cluster center of the class needs to be recalculated:

for a calculated cluster center, a group is considered to end if no objects are assigned to a different cluster center upon recalculation, or no more changes occur to the cluster center.

Fig. 4 schematically illustrates a flow chart of a method of quantifying expert correlation features, according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the expert correlation feature includes a current work address and/or address, as shown in fig. 4, and the expert correlation feature is quantized, for example, by operation S4311, to obtain a plurality of coordinate points.

In operation S4311, the latitude and longitude coordinates of the current working address and/or address are mapped to the multi-dimensional coordinate space, resulting in a plurality of coordinate points. The multidimensional coordinate space comprises a plurality of coordinate axes, and the coordinate axes are in one-to-one correspondence with expert correlation characteristics.

For example, first, the correlation feature of each expert needs to be quantized, which is expressed as a plurality of coordinate points. In this example, two features that best reflect the relevance of the expert, namely the current work address and address, may be selected. For each expert, the longitude and latitude coordinates of their work address and address are mapped to a multidimensional coordinate space to obtain a plurality of coordinate points. The multidimensional coordinate space comprises two coordinate axes, one representing the longitude and latitude coordinates (x-axis) of the work address and the other representing the longitude and latitude coordinates (y-axis) of the address. Thus, each expert is represented as a coordinate point (x, y). In this multidimensional coordinate space, the distances between them can be calculated from the specific longitude and latitude coordinates of the expert, thereby evaluating their relevance. Points closer in distance represent higher correlation, and points farther in distance represent lower correlation.

And then, clustering and grouping a plurality of coordinate points of all the experts by adopting a Kmeans algorithm according to the number of required experts. In this process, a suitable distance measure (e.g., euclidean distance) may be selected to measure similarity between experts. All the experts can be divided into a plurality of clusters (sub-expert groups) through a Kmeans algorithm, and each cluster comprises one or more high-similarity experts. For example, assuming 7 experts are required, the coordinate points of all the experts may be divided into 7 clusters. The experts in each cluster have a high similarity in work addresses and addresses.

Finally, a random extraction of one expert from each cluster is used as a representative of the group, and a target expert group containing 7 experts is formed. These experts have a high degree of similarity in work addresses and addresses.

In this way, a process of randomly extracting one expert from each sub-expert group can be implemented. This can increase the fairness and fairness of the bidding process. Meanwhile, since only one expert is extracted per group, and different groups of experts can come from different fields and backgrounds, the final composed target expert group will contain experts in different fields with lower similarity and relevance. This can improve the broad representativeness and fairness of the bidding process.

Fig. 5 schematically illustrates a flow chart of a method of quantifying expert correlation features according to another embodiment of the disclosure.

According to an embodiment of the present disclosure, the expert correlation feature further includes a learning experience and/or a work experience, as shown in fig. 5, and for example, the expert correlation feature may be quantized by operation S5311 to obtain a plurality of coordinate points.

In operation S5311, latitude and longitude coordinates of the school address and/or the history work address are mapped to the multi-dimensional coordinate space to obtain a plurality of coordinate points.

For example, first, the correlation feature of each expert needs to be quantized, which is expressed as a plurality of coordinate points. In this example, four features that best reflect expert correlation, i.e., current work address, learning experience, and historical work address, may be selected. For each expert, the longitude and latitude coordinates of their work address, school address and historical work address are mapped to a multidimensional coordinate space to obtain a plurality of coordinate points. The multidimensional coordinate space comprises four coordinate axes, one representing the longitude and latitude coordinates (x-axis) of the work address, one representing the longitude and latitude coordinates (y-axis) of the address, one representing the longitude and latitude coordinates (z-axis) of the school address, and the other representing the longitude and latitude coordinates (w-axis) of the historical work address. Thus, each expert is represented as a coordinate point (x, y, z, w). In this multidimensional coordinate space, the distances between them can be calculated from the specific longitude and latitude coordinates of the expert, thereby evaluating their relevance. Points closer in distance represent higher correlation, and points farther in distance represent lower correlation.

And then, clustering and grouping a plurality of coordinate points of all the experts by adopting a Kmeans algorithm according to the number of required experts. In this process, a suitable distance measure (e.g., euclidean distance) may be selected to measure similarity between experts. All the experts can be divided into a plurality of clusters (sub-expert groups) through a Kmeans algorithm, and each cluster comprises one or more high-similarity experts. For example, assuming 7 experts are required, the coordinate points of all the experts may be divided into 7 clusters. The experts in each cluster have a high similarity in work addresses, learning experiences and historical work addresses.

