CN116628214A

CN116628214A - Information display method and device, readable storage medium and electronic equipment

Info

Publication number: CN116628214A
Application number: CN202310140495.7A
Authority: CN
Inventors: 李坤; 魏旺旺; 王佳玮; 金雄男; 杨倩; 段曼妮; 王永恒; 傅四维
Original assignee: Zhejiang Lab
Current assignee: Zhejiang Lab
Priority date: 2023-02-08
Filing date: 2023-02-08
Publication date: 2023-08-22

Abstract

The specification discloses an information display method, an information display device, a readable storage medium and electronic equipment, wherein for each enterprise, each label of the enterprise is determined according to enterprise information of the enterprise, and after each label corresponding to each enterprise is determined, each enterprise is clustered according to each label. And determining the enterprise type of each enterprise of the cluster according to the label of at least one enterprise contained in the cluster aiming at each cluster in the cluster result, and further determining the portrait information corresponding to each enterprise according to each label and enterprise type corresponding to each enterprise. And displaying portrait information determined according to each label and the enterprise type. The method determines the enterprise type of the enterprise based on each label of the enterprise, displays the enterprise type and each label as portrait information of the enterprise, and compared with portrait information only containing each label, the portrait information determined by the method is more accurate, contains more information, and ensures the accuracy of display information.

Description

Information display method and device, readable storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an information display method and apparatus, a readable storage medium, and an electronic device.

Background

At present, with the development of internet technology and the development of enterprise management systems, how to integrate enterprise portraits and display the enterprise portraits so as to realize effective supervision of enterprises has become one of the problems to be solved by related departments.

One common method for integrating image information of an enterprise is based on marking the enterprise. Specifically, first, enterprise information of an enterprise can be obtained from each platform. And then determining each label corresponding to the enterprise according to the acquired enterprise information. The label can be a label for representing the industry where the enterprise is located, and can also be a label for representing the business risk of the enterprise. And finally, taking the determined label corresponding to the enterprise as the enterprise image information.

However, the method used when integrating the enterprise portrait information is only to use the determined labels as the portrait information of the enterprise, so that the determined enterprise portrait information is not accurate enough, and further the enterprise cannot be effectively supervised based on the enterprise portrait information.

Disclosure of Invention

The present disclosure provides an information display method, an information display device, a readable storage medium, and an electronic apparatus, so as to partially solve the foregoing problems in the prior art.

The technical scheme adopted in the specification is as follows:

the specification provides an information display method, which comprises the following steps:

for each enterprise, determining enterprise information of the enterprise according to the acquired enterprise identification of the enterprise;

identifying the enterprise information and determining each label of the enterprise;

clustering the enterprises according to the labels corresponding to the enterprises respectively;

for each cluster obtained by clustering, determining the enterprise type of each enterprise of the cluster according to the label of at least one enterprise contained in the cluster;

determining portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and each label corresponding to each enterprise;

when a display request is received, determining and displaying portrait information of a designated enterprise matched with a designated identifier from portrait information of each enterprise stored in advance according to the designated identifier carried in the display request.

Optionally, determining the enterprise type of each enterprise of the cluster according to the label of at least one enterprise contained in the cluster specifically includes:

Determining an enterprise corresponding to a clustering center of each cluster in the clustering result as a characterization enterprise of the cluster;

determining the enterprise type of the characterization enterprise of the cluster according to each label of the characterization enterprise of the cluster;

and taking the enterprise type of the cluster, which characterizes the enterprise, as the enterprise type of each enterprise of the cluster.

Optionally, the tag includes an entity tag and a non-entity tag, the entity tag including at least one of a user name and a business name;

according to the enterprise types and the labels respectively corresponding to the enterprises, the portrait information respectively corresponding to the enterprises is determined, and the method specifically comprises the following steps:

for each enterprise, determining the association relationship between each label of the enterprise and the enterprise;

establishing a knowledge graph taking enterprises and labels as nodes according to the enterprises, the labels respectively corresponding to the enterprises and the association relations between the labels and the enterprises, wherein edges between the nodes in the knowledge graph are used for representing the association relations between two nodes connected with the edges in the knowledge graph;

Determining at least part of knowledge maps corresponding to each enterprise from the knowledge maps;

and determining portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and at least part of the knowledge graph corresponding to each enterprise.

Optionally, for each enterprise, the number of enterprise identities of the enterprise is a plurality;

establishing a knowledge graph taking enterprises and labels as nodes, which specifically comprises the following steps:

establishing an initial map taking enterprise identifications and labels as nodes;

for each enterprise, determining nodes corresponding to the enterprise identifications of the enterprise from the initial map as specific nodes according to the enterprise identifications of the enterprise;

and fusing the specific nodes, and updating the initial map according to the fusion result to obtain a knowledge map.

Optionally, determining the portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and at least part of the knowledge graph corresponding to each enterprise, which specifically includes:

for each enterprise, determining neighbor nodes adjacent to the node corresponding to the enterprise from the knowledge graph;

Determining influence of the enterprise according to the neighbor nodes;

and determining portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise, at least part of the knowledge graph corresponding to each enterprise and the influence degree corresponding to each enterprise.

Optionally, determining the influence degree of the enterprise according to the neighboring nodes specifically includes:

determining the number of nodes connected by the neighbor node in the knowledge graph as a specific number for each neighbor node, and determining the influence degree of the neighbor node;

and determining the influence degree of the enterprise according to the influence degree of each neighbor node, the specific number of each neighbor node and the weight of the edge between each neighbor node and the node corresponding to the enterprise.

Optionally, the enterprise information comprises at least one of structured information and unstructured information related to the enterprise;

identifying the enterprise information and determining each label of the enterprise, wherein the method specifically comprises the following steps:

performing entity word recognition on the enterprise information, and determining each entity word contained in the enterprise information;

And determining a specific entity word as a label of the enterprise from the entity words.

The present specification provides an information display apparatus including:

the information determining module is used for determining enterprise information of each enterprise according to the acquired enterprise identification of the enterprise;

the identification module is used for identifying the enterprise information and determining each label of the enterprise;

the clustering module is used for clustering the enterprises according to the labels respectively corresponding to the enterprises;

the type determining module is used for determining the enterprise type of each enterprise of each cluster according to the label of at least one enterprise contained in each cluster;

the portrait determining module is used for determining portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and each label corresponding to each enterprise;

and the updating module is used for determining the portrait information of the appointed enterprises matched with the appointed identification from the prestored portrait information of each enterprise according to the appointed identification carried in the display request when the display request is received, and displaying the portrait information.

