CN115687721A - Enterprise dynamic information recommendation method and device, computing equipment and storage medium - Google Patents
Enterprise dynamic information recommendation method and device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN115687721A CN115687721A CN202211335850.8A CN202211335850A CN115687721A CN 115687721 A CN115687721 A CN 115687721A CN 202211335850 A CN202211335850 A CN 202211335850A CN 115687721 A CN115687721 A CN 115687721A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- dynamic information
- monitored
- enterprises
- recalled
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000013598 vector Substances 0.000 claims abstract description 67
- 238000010586 diagram Methods 0.000 claims description 22
- 238000012216 screening Methods 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 238000003058 natural language processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000002093 peripheral effect Effects 0.000 abstract 2
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an enterprise dynamic information recommendation method and device, a computing device and a storage medium. The method comprises the following steps: acquiring an enterprise to be monitored, and acquiring a pre-constructed enterprise relation graph containing the enterprise to be monitored; acquiring an embedded vector of each enterprise in the enterprise relation graph, and acquiring a recall enterprise corresponding to the enterprise to be monitored according to the embedded vector; and determining the related enterprise dynamic information of the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise, and recommending the related enterprise dynamic information to the user. Therefore, the generalized enterprise dynamic information recommendation is realized, enterprise dynamic information of related enterprises which potentially affect the monitored enterprise is extracted for the user from the enterprise monitored by the user, and the extracted enterprise dynamic information which affects other enterprises of the monitored enterprise is recommended to the user, so that the user can comprehensively and timely know the enterprise dynamics of peripheral enterprises of the monitored enterprise, and the condition that the user omits the peripheral dynamics of the monitored enterprise to cause poor information is avoided.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an enterprise dynamic information recommendation method, an enterprise dynamic information recommendation device, computing equipment and a storage medium.
Background
Enterprise dynamic monitoring is an important function in enterprise information services. In common enterprise dynamic monitoring, generally, a user monitors an enterprise in which the user is interested by himself, and the system pushes daily enterprise dynamic information of the monitored enterprise to the user. In this process, the system will push only if the user actively triggers the monitoring.
However, because the risk flow among enterprises is complicated, one enterprise is likely to be influenced by the dynamics of other enterprises, and when a user does not monitor an enterprise with a risk source, the user cannot acquire related enterprise dynamic information, which causes message lag and brings serious influence. For example, a parent company of company a has bankruptcy clearing, but the user cannot obtain the dynamic information of the parent company of company a only by monitoring company a, thereby bringing about a serious influence on the user.
Disclosure of Invention
In view of the above problems, the present invention has been made to provide a method, an apparatus, a computing device and a storage medium for recommending enterprise dynamic information, which overcome or at least partially solve the above problems.
According to one aspect of the invention, an enterprise dynamic information recommendation method is provided, which comprises the following steps:
acquiring enterprises to be monitored, and acquiring a pre-constructed enterprise relationship diagram containing the enterprises to be monitored, wherein the enterprise relationship diagram is a relationship diagram constructed by taking the enterprises as nodes and taking the sum of the weights of all incidence relationship information among the enterprises as an edge;
acquiring an embedded vector of each enterprise in the enterprise relation graph, and acquiring a recall enterprise corresponding to the enterprise to be monitored according to the embedded vector;
and determining the related enterprise dynamic information of the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise, and recommending the related enterprise dynamic information to the user.
Further, the determining method of the embedded vector of the enterprise comprises the following steps:
sampling the enterprise relation graph to obtain a sampling sequence of each enterprise;
and aiming at each enterprise, training the sampling sequence of the enterprise by adopting a preset natural language processing model to obtain the embedded vector of the enterprise.
Further, after retrieving the enterprise corresponding to the enterprise to be monitored according to the embedded vector, the method further includes:
calculating the embedding similarity between the embedding vector of the enterprise to be monitored and the embedding vector of the enterprise to be recalled;
determining dynamic scores corresponding to each piece of enterprise dynamic information of the recalled enterprises respectively;
and calculating the influence value of the dynamic information of the enterprise to be monitored according to the embedded similarity and the dynamic value corresponding to the recalled enterprise.
Further, determining the enterprise dynamic information related to the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise, and recommending the enterprise dynamic information to the user further includes:
if the enterprise dynamic of the recalled enterprise is multiple, sorting enterprise dynamic information corresponding to the recalled enterprise according to the influence value;
and screening a first preset amount of enterprise dynamic information from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored, and recommending the enterprise dynamic information to the user.
Further, before the enterprise dynamic information corresponding to the recalled enterprise is ranked according to the influence score, the method further includes: if the number of the recalling enterprises is multiple, screening a second preset number of the recalling enterprises from the multiple recalling enterprises according to the embedding similarity;
ranking the enterprise dynamic information corresponding to the recalled enterprises based on the impact scores further comprises:
and aiming at any one of the screened recalling enterprises, sequencing the enterprise dynamic information corresponding to the recalling enterprise according to the influence value.