Finally, a random extraction of one expert from each cluster is used as a representative of the group, and a target expert group containing 7 experts is formed. These experts have a high similarity in work addresses, learning experiences and historical work addresses.

Fig. 6 schematically illustrates a flow chart of a method of quantifying expert correlation features in accordance with yet another embodiment of the present disclosure.

According to an embodiment of the present disclosure, the expert correlation feature further includes an age and/or a sex, and as shown in fig. 6, the expert correlation feature may be further quantized, for example, by operation S6311, to obtain a plurality of coordinate points.

In operation S6311, the age and/or sex is mapped to a multi-dimensional coordinate space, resulting in a plurality of coordinate points. Wherein, the coordinate axis scales corresponding to the sexes are male and female.

For example, first, the correlation feature of each expert needs to be quantized, which is expressed as a plurality of coordinate points. In this example, five features that best reflect expert correlation, namely current work address, school address, historical work address, and age, may be selected. For each expert, their work address, school address, historical work address, and age are mapped to a multidimensional coordinate space, resulting in a plurality of coordinate points. The multidimensional coordinate space comprises five coordinate axes, one representing the longitude and latitude coordinates (x-axis) of the work address, one representing the longitude and latitude coordinates (y-axis) of the address, one representing the longitude and latitude coordinates (z-axis) of the school address, the other representing the longitude and latitude coordinates (w-axis) of the historical work address, and the last representing the age (t-axis). Thus, each expert is represented as a coordinate point (x, y, z, w, t). In this multidimensional coordinate space, the distance between the specific longitude and latitude coordinates and the age of the expert can be calculated according to the distance, so that the correlation of the expert can be evaluated. Points closer in distance represent higher correlation, and points farther in distance represent lower correlation.

In addition, in order to consider the gender factor, the gender may be mapped onto the t-axis corresponding to the age. The coordinate axis scales corresponding to the sex are male and female. Thus, each coordinate point has a sex identification of a man or woman in addition to latitude and longitude coordinates and age.

And then, clustering and grouping a plurality of coordinate points of all the experts by adopting a Kmeans algorithm according to the number of required experts. In this process, a suitable distance measure (e.g., euclidean distance) may be selected to measure similarity between experts. All the experts can be divided into a plurality of clusters (sub-expert groups) through a Kmeans algorithm, and each cluster comprises one or more high-similarity experts. For example, assuming 7 experts are required, the coordinate points of all the experts may be divided into 7 clusters. The experts in each cluster have a high similarity in work address, school address, historical work address, and age. In consideration of gender factors, each cluster may contain experts from different sexes.

Finally, a random extraction of one expert from each cluster is used as a representative of the group, and a target expert group containing 7 experts is formed. These experts have a high similarity in work address, school address, historical work address, and age. Meanwhile, in order to consider sex diversity, the extracted specialists may come from different sexes.

Fig. 7A schematically illustrates a flow chart of a method of extracting one expert from each sub-expert group in accordance with an embodiment of the present disclosure. Fig. 7B schematically illustrates a flow chart of an expert extraction method according to another embodiment of the present disclosure.

According to an embodiment of the present disclosure, as shown in fig. 7A, one expert is extracted from each sub-expert group, for example, through operations S741 to S742, respectively, to obtain a target expert group.

In operation S741, the experts in each sub-expert group are randomly ordered to obtain a plurality of random expert sequences.

In operation S742, an expert is extracted from each random expert sequence to obtain a target expert group. Wherein extracting an expert from a single random expert sequence comprises: and sequentially extracting the experts according to the random expert sequence order according to the expert participation wish.

For example, assume that coordinate points of all experts have been divided into 7 sub-expert groups. Each sub-expert group contains coordinate points of about 10 experts. First, the experts in each sub-expert group are randomly ordered to obtain 7 random expert sequences. Each random expert sequence contains coordinate points of about 10 experts. These random orderings are independent, i.e. the random orderings of the different sub-expert groups are independent of each other. For example, assume that there are 7 sub-expert groups, each of which contains coordinate points of 10-bit experts. The expert coordinate points of each sub-expert group can be randomly ordered to obtain 7 random expert sequences. These random expert sequences can be expressed as: s1, S2, S3, &.