Optionally, the type determining module is configured to determine, for each cluster in the clustering result, an enterprise corresponding to a cluster center of the cluster, as a characterizing enterprise of the cluster, determine, according to each tag of the characterizing enterprise of the cluster, an enterprise type of the characterizing enterprise of the cluster, and take the enterprise type of the characterizing enterprise of the cluster as an enterprise type of each enterprise of the cluster.

the portrait determining module is configured to determine, for each enterprise, an association relationship between each label of the enterprise and the enterprise, establish a knowledge graph with the enterprise and the label as nodes according to the enterprise, each label corresponding to each enterprise, and the association relationship corresponding to each label and each enterprise, wherein an edge between the nodes in the knowledge graph is used for characterizing the association relationship between two nodes connected with the edge in the knowledge graph, determine, from the knowledge graph, at least part of the knowledge graph corresponding to each enterprise, and determine portrait information corresponding to each enterprise according to an enterprise type corresponding to each enterprise and at least part of the knowledge graph corresponding to each enterprise.

the portrait determining module is used for establishing an initial map taking enterprise identifications and labels as nodes, determining the nodes corresponding to the enterprise identifications of each enterprise from the initial map according to the enterprise identifications of each enterprise as specific nodes, fusing the specific nodes, and updating the initial map according to fusion results to obtain a knowledge map.

Optionally, the portrait determining module is configured to determine, for each enterprise, a neighboring node adjacent to a node corresponding to the enterprise from the knowledge graph, determine, according to the neighboring nodes, an influence degree of the enterprise, and determine, according to the enterprise type corresponding to each enterprise, at least a part of the knowledge graph corresponding to each enterprise, and the influence degree corresponding to each enterprise, portrait information corresponding to each enterprise.

Optionally, the portrayal determining module is configured to determine, for each neighboring node, the number of nodes connected by the neighboring node in the knowledge graph as a specific number, and determine the influence degree of the neighboring node, and determine the influence degree of the enterprise according to the influence degree of each neighboring node, the specific number of each neighboring node, and the weight of the edge between each neighboring node and the node corresponding to the enterprise.

the identification module is used for carrying out entity word identification on the enterprise information, determining each entity word contained in the enterprise information, and determining a specific entity word from the entity words as a label of the enterprise.

The present specification provides a computer readable storage medium storing a computer program which when executed by a processor implements any of the above-described information presentation methods.

The electronic device provided in the present specification includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements any of the above information presentation methods when executing the program.

The above-mentioned at least one technical scheme that this specification adopted can reach following beneficial effect:

in the information display method provided by the specification, for each enterprise, each label of the enterprise is determined according to the enterprise information of the enterprise, after each label corresponding to each enterprise is determined, each enterprise is clustered according to each label, then for each cluster in a clustering result, the enterprise type of each enterprise of the cluster is determined according to the label of at least one enterprise contained in the cluster, and further, the portrait information corresponding to each enterprise is determined according to each label and the enterprise type corresponding to each enterprise, so that portrait information containing each label and each enterprise type can be displayed when a display request is received.

According to the method, based on the fact that the labels corresponding to the enterprises are determined, the enterprise types corresponding to the enterprises are determined, and the portrait information determined according to the enterprise types and the labels is displayed.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification, illustrate and explain the exemplary embodiments of the present specification and their description, are not intended to limit the specification unduly. Attached at

In the figure:

fig. 1 is a schematic flow chart of an information display method provided in the present specification;

FIG. 2 is a schematic diagram of a knowledge graph provided in the present specification;

FIG. 3 is a schematic flow chart of determining enterprise portrait information provided in the present specification;

FIG. 4 is a schematic view of the enterprise ontology provided in the present specification;

FIG. 5 is a block diagram of an enterprise portrait provided in the present specification;

fig. 6 is a schematic diagram of determining the influence degree corresponding to the preset step length of the node provided in the present disclosure;

fig. 7 is a schematic structural diagram of an information display device provided in the present specification;

Fig. 8 is a schematic view of the electronic device corresponding to fig. 1 provided in the present specification.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.

The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.

At present, when displaying portrait information of an enterprise, the problem exists that the portrait information is not accurate enough when the label of the identified enterprise is directly used as the portrait information of the enterprise. Based on the above, the present specification provides an information display method, in which, for each enterprise, after each label corresponding to the enterprise is determined, the enterprise type of the enterprise is determined, and then each label and the enterprise type are used as portrait information of the enterprise, and the portrait information is displayed when the display is required. Thus, the displayed portrait information contains the labels of enterprises and the types of enterprises, and the portrait information contains more information and is more accurate.

Fig. 1 is a flow chart of an information display method provided in the present specification, specifically including the following steps:

s100: for each enterprise, determining enterprise information of the enterprise according to the acquired enterprise identification of the enterprise.

In the field of information display, particularly in the field of displaying enterprise information, it is generally required to acquire portrait information corresponding to an enterprise and display the portrait information to a user. Based on the above brief description of the information display method provided in the present specification, the information display method needs to determine the type of the enterprise based on each label of the enterprise after determining each label corresponding to the enterprise, so as to determine the portrait information of the enterprise. Also, because the tags of the business may generally be determined based on the business information, the business information of the business may be determined first, and the tags of the business may be determined based on the business information.

In one or more embodiments provided herein, the information presentation method may be performed by a server.

Specifically, the server may first determine the business that needs to generate the portrait information. The server can store a list corresponding to enterprises which orderly generate portrait information in advance, and when portrait information needs to be generated, the server determines enterprise identifications corresponding to the enterprises according to the pre-stored list. Of course, the server may also receive a portrayal generation request, where the portrayal generation request carries an enterprise identifier of an enterprise for which portrayal information needs to be generated. The present specification is not limited to how the enterprise to generate the portrait information determines and can set the enterprise as required.

After determining the enterprise needing to generate the portrait information, the server can determine the enterprise information of each enterprise needing to generate the portrait information according to the enterprise identifier of the enterprise.

The server can also store enterprise information of a plurality of enterprises, and when the enterprise information needs to be determined, the enterprise information of the enterprise corresponding to the enterprise identifier is determined from the prestored enterprise information corresponding to each enterprise respectively according to the enterprise identifier. The server can also query information corresponding to the enterprise from a network platform in the Internet according to the enterprise identifier. The enterprise identifier may be an enterprise name or a unique identifier assigned to the enterprise. Taking the server storing the enterprise information corresponding to the enterprise as an example, if the server allocates an ID corresponding to each enterprise, assuming that the ID of the enterprise a is 3, the 3 may be the enterprise identifier of the enterprise a.

S102: and identifying the enterprise information and determining each label of the enterprise.

In one or more embodiments provided herein, after determining the enterprise information, the terminal needs to determine each tag of the enterprise according to the enterprise information, and may then determine portrait information of the enterprise based on each tag. Thus, the server may identify the acquired business information and determine the labels of the business.

Specifically, the obtained enterprise information contains at least one of structured information and unstructured information.