Next, one expert is extracted from each random expert sequence as a representative of the group. This process may take into account the expert's willingness to participate. Assuming that 10 experts are in each sub expert group, the experts can be extracted in sequence according to the participation will of the experts and the sequence of the random expert sequences. For example, from S1, the first expert may be sequentially extracted according to the participation intention of the experts (as shown in fig. 7B, that is, when a group of first-order experts indicates not to participate, the group of second-order experts is contacted until a certain-order expert agrees or none of the group of experts agrees); from S2, sequentially extracting second specialists according to the participation intention of the specialists; and so on. Thus, a representative expert may be extracted from each sub-expert group to form the target expert group.

In this way, a process of randomly extracting one expert from each sub-expert group in order and will can be implemented. This can increase the fairness and fairness of the bidding process. Meanwhile, by determining the random extraction sequence in advance, after new experts are added and other extraction conditions are adjusted, the existing extraction sequence is not affected, and the stability of the extraction process is ensured.

Fig. 8 schematically illustrates a flow chart of a method of clustering a target expert library according to another embodiment of the present disclosure.

According to an embodiment of the present disclosure, as shown in fig. 8, the target expert database is clustered, for example, through operation S831.

In operation S831, a plurality of coordinate points are clustered and grouped by adopting Kmeans algorithm according to the preset number of experts, so as to obtain a plurality of sub-expert groups. Wherein the preset expert number is greater than the required expert number.

For example, assume that the target expert database contains relevance features for 100-bit experts, including latitude and longitude coordinates of work address, school address, and historical work address, and age. The number of required experts is 7. First, the number of preset sub-expert groups is 10 groups. Then, a Kmeans algorithm is adopted to cluster and group a plurality of coordinate points of all experts. In this process, a suitable distance measure (e.g., euclidean distance) may be selected to measure similarity between experts. All the experts are divided into 10 clusters (sub-expert groups) by a Kmeans algorithm, and each cluster contains high-similarity experts.

Then, an expert is randomly extracted from each cluster as a representative of the group, and a target expert group containing 7 experts is formed. These experts have a high similarity in work address, school address, historical work address, and age.

Consider the case of a spare sub-expert group:

if no suitable expert in a sub-expert group can be extracted, it is contemplated that one expert from the redundant 3 spare sub-expert groups can be extracted to fill the void. These spare sub-expert groups act as supplements in building the target expert group to ensure that the final target expert group is able to meet the requirements.

It should be noted that, because the grouping and the random ordering in the group are already determined when the drawing occurs, if all the experts in a group cannot participate in the evaluation, the drawing can only adjust the drawing condition. The adjustment of the extraction conditions will change the grouping and the expert in each group, so when the expert meeting the requirement cannot be generated in one group, the above steps can be repeated again from the screening expert to extract.

Based on the expert extraction method, the disclosure further provides an expert extraction device. The expert extraction device will be described in detail below with reference to fig. 9.

Fig. 9 schematically shows a block diagram of the structure of the expert extraction apparatus according to the embodiment of the present disclosure.

As shown in fig. 9, the expert extraction apparatus 900 of this embodiment includes, for example: a first determination module 910, a second determination module 920, a grouping module 930, and an extraction module 940.

The first determination module 910 is configured to determine a target expert database. In an embodiment, the first determining module 910 may be configured to perform the operation S210 described above, which is not described herein.

The second determination module 920 is configured to determine expert correlation characteristics. In an embodiment, the second determining module 920 may be configured to perform the operation S220 described above, which is not described herein.

The grouping module 930 is configured to cluster and group the target expert database according to the number of required experts and the expert correlation feature, to obtain a plurality of sub-expert groups. In an embodiment, the grouping module 930 may be configured to perform the operation S230 described above, which is not described herein.

The extracting module 940 is configured to extract an expert from each sub-expert group, respectively, to obtain a target expert group; the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold. In an embodiment, the extracting module 940 may be configured to perform the operation S240 described above, which is not described herein.

According to an embodiment of the present disclosure, any of the plurality of modules of the first determining module 910, the second determining module 920, the grouping module 930, and the extracting module 940 may be combined in one module to be implemented, or any of the plurality of modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the first determination module 910, the second determination module 920, the grouping module 930, and the extraction module 940 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging the circuitry, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, at least one of the first determination module 910, the second determination module 920, the grouping module 930, and the extraction module 940 may be at least partially implemented as computer program modules, which when executed, may perform the respective functions.