The structured information can be identified and stored by using a relational database, and the data can be realized by using a two-dimensional table to logically express. For enterprises, the structured data corresponding to the enterprises can be English holly names of the enterprises, whether the enterprises are logged out, legal persons of the enterprises, the enterprise scale, the region where the enterprises are located, the enterprise credit level, the enterprise operating range, the enterprise personnel growth rate and other basic information of the enterprises, the stakeholder names of the enterprises, the stakeholders occupying the strands in the enterprises and other stakeholders of the enterprises, and the total annual income value of the enterprises, the main business income, the fixed asset depreciation and other financial information of the enterprises, and of course, the structured information can also be practitioner conditions, intellectual property conditions, scientific research conditions and the like, and the type of information contained in the structured information, how to determine and the like can be set according to requirements, so that the structured data is not limited in the specification.

The unstructured information is data without a fixed structure, corresponding to the structured information. For an enterprise, unstructured information corresponding to the enterprise may be various information such as comments of staff or masses to the enterprise, self-introduction of the enterprise, news stories related to the enterprise, and the like. The content and how to determine the unstructured information of the enterprise can be set according to the needs, and the specification is not limited to this.

After determining the enterprise information corresponding to the enterprise, the server can segment the enterprise information, determine each word, and determine each entity word contained in the enterprise information according to the part of speech of each word. And then the server determines specific entity words corresponding to the specific types from the determined entity words according to the preset specific types, and the specific entity words are used as labels of the enterprise.

If the enterprise information is structured information, the enterprise information may include a plurality of data stored in the form of key-value pairs. For each key-value pair, the value in the key-value pair may be an entity word, and the key in the key-value pair may be a correspondence between the entity word and the business. Thus, the server may divide the business information into keys and values, and the server may use the values as labels for the business information. As shown in table 1.

Legal person	A	At the site	China
				Contact telephone	123	Enterprise asset	10000

TABLE 1

Table 1 is a schematic representation of the business information provided in this specification. Taking the name of the enterprise as an example, assume that the legal person of the enterprise is a, the location of the enterprise is china, the contact phone of the enterprise is 123, and the asset of the enterprise is 10000. The legal person and a may be a key-value pair, the legal person is a key, and a is a value. The server may segment the structured information to obtain legal person, a, location, china, contact phone, 123, enterprise asset, 10000. And then determining each specific entity word from the entity words according to the preset specific type. Taking a preset specific type as a place as an example, assume that the matching format of the place is as follows: the last word is the entity word of the "country" word, and the server can determine the entity word of the last word as the "country" word from the entity words according to the matching format corresponding to the specific type: china, as a labeling of the enterprise D. Of course, the table and the representation of the key value pair are merely examples, and the specific form of the enterprise information may be set according to the need, which is not limited in this specification.

If the enterprise information is unstructured information, taking unstructured information as user comments as an example, and assuming that the user comments on the D enterprise are' the subsidiary company of the B enterprise, the user comments take the effect of cooling by leaning against the big tree, and the user comments are recommended. The server may segment the enterprise information to obtain: this is, B enterprise, subsidiary, back big tree, good, cool, recommended, go. The server may determine each entity word according to the part of speech corresponding to each word: enterprise B, subsidiary. If the preset specific type is other enterprises related to the enterprise, the matching format is as follows: the last two words are entity words of "business", then the server may determine a specific entity word from the entity words according to the matching format: and B, taking the enterprise as a label of the D enterprise.

S104: and clustering the enterprises according to the labels respectively corresponding to the enterprises.

In one or more embodiments provided herein, if tags of some businesses are relatively close, then the corresponding business types of those businesses may be the same type. Likewise, if the gap between labels of some enterprises is large, the enterprise types corresponding to the enterprises may be different types. Based on the above point of view, if each enterprise is clustered according to the label, it can be quickly determined whether each enterprise is of the same type. Based on this, after determining each tag of the enterprise, the server may determine the type of enterprise corresponding to the enterprise based on each tag.

Specifically, the server may determine a specified number of tags from among the tags as the tags for clustering.

Then, for each tag used for clustering, the server may encode the tag, determining the feature to which the tag corresponds. For discrete ID type tags such as user names and business names, the server may use a single-hot encoding rule To encode the discrete ID type tags, and for text type tags, the server may use a Word Vector embedded representation (Word To Vector, word2 Vec) encoding rule To encode the discrete ID type tags. The type corresponding to the specific tag and the coding rule corresponding to each type can be set according to the needs, and the specification does not limit the type.

Then, for each enterprise, the server can determine the label corresponding to the enterprise and used for clustering, and fuse the characteristics corresponding to the labels respectively used for clustering, so as to determine the fusion characteristics corresponding to the enterprise.

Finally, the server can cluster the fusion features to determine a clustering result. Since clustering according to features is already a mature technology at present, the description is not repeated here.

In addition, the server can also determine the labels for clustering by adopting a plurality of algorithms such as a recursive feature elimination method, a feature elimination method and the like, and particularly how to determine the labels for clustering can be set according to the needs, and the specification does not limit the labels.

S106: and determining the enterprise type of each enterprise of each cluster according to the label of at least one enterprise contained in the cluster aiming at each cluster obtained by clustering.

In one or more embodiments provided herein, after clustering is completed, the server may determine the relationship between enterprises, but it is not known what type of enterprise is specifically characterized by each cluster in the clustering result. Therefore, if the type of the enterprise corresponding to each enterprise is to be determined, the determination is also performed according to the tags of the enterprises. For each cluster, each enterprise corresponding to the cluster is an enterprise of the same enterprise type, so that the enterprise type of each enterprise in the cluster can be determined as long as the enterprise type corresponding to one enterprise in the cluster is determined. Based on this, the server may determine, for each cluster included in the cluster result, a type of business of each business of the cluster according to a label of at least one business included in the cluster.

Specifically, the server may randomly select, for each cluster in the cluster result, any enterprise from the enterprises included in the cluster, as a characterizing enterprise of the cluster.

Then, a correspondence between the tags preset in the server and the type of business is obtained. The server may match each tag of the characterizing enterprise with each preset correspondence, and determine an enterprise type matching the tag of the characterizing enterprise as the enterprise type of the characterizing enterprise.

The corresponding relation between the label Chinese and the enterprise type local company is preset in the server. Assuming that the determined characterized enterprise is enterprise D and the label corresponding to enterprise D is "china", the server may determine that enterprise D is "china enterprise".

Finally, the server may treat the enterprise type characterizing the enterprise as the enterprise type of each enterprise of the cluster. Wherein the label for determining the enterprise type of the characterized enterprise is one of labels for clustering.

S108: and determining portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and each label corresponding to each enterprise.

S110: when a display request is received, determining and displaying portrait information of a designated enterprise matched with a designated identifier from portrait information of each enterprise stored in advance according to the designated identifier carried in the display request.

In one or more embodiments provided herein, as described above, the information displaying method in the present specification may determine the type of enterprise and each tag of the enterprise as portrait information of the enterprise, and then directly display portrait information including the type of enterprise and the tag of the enterprise when the display is required. Compared with the mode of directly taking the label of the enterprise as the image information, the image information determined in the specification contains more information, and the accuracy is higher.

Specifically, for each enterprise, the server may determine each label of the enterprise, and the type of enterprise corresponding to the enterprise. Wherein, each label of the enterprise is each label determined in step S102, and the enterprise type is the enterprise type determined in step S106.

The server may then store each tag of the enterprise and the enterprise type of the enterprise as portrayal information for the enterprise.

After storing the image information corresponding to each enterprise, the server may receive the display request. The display request carries a designated identifier, and the designated identifier is an enterprise identifier of an enterprise needing to display portrait information.

The server can analyze the display request, determine the designated identifier carried in the display request, determine the portrait information of the enterprise matched with the designated identifier from the portrait information respectively corresponding to the enterprises stored in advance according to the designated identifier, and display the determined portrait information.

When the server displays the portrait information of the enterprise, the display form of the portrait information can be in various forms such as a list form, a graph form and the like, and the present specification does not limit how to display the portrait information according to needs.

Based on the information display method of fig. 1, for each enterprise, each label of the enterprise is determined according to the enterprise information of the enterprise, after each label corresponding to each enterprise is determined, each enterprise is clustered according to each label, then for each cluster in the clustering result, the enterprise type of each enterprise of the cluster is determined according to the label of at least one enterprise contained in the cluster, and further, the portrait information corresponding to each enterprise is determined according to each label and the enterprise type corresponding to each enterprise, so that when a display request is received, portrait information containing each label and each portrait information of each enterprise type can be displayed.

According to the method, based on the fact that the labels corresponding to the enterprises are determined, the enterprise types and the labels are displayed as the portrait information of the enterprises, and compared with the portrait information only containing the labels, the portrait information determined by the method is more accurate, contains more information, and ensures the accuracy of displayed information.

In addition, the dimension of the features determined in the encoding process is more, so that more calculation resources are required when clustering is performed based on the features. Therefore, in step S104, in addition to encoding each label, the server may also determine the enterprise feature corresponding to each enterprise by directly quantifying each label.

Specifically, for each tag type of tag, the corresponding relationship between each tag and its quantized value may be preset in the server.

The server may determine, for each tag of the enterprise, a tag type corresponding to the tag according to the tag, and then determine a quantized value corresponding to the tag from a correspondence between the tag and its quantized value.

Taking a tag as a large company as an example, the server can determine that the type corresponding to the tag is an enterprise scale according to the tag, and determine the quantized value corresponding to the large company as the quantized value of the tag according to the corresponding relationship between each tag corresponding to the enterprise scale and the quantized value thereof.

Taking the tag as an example of "a", the server can determine that the type corresponding to the tag is "enterprise legal person" according to the tag a, and determine the quantized value corresponding to "enterprise legal person" as the quantized value of the tag according to the corresponding relationship between each tag corresponding to "enterprise legal person" and the quantized value thereof. The quantized value corresponding to the corporate legal person can be determined for the number of companies under the legal person, or can be determined for fixed assets according to the legal person. The specific content and number of tag types and the correspondence between each tag and its quantization value may be set as needed, which is not limited in this specification.

Finally, the server can directly take each label as each dimension, and determine the enterprise characteristics of the enterprise according to the quantized values corresponding to each label.

After the enterprise characteristics are determined, the server can cluster each enterprise according to the enterprise characteristics corresponding to each enterprise according to a plurality of clustering algorithms such as a k-meas clustering algorithm, a mean shift clustering algorithm and the like. The clustering algorithm adopted when the enterprise features are clustered can be set according to the needs, and the specification does not limit the clustering algorithm.

Furthermore, in the process of clustering enterprises by using the k-meas clustering algorithm, in order to avoid the situation that the initial clustering centers are too aggregated, the clustering result is not accurate enough, or more iterations are needed to obtain an accurate clustering effect. The server can determine an initial clustering center according to the densities respectively corresponding to the enterprise features, and then cluster the enterprise features according to the initial clustering center, so that the aim of rapidly determining an accurate clustering result is fulfilled.

Specifically, the server may determine, for each enterprise, a distance between the enterprise characteristics of each other enterprise and the enterprise characteristics of the enterprise according to the enterprise characteristics corresponding to each enterprise. And determining an average distance based on the distances between the enterprise features. For each enterprise feature, taking the example that the enterprise feature contains n dimensions, the enterprise feature can be characterized as (x) ₁ ,……，x _i ，……x _n ) Characterised by another enterprise feature (y ₁ ,……，y _i ，……y _n ) For example, the distance between the two enterprise features may be determined asAfter determining the distance between the enterprise features, the server may determine an average distance: />Wherein G is the total number of enterprise features, +.>For characterizing G x (G-1), and Σd (x, y) for characterizing the distance that adds the distances between the determined business features.

Next, for each enterprise, centering on the enterprise feature corresponding to the enterprise, determining that the distance from the enterprise feature does not exceed the average, and centering on the average distance as a radiusEnterprise characteristics of distances as specified characteristics. And determining the number of the specified features as the densities corresponding to the enterprise features. And sorting the enterprise features according to the densities respectively corresponding to the enterprise features to obtain a first sorting result. At p _i For example, the density of the characteristic of the enterprise is represented by p _i The determination may be based on the number of other enterprise features contained within a circle centered on the enterprise feature and determined by the average distance as a radius.

The server may then determine, for each enterprise feature, an enterprise feature having a smallest distance from the node from among the enterprise features having a density greater than the enterprise feature density, based on the density of the enterprise feature and the densities of other enterprise features, as a target feature. And determining the distance between the enterprise feature and the target feature, and sorting the enterprise features according to the distance to obtain a second sorting result. Delta _i Characterizing the distance as an example, for an ith enterprise feature, the target feature corresponding to the enterprise feature may be Wherein p is _i For the density of the enterprise feature->For characterizing an enterprise feature having a density greater than the enterprise feature from among the other enterprise features. Thus (S)> May be used to characterize the target feature to which the enterprise feature corresponds. The server may determine the distance between the enterprise feature and the target feature after determining the target feature.

And finally, selecting a designated number of enterprise features as an initial clustering center according to the first sorting result and the second sorting result.

For the most dense enterprises, the method is specific toSign, its corresponding target feature is not present, so the distance between the enterprise feature with the greatest density and its corresponding target feature can be defined as delta _i ＝max _j (d (i, j)). Where i is used to characterize the most dense enterprise feature. That is, the maximum distance is selected from the distances corresponding to the enterprise features having the maximum density and the other enterprise features, respectively, and is used as the distance between the enterprise feature having the maximum density and the corresponding target feature.