As shown in fig. 10, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1002 or a program loaded from a storage section 1008 into a Random Access Memory (RAM) 1003. The processor 1001 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 1001 may also include on-board memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flows according to embodiments of the present disclosure.

In the RAM 1003, various programs and data necessary for the operation of the electronic apparatus 1000 are stored. The processor 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. The processor 1001 performs various operations of the method flow according to the embodiment of the present disclosure by executing programs in the ROM 1002 and/or the RAM 1003. Note that the program may be stored in one or more memories other than the ROM 1002 and the RAM 1003. The processor 1001 may also perform various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the disclosure, the electronic device 1000 may also include an input/output (I/O) interface 1005, the input/output (I/O) interface 1005 also being connected to the bus 1004. The electronic device 1000 may also include one or more of the following components connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output portion 1007 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage portion 1008 including a hard disk or the like; and a communication section 1009 including a network interface card such as a LAN card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The drive 1010 is also connected to the I/O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is installed as needed in the drive 1010, so that a computer program read out therefrom is installed as needed in the storage section 1008.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium described above carries one or more programs that, when executed, implement the expert extraction method according to the embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 1002 and/or RAM 1003 and/or one or more memories other than ROM 1002 and RAM 1003 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code, when executed in a computer system, causes the computer system to implement the expert extraction method provided by embodiments of the present disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 1001. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted in the form of signals on a network medium, distributed, and downloaded and installed via the communication section 1009, and/or installed from the removable medium 1011. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 1009, and/or installed from the removable medium 1011. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 1001. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. An expert extraction method, comprising:

determining a target expert database;

determining expert correlation characteristics;

Clustering and grouping the target expert database according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub-expert groups;

extracting an expert from each sub expert group respectively to obtain a target expert group;

the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold.

2. The method of claim 1, wherein clustering the target expert pool according to the number of required experts and the expert correlation feature to obtain a plurality of sub-expert groups comprises:

quantifying the expert correlation characteristics to obtain a plurality of coordinate points; and

and clustering and grouping the coordinate points by adopting a Kmeans algorithm according to the number of required experts to obtain the sub-expert groups.

3. The method of claim 2, wherein the expert correlation feature comprises a current work address and/or address, and wherein quantifying the expert correlation feature to obtain a plurality of coordinate points comprises:

mapping longitude and latitude coordinates of the current working address and/or address to a multidimensional coordinate space to obtain a plurality of coordinate points;

the multidimensional coordinate space comprises a plurality of coordinate axes, and the coordinate axes are in one-to-one correspondence with the expert correlation features.

4. A method according to claim 3, wherein the expert correlation feature further comprises a learning experience and/or a work experience, and wherein quantifying the expert correlation feature to obtain a plurality of coordinate points further comprises:

and mapping longitude and latitude coordinates of the school address and/or the historical working address to a multidimensional coordinate space to obtain the coordinate points.

5. The method of claim 3, wherein the expert correlation feature further comprises an age and/or a gender, and wherein quantifying the expert correlation feature to obtain a plurality of coordinate points further comprises:

mapping the age and/or sex to a multidimensional coordinate space to obtain a plurality of coordinate points;

wherein, the coordinate axis scales corresponding to the gender are male and female.

6. The method of claim 1, wherein extracting an expert from each of the sub-expert groups, respectively, to obtain a target expert group comprises:

randomly sequencing the experts in each sub expert group to obtain a plurality of random expert sequences;

extracting an expert from each random expert sequence to obtain the target expert group;

wherein extracting an expert from a single said random expert sequence comprises:

And sequentially extracting the experts according to the random expert sequence order according to the expert participation wish.

7. The method of claim 2, wherein clustering the target expert pool according to the number of required experts and the expert correlation feature to obtain a plurality of sub-expert groups further comprises:

clustering and grouping the coordinate points by adopting a Kmeans algorithm according to the preset expert number to obtain a plurality of sub-expert groups;

wherein the preset number of experts is greater than the required number of experts.

8. An expert extraction device, comprising:

the first determining module is used for determining a target expert database;

the second determining module is used for determining expert correlation characteristics;

the grouping module is used for clustering and grouping the target expert database according to the number of required experts and the expert correlation characteristics to obtain a plurality of sub-expert groups; and

the extraction module is used for extracting one expert from each sub expert group respectively to obtain a target expert group; the distance between the clustering centers of any two sub-expert groups is larger than a preset threshold.

9. An electronic device, comprising:

One or more processors;

storage means for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.

10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-7.

11. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.