Further, for each cluster, the feature of the cluster center of the cluster may be the feature that best characterizes the cluster characteristics. Based on the same thought, the enterprise corresponding to the cluster center of the cluster is the enterprise which can most ensure the enterprise type of the cluster. Therefore, in step S106, when determining the characterization feature, the server may directly use the enterprise corresponding to the cluster center as the characterization enterprise.

Further, the server may be preset with a correspondence between the tag and the type of the enterprise, but in the case that the enterprise includes a plurality of tags, a situation that one enterprise corresponds to a plurality of types of enterprises may also occur. In this specification, a cluster generally corresponds to only one type of business. Therefore, in step S106, the preset correspondence in the server may be a correspondence between a plurality of different types of labels and one enterprise type.

Taking the label type as an enterprise scale and the innovation industry proportion as an example, assuming that the labels are large companies and the proportion of the labels is more than 50 percent, and correspond to large high-new technology enterprises, the labels are small companies and the proportion of the labels is more than 50 percent, correspond to small high-new technology enterprises, the labels are large companies and the proportion of the labels is less than 50 percent, correspond to large low-end technology enterprises, and the labels are small companies and the proportion of the labels is less than 50 percent, correspond to small low-end technology enterprises. If the tags characterizing the business are "small businesses" and "over 50%", then the business type characterizing the business may be determined to be a small high-tech business.

Of course, the specific correspondence relationship, the number of tags in the correspondence relationship, and the like may be set as needed, which is not limited in this specification.

In addition, in order to avoid the situation that when the graph formed by each enterprise in the cluster is annular, the cluster corresponding to the cluster center cannot be determined, the server can also randomly select a specified number of enterprises from the enterprises contained in the cluster, and the enterprises are respectively used as characterization enterprises. And averaging the characteristics of each characterization enterprise to obtain average characteristics, and finally, taking the enterprise type of the enterprise corresponding to the determined average characteristics as the enterprise type of the cluster. The enterprise corresponding to the average feature is the enterprise corresponding to the feature closest to the average feature distance. The distance can be measured in a plurality of modes such as Euclidean distance, cosine distance, vector product and the like, and can be specifically set according to the needs, and the distance is not limited in the specification.

Furthermore, compared with the list form for representing the portrait information of the enterprises, the knowledge graph is more visual for representing the portrait information of the enterprises, and the knowledge graph can also represent the association relationship among the enterprises. Therefore, in step S108, the determined image information may be in the form of a knowledge graph.

Specifically, the server may determine, for each enterprise, an association relationship between each tag of the enterprise and the enterprise.

Then, the service can determine each node in the knowledge graph according to each determined enterprise and each label corresponding to each enterprise. And connecting the nodes corresponding to the labels in the knowledge graph with the nodes of the enterprises corresponding to the labels according to the association relation between the labels and the enterprises corresponding to the labels, and determining the edges in the knowledge graph. Thus, a knowledge graph except for enterprises and labels is constructed. The constructed knowledge graph comprises nodes corresponding to enterprises, nodes corresponding to labels and edges among the nodes. The edges between the nodes in the knowledge graph are used for representing the association relationship between two nodes connected with the edges in the knowledge graph. Take fig. 2 as an example.

Fig. 2 is a schematic diagram of a knowledge graph provided in the present specification. Wherein, the black dots represent the nodes corresponding to enterprises, and the black dots represent the nodes corresponding to enterprises in the graphIn C ₁ 、C ₂ 、C ₃ Three businesses are shown as examples. White dots represent nodes corresponding to labels, and u is used in the figure ₁ 、u ₂ 、u ₃ 、u ₄ Four labels are shown as examples. r is used for representing the association relation between the nodes.

Thus, after determining the knowledge-graph, the server may determine, for each enterprise, at least a portion of the knowledge-graph corresponding to the enterprise from the knowledge-graph. When the portrait information is required to be displayed later, the server can directly display the enterprise type and at least part of the knowledge graph corresponding to the enterprise as the portrait information.

Further, for each enterprise, the enterprise may correspond to a different enterprise name in a different network platform. For example, the name of an enterprise A on an x platform is an enterprise A, the name of an enterprise A on a y platform is an development company A, and the name of an enterprise A on a z platform is an A finite liability company. The a-business corresponds to three names. In the process of building the knowledge graph, generally speaking, the node corresponding to the enterprise is the node corresponding to the enterprise name. The enterprise a corresponds to the nodes corresponding to the three enterprises in the knowledge graph, which results in inaccurate portrait information of the determined enterprise a. Thus, the server may fuse, for each enterprise, the nodes corresponding to the enterprise names of the enterprise.

Specifically, the server may establish an initial map using the enterprise identifier and the label as nodes according to the enterprise identifier corresponding to each enterprise, the label corresponding to each enterprise, the association relationship between each label and each enterprise, and the like.

Then, the server may determine, for each enterprise, from the initial map, a node corresponding to each enterprise identifier of the enterprise, as each specific node, according to each enterprise identifier corresponding to the enterprise.

Finally, the server may fuse each specific node, i.e., fuse each specific node into one node. The server may then determine each neighboring node in the initial graph that is connected to each particular node, and construct an edge between each particular node and each neighboring node after the fusing of each particular node based on the edge between each neighboring node and each particular node. And updating the initial map according to the fusion result, and taking the updated result as a knowledge map.

In one or more embodiments provided herein, the present disclosure also provides a method for determining enterprise portrait information, as illustrated in fig. 3.

Fig. 3 is a schematic flow chart of determining enterprise portrait information provided in the present specification, where the server may first determine an enterprise identifier, then obtain enterprise information according to the enterprise identifier, and further determine each tag of an enterprise corresponding to the enterprise identifier according to the determined enterprise information. Then, the server can determine an initial map taking the enterprise name and the label as nodes according to the determined labels of the enterprises corresponding to the enterprise identifiers respectively, and then fuse the nodes corresponding to different enterprise names of the same enterprise in the knowledge map according to different enterprise names belonging to the same enterprise to obtain the knowledge map. Meanwhile, the server can cluster each enterprise based on the labels corresponding to each enterprise respectively, and determine the enterprise types corresponding to each enterprise respectively based on the clustering result. Finally, the server can display the enterprise type corresponding to the enterprise and the subgraph of the enterprise in the knowledge graph when the portrait information of the enterprise is required to be displayed. Based on the mode, compared with the enterprise portrait information determined only based on the structural information, the determined enterprise portrait information is richer in information and more visual in display effect.

Further, in step S102, when determining the label corresponding to the business, the label corresponding to the business may be other data such as a range matching the specific entity word in addition to the specific entity word. Thus, the server may also determine the enterprise data as a label for the enterprise.

Specifically, the server may be preset with a matching rule between the tag and a specific entity word. Then, for each specific entity word, the server may determine, from the preset matching rules and the specific entity word, a matching rule corresponding to the specific entity word, and use a label corresponding to the matching rule as a label corresponding to the entity word.

Taking the enterprise information as an example containing 120 persons of staff, if the specific type is "staff number", the server can determine that the specific entity word is 120 persons. If the matching rules of 'the number of staff exceeds 100' and 'large enterprises' and the matching rules of 'the number of staff is less than 100' and 'small enterprises' are preset in the server. The server can determine that the matching rules of 'staff number more than 100' and 'large enterprise' are the matching rules corresponding to the specific entity word from the preset matching rules according to the specific entity word, and take the 'large enterprise' as the label corresponding to the enterprise.

Further, in addition to entity words, the labels corresponding to the enterprises may also be non-entity words. Taking the business scope of the enterprise as "design, release and proxy domestic advertisement service" as an example, it is obvious that the design, release and proxy domestic advertisement service is not an entity word, but is one of the basic information of the enterprise. Therefore, if the non-entity tag is other attribute information than the tag corresponding to the entity word in the business related information such as the basic information, the stock right information, the financial information, the practitioner's situation, the intellectual property information, etc. corresponding to the business, the server can extract the attribute word from the business information.

Specifically, the server may input the enterprise information as input, and input the attribute recognition model trained in advance, so as to obtain the attribute word corresponding to the enterprise output by the attribute recognition model, and use the attribute word as the non-entity tag corresponding to the enterprise. Wherein for each non-entity tag, the non-entity tag is an attribute word, which may be a word used to describe the business.

The attribute identification model can be trained by the following modes:

a number of enterprise information is determined as each training sample. And labeling attribute words contained in each training sample manually aiming at each training sample, and taking the attribute words as labels of the training samples. And inputting each training sample into the attribute recognition model to be trained to obtain each attribute word output by the attribute recognition model. And finally, training the attribute recognition model based on the difference between the attribute words and the labels of each training sample.

Of course, the attribute word may be a word, or may be a specific whole text. The specific type of the attribute word can be set according to the need, and the specification does not limit the specific type of the attribute word.

Similarly, the server can also adopt a machine learning mode to train to obtain an entity recognition model, and then determine specific entity words in the enterprise information through the entity recognition model.

If only the labels corresponding to the enterprises are specified, the association relationship between the labels and the enterprises is not specified. Then, when the enterprise is characterized based on the determined tag, a situation may occur in which the enterprise cannot be accurately characterized. The number of the enterprise staff is 100, the number of the plan expansion persons in 2023 is 200, and the labels of the enterprise can be 100 and 200. Clearly, the enterprise cannot be accurately characterized based on the above-described tags. Therefore, in order to avoid the above, in step S102, the server may determine the association relationship between each tag and the enterprise, while determining each tag corresponding to the enterprise.

Specifically, for the structured information, the server may directly use the keys of each label as the association relationship between the label and the enterprise.

For unstructured information, the server can determine, for each tag of the enterprise, an association relationship corresponding to the tag based on enterprise information including the tag after determining the tag.

Of course, the server can also train to obtain the whole recognition model by adopting a machine learning mode, and then recognize each label of the enterprise and the corresponding association relation of each label respectively through the whole recognition model.

The integral recognition model is obtained by training in the following mode:

a number of enterprise information is determined as each training sample. And manually marking the labels contained in the training samples and the association relation between the labels and enterprises corresponding to the training samples aiming at each training sample, and taking the labels and the association relation as a first marking and a second marking of the training samples. And inputting the training sample into a feature extraction layer of the overall recognition model to be trained to obtain features output by the feature extraction layer, and respectively inputting the features into a label determining branch and a relation determining branch of the overall recognition model to obtain labels output by the label determining branch and association relations output by the relation determining branch. And finally, training the integral recognition model based on the difference between the labels of the training samples and the first label and the difference between the association relation and the second label.

It should be noted that, the model structures of the entity recognition model, the attribute recognition model and the overall recognition model may be set according to needs, which is not limited in this specification.

In addition, since the portrait information corresponding to the enterprise can be displayed based on the knowledge graph form, each label corresponding to the enterprise can be determined based on the knowledge extraction method when each label corresponding to the enterprise is determined. As shown in figure 4 of the drawings,

fig. 4 is a schematic structural diagram of an enterprise ontology provided in the present specification, where a label predefined for an enterprise includes: the patent owned by the enterprise, the enterprise invested externally by the enterprise, the land block purchased by the enterprise, the stakeholder of the enterprise, and the correspondence between the stakeholder of the enterprise and the patent. The server can identify the preset labels according to the determined enterprise information, and determine the labels corresponding to the enterprise. Wherein the enterprise ontology is a data model of the enterprise, and is used for modeling the enterprise according to the labels, namely, describing the accuracy of the enterprise by using the labels of the enterprise,

it should be noted that the types of labels of the enterprise shown in fig. 3 are merely illustrative, and the types of labels and the number of labels contained in the enterprise body may be set according to needs, which is not limited in this specification.

Based on the same concept, the present specification also provides a block diagram of enterprise portrait information. As shown in fig. 5.

Fig. 5 is a block diagram of an enterprise portrait provided in the present specification. In the figure, image information corresponding to enterprise a is shown. It can be seen that the patents owned by enterprise a are patent 1, patent 2, patent 3 and patent 4, respectively. The stakeholder of enterprise a was the first, and patent 1 was invented by the first. The law of the enterprise A is the law of B, the staff of the enterprise is the law of C, the enterprise degree invests the enterprise B externally, and the law of the enterprise B is the law of C. In addition, businesses have purchased a parcel. And the enterprise type corresponding to the enterprise is a high-speed development type enterprise. Based on the knowledge graph, the image information corresponding to the enterprise can be accurately and intuitively displayed.

Of course, besides the above examples, the labels of the enterprises can be labels of personnel scale, participants, enterprise capital and the like corresponding to the enterprises, and then nodes corresponding to the labels can be displayed in the knowledge graph. Meanwhile, because the charts are combined and used more intuitively, when the knowledge graph corresponding to the enterprise is displayed, the labels corresponding to the enterprise can be displayed in a form of a table. As shown in table 2.

TABLE 2

Table 2 is a schematic illustration of enterprise image information provided in the present specification, and the information included in table 2 is, for example, image information of enterprise a shown in fig. 5, and the schematic illustration of enterprise image information may be displayed while the knowledge graph shown in fig. 5 is displayed, so that image information corresponding to the enterprise may be displayed more intuitively based on the schematic illustration of enterprise image information and the knowledge graph.

In addition, besides the enterprise type corresponding to the enterprise, the influence degree corresponding to the enterprise can be used for characterizing the enterprise. And in general, for each node in the knowledge graph, the greater the number of neighbor nodes connected to the node, the more important the node. Based on the same idea, the server can determine the influence degree of the enterprise according to the number of the neighbor nodes.

Specifically, the server may determine, for each enterprise, a node corresponding to the enterprise from the knowledge graph.

The server may then determine neighbor nodes adjacent to the node corresponding to the enterprise and determine the impact of the enterprise based on the number of neighbor nodes.

And finally, the service area can take at least part of the knowledge graph corresponding to the enterprise and the influence degree corresponding to the enterprise as portrait information of the enterprise.

Further, for each node, if the importance of the neighboring node adjacent to the node is higher, the importance of the node is also higher. Therefore, the server can also determine the influence degree of the nodes corresponding to the enterprise by adopting the influence degree of the neighbor nodes.

Specifically, after determining the neighboring nodes, the server may determine, for each neighboring node, a degree of influence of the neighboring node. The influence of the neighboring node can be determined according to the number of nodes adjacent to the neighboring node.

Therefore, the server can determine the influence degree corresponding to the enterprise according to the influence degree corresponding to each neighbor node. Wherein the influence of the enterprise is positively correlated with the influence of the neighboring nodes.

In addition, for an enterprise, the influence of the node of the label corresponding to the enterprise belonging to the enterprise on the node of the enterprise is obviously different from the influence of the node of the label corresponding to the legal person of the enterprise on the node of the enterprise. That is, when determining the influence degree corresponding to the enterprise, the relationship between each neighboring node and the node corresponding to the enterprise should also be considered. Thus, the server may set a weight for the association between each type of tag and the business for that type of tag. The influence of the label corresponding to the weight on the enterprise is positively correlated with the weight.

Specifically, the server may determine, for a neighboring node adjacent to the node corresponding to the enterprise, an edge connected between the neighboring node and the node corresponding to the enterprise, and determine a weight of an association relationship corresponding to the edge.

Then, the server can determine the influence degree of the enterprise according to the influence degree corresponding to each neighbor node and the weight of the edge corresponding to each neighbor node.

Further, if the influence of the nodes in the knowledge graph on the neighboring nodes is considered, the influence of each neighboring node on the neighboring node caused by the neighboring node is considered when determining the influence degree of the enterprise. Therefore, the server can also determine the influence degree of the neighboring node, and determine the influence degree of the node corresponding to the enterprise according to the influence degree of the neighboring node.

Specifically, the server may determine at least a part of the knowledge graph corresponding to the node from the knowledge graphs, and use the at least part of the knowledge graph as the subgraph corresponding to the node.

Then, from the subgraph corresponding to the node, each level of neighbor nodes corresponding to the node are determined, as shown in fig. 6.

Fig. 6 is a schematic diagram of at least a part of a knowledge graph corresponding to a node provided in the present specification. The round dots represent each node, the solid lines represent the association relation among the nodes in the knowledge graph structure, and w is the weight corresponding to the edge. Taking the at least part of the knowledge graph as e ₇ And a sub-graph corresponding to the node. Then the e ₇ The 1-order neighbor node corresponding to the node is e ₃ Then e ₇ The 2-order neighbor node corresponding to the node is i ₂ 、e ₆ Then e ₇ The 3-order neighbor node corresponding to the node is e ₂ 。

The server may determine node e ₆ The degree of influence of w ₄ Node e ₃ Has an influence of 3w ₄ w ₃ +w ₂ Node e ₇ The degree of influence of (3 w) ₄ w ₃ +w ₂ )w ₁ 。

Further, for each node, the server may set the importance of the node itself, and for the node corresponding to the label, the importance corresponding to the node may be the quantized value corresponding to the label. For a node corresponding to an enterprise, the importance corresponding to the node may be determined based on the importance of neighboring nodes adjacent to the node. When determining the influence degree corresponding to each node, the importance degree corresponding to each node can be determined, and the influence degree of each node and the importance degree are added to be used as the influence degree of the node determined again.

Taking fig. 6 as an example, assume node e ₂ The importance of (A) is ₂ Node e ₃ The importance of (A) is ₃ Node i ₂ The importance of (A) is ₄ Node e ₆ The importance of (A) is ₆ Node e ₇ The importance of (A) is ₇ 。e ₆ Is the influence degree A ₂ w ₄ +A ₆ ，e ₃ The influence degree is (A) ₂ w ₄ +A ₆ )w ₃ +A ₄ w ₂ +A ₃ ，e ₇ The degree of influence is [ (A) ₂ w ₄ +A ₆ )w ₃ +A ₄ w ₂ +A ₃ ]w ₁ +A ₇ 。

Taking a knowledge graph as G (V, E) as an example, wherein V= { V ₁ ,v ₂ ,...v _n Used for representing n nodes in the knowledge graph, E= { E ₁ ,e ₂ ,...e _m And the M edges in the knowledge graph are used for representing. Suppose node v ₀ E V and k nodes V ₁ ,v ₂ ,...v _k Connected, node v ₀ The influence degree NR (v) of (a) is as follows:

Wherein: sigma epsilon (0, 1) is a preset value. NR (v) _i ) For characterising node v _i Importance of the device itself. S is S _out (v _i ) For node v _i Is the outages of the node v _i Is a number of neighbor nodes. Omega (v) _i ,v ₀ ) Representing node v _i And node v ₀ The weight of the connected edge is usually defined by manually specifying the weight corresponding to each edge in advance in relation to each other by each label.For characterising v ₀ Obtaining node v _i The weight ratio of the influence degree.

Obviously, the larger the weight of the neighbor node to which the node v is connected, the more the accumulated component the node v obtains from the neighbor node. The larger the node itself, the greater the importance obtained from the neighboring nodes. The greater the weight of a node to a neighbor node edge, the greater the weight obtained from the neighbor node.

After determining the influence degree corresponding to the enterprises, the server can determine each enterprise with higher fixation degree from the enterprises contained in the knowledge graph according to the influence degree corresponding to each enterprise. As shown in table 3.

Enterprise name	Influence degree scoring
		Enterprise A	1.12
Enterprise B	0.95
		Enterprise C	0.88
Enterprise D	0.6
		Enterprise E	0.55

TABLE 3 Table 3

Table 3 provides the influence of the top 5 business and its corresponding influence provided in this specification. It can be seen that the influence of enterprise a is 1.12 and that of enterprise B is 0.95. 0.95 … …. The server may receive a presentation request carrying a tag type when it is desired to supervise the enterprise based on the degree of influence. Based on the above table 3, the influence degree corresponding to each enterprise can be rapidly determined and returned according to the display request. How the influence degree of each enterprise is displayed, the data type carried in the display request and how the server responds to the display request can be set according to the needs, and the description is not limited to the method.

After determining the enterprise type and the influence degree of the enterprise corresponding to the enterprise, the server can take the enterprise type and the influence degree corresponding to each enterprise as one of the labels of the enterprise, and update the knowledge graph according to the determined labels. And the enterprise type and influence degree corresponding to the enterprise can be stored only, and the enterprise type and influence degree can be displayed when the enterprise needs to be displayed. In order to ensure the accuracy of the image information of the displayed enterprise, the server can execute the information display method according to the preset time interval to redetermine the image information of the enterprise so as to update the image information of the enterprise and ensure the accuracy of the image information of the enterprise. How to display the portrait information corresponding to the enterprise and when to execute the information display method can be set according to the needs, and the present specification is not limited to this.

The information display method provided for one or more embodiments of the present disclosure further provides a corresponding information display device based on the same concept, as shown in fig. 7.

Fig. 7 is a schematic diagram of an information display device provided in the present specification, specifically including:

the information determining module 200 is configured to determine, for each enterprise, enterprise information of the enterprise according to the obtained enterprise identifier of the enterprise.

And the identification module 202 is used for identifying the enterprise information and determining each label of the enterprise.

And the clustering module 204 is used for clustering the enterprises according to the labels respectively corresponding to the enterprises.

The type determining module 206 is configured to determine, for each clustered cluster obtained by clustering, an enterprise type of each enterprise of the clustered cluster according to a label of at least one enterprise included in the clustered cluster.

And the portrait determining module 208 is configured to determine portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and each label corresponding to each enterprise.

And the updating module 210 is used for determining and displaying the portrait information of the appointed enterprise matched with the appointed identification from the pre-stored portrait information of each enterprise according to the appointed identification carried in the display request when the display request is received.

Optionally, the labels include an entity label and a non-entity label, the entity label includes at least one of a user name and an enterprise name, the portrait determining module 208 is configured to determine, for each enterprise, an association relationship between each label of the enterprise and the enterprise, establish a knowledge graph with the enterprise and the label as nodes according to each label corresponding to each enterprise and each association relationship between each label and each enterprise corresponding to each label, edges between the nodes in the knowledge graph are used to characterize the association relationship between two nodes connected with the edges in the knowledge graph, determine, from the knowledge graph, at least part of the knowledge graph corresponding to each enterprise, and determine, according to each enterprise type corresponding to each enterprise and at least part of the knowledge graph corresponding to each enterprise, portrait information corresponding to each enterprise.

Optionally, for each enterprise, the number of enterprise identifiers of the enterprise is multiple, the portrait determining module 208 is configured to establish an initial graph with the enterprise identifiers and the labels as nodes, determine, for each enterprise, from the initial graph according to each enterprise identifier of the enterprise, a node corresponding to each enterprise identifier of the enterprise as each specific node, fuse each specific node, and update the initial graph according to a fusion result, so as to obtain a knowledge graph.

Optionally, the representation determining module 208 is configured to determine, for each enterprise, a neighboring node adjacent to a node corresponding to the enterprise from the knowledge graph, determine, according to the neighboring nodes, an influence degree of the enterprise, and determine, according to the enterprise type corresponding to each enterprise, at least a part of the knowledge graph corresponding to each enterprise, and the influence degree corresponding to each enterprise, representation information corresponding to each enterprise.

Optionally, the portrayal determining module 208 is configured to determine, for each neighboring node, the number of nodes connected by the neighboring node in the knowledge graph as a specific number, and determine the influence degree of the neighboring node, and determine the influence degree of the enterprise according to the influence degree of each neighboring node, the specific number of each neighboring node, and the weight of the edge between each neighboring node and the node corresponding to the enterprise.

Optionally, the business information includes at least one of structured information and unstructured information related to the business, and the identifying module 202 is configured to identify entity words of the business information, determine each entity word included in the business information, and determine a specific entity word in each entity word as a tag of the business.

The present specification also provides a computer-readable storage medium storing a computer program operable to perform the information presentation method provided in fig. 1 described above.

The present specification also provides a schematic structural diagram of the electronic device shown in fig. 8. At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile storage, as illustrated in fig. 8, although other hardware required by other services may be included. The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to implement the information display method described in fig. 1. Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.

In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present disclosure and is not intended to limit the disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present description.

Claims

1. An information display method, characterized in that the method comprises:

2. The method according to claim 1, wherein determining the type of business of each business of the cluster based on the label of at least one business contained in the cluster, specifically comprises:

3. The method of claim 1, wherein the tags include an entity tag and a non-entity tag, the entity tag including at least one of a user name and a business name;

4. The method of claim 3, wherein for each business, the number of business identifications for that business is a plurality;

5. The method of claim 3, wherein determining the portrait information corresponding to each enterprise according to the enterprise type corresponding to each enterprise and at least a part of the knowledge graph corresponding to each enterprise, specifically comprises:

determining influence of the enterprise according to each neighbor node;

6. The method of claim 5, wherein determining the impact of the enterprise based on each neighbor node comprises:

7. The method of claim 1, wherein the enterprise information comprises at least one of structured information and unstructured information related to the enterprise;

8. An information presentation apparatus, the apparatus comprising:

9. The apparatus of claim 8, wherein the type determining module is configured to determine, for each cluster in the cluster result, an enterprise corresponding to a cluster center of the cluster, as a characterizing enterprise of the cluster, determine, according to each tag of the characterizing enterprise of the cluster, an enterprise type of the characterizing enterprise of the cluster, and use the enterprise type of the characterizing enterprise of the cluster as an enterprise type of each enterprise of the cluster.

10. The apparatus of claim 8, wherein the tags comprise an entity tag and a non-entity tag, the entity tag comprising at least one of a user name and a business name;

11. The apparatus of claim 10, wherein for each business, the number of business identifications for that business is a plurality;

12. The apparatus of claim 10, wherein the representation determining module is configured to determine, for each enterprise, from the knowledge-graph, a neighboring node adjacent to a node corresponding to the enterprise, determine, based on each neighboring node, an influence of the enterprise, and determine, based on the enterprise type respectively corresponding to each enterprise, at least a portion of the knowledge-graph respectively corresponding to each enterprise, and the influence respectively corresponding to each enterprise, representation information respectively corresponding to each enterprise.

13. The apparatus of claim 12, wherein the representation determining module is configured to determine, for each neighboring node, a number of nodes connected by the neighboring node in the knowledge-graph as a specific number, and determine a degree of influence of the neighboring node, and determine a degree of influence of the enterprise according to a degree of influence of each neighboring node, the specific number of each neighboring node, and a weight of an edge between each neighboring node and a node corresponding to the enterprise.

14. The apparatus of claim 8, wherein the enterprise information comprises at least one of structured information and unstructured information related to the enterprise;

15. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.

16. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any of the preceding claims 1-7 when executing the program.