Further, determining the enterprise dynamic information associated with the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise further includes:
if the number of the recalling enterprises is multiple and the enterprise dynamic of each recalling enterprise is one, ranking the enterprise dynamic information corresponding to the plurality of recalling enterprises according to the influence value;
and taking the sequenced enterprise dynamic information as the related enterprise dynamic information of the enterprise to be monitored and recommending the related enterprise dynamic information to the user.
Further, before ranking the dynamic enterprise information corresponding to the plurality of recalled enterprises according to the impact scores, the method further includes: screening a third preset number of recalling enterprises from the plurality of recalling enterprises according to the embedding similarity;
ranking the enterprise dynamic information corresponding to each recalled enterprise according to the impact score further comprises:
and sequencing the enterprise dynamic information corresponding to the third preset number of the selected recalled enterprises according to the influence scores.
Further, calculating the influence score of the enterprise dynamic information on the enterprise to be monitored according to the embedding similarity and the dynamic score corresponding to the recalled enterprise further comprises:
and multiplying the embedding similarity and the dynamic score corresponding to the recalled enterprise, and taking the calculation result as the influence score of the enterprise to be monitored as the dynamic information of the enterprise.
Further, determining the dynamic score corresponding to each piece of enterprise dynamic information of the recalled enterprise further includes:
and determining the information type of each piece of enterprise dynamic information of the recalled enterprise, and determining a dynamic score corresponding to the enterprise dynamic information according to the information type.
Further, obtaining the recalled enterprise corresponding to the enterprise to be monitored according to the embedded vector further includes:
searching enterprises which have inter-enterprise association relation with the enterprise to be monitored in the enterprise relation graph;
calculating the Euclidean distance between the found embedded vector of the enterprise and the embedded vector of the enterprise to be monitored;
and if the Euclidean distance is smaller than or equal to the preset distance, determining the enterprise corresponding to the Euclidean distance as a recalling enterprise corresponding to the enterprise to be monitored.
According to another aspect of the present invention, there is provided an enterprise dynamic information recommendation apparatus, including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is suitable for acquiring enterprises to be monitored and acquiring a pre-constructed enterprise relation graph containing the enterprises to be monitored, and the enterprise relation graph is a relation graph constructed by taking the enterprises as nodes and taking the sum of the weights of all incidence relation information among the enterprises as a side;
the second acquisition module is suitable for acquiring the embedded vector of each enterprise in the enterprise relation graph and acquiring the recalling enterprise corresponding to the enterprise to be monitored according to the embedded vector;
and the recommending module is suitable for determining the related enterprise dynamic information of the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise and recommending the related enterprise dynamic information to the user.
Further, the apparatus further comprises: the embedded vector determining module is suitable for sampling the enterprise relational graph to obtain a sampling sequence of each enterprise;
and aiming at each enterprise, training the sampling sequence of the enterprise by adopting a preset natural language processing model to obtain the embedded vector of the enterprise.
Further, the apparatus further comprises: the computing module is suitable for computing the embedding similarity between the embedding vector of the enterprise to be monitored and the embedding vector of the enterprise to be recalled;
determining dynamic scores corresponding to each piece of enterprise dynamic information of the recalled enterprises respectively;
and calculating the influence value of the dynamic information of the enterprise to be monitored according to the embedding similarity and the dynamic value corresponding to the recalled enterprise.
Further, the recommendation module is further adapted to: if the enterprise dynamic of the recalled enterprise is multiple, sorting enterprise dynamic information corresponding to the recalled enterprise according to the influence value;
and screening a first preset amount of enterprise dynamic information from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored, and recommending the enterprise dynamic information to the user.
Further, the recommendation module is further adapted to: if the number of the recalling enterprises is multiple, screening a second preset number of the recalling enterprises from the multiple recalling enterprises according to the embedding similarity;
and aiming at any one of the screened recalling enterprises, sequencing the enterprise dynamic information corresponding to the recalling enterprise according to the influence value.
Further, the recommendation module is further adapted to: if the number of the recalling enterprises is multiple and the enterprise dynamics of each recalling enterprise is one, sequencing the enterprise dynamic information corresponding to the plurality of the recalling enterprises according to the influence scores;
and taking the sequenced enterprise dynamic information as the related enterprise dynamic information of the enterprise to be monitored and recommending the related enterprise dynamic information to the user.
Further, the recommendation module is further adapted to: screening a third preset number of recalling enterprises from the plurality of recalling enterprises according to the embedding similarity;
and sequencing the enterprise dynamic information corresponding to the third preset number of the selected recalled enterprises according to the influence scores.
Further, the calculation module is further adapted to: and multiplying the embedding similarity and the dynamic score corresponding to the recalled enterprise, and taking the calculation result as the influence score of the enterprise to be monitored as the dynamic information of the enterprise.
Further, the calculation module is further adapted to: and determining the information type of each piece of enterprise dynamic information of the recalled enterprise, and determining a dynamic score corresponding to the enterprise dynamic information according to the information type.
Further, the second obtaining module is further adapted to: searching enterprises which have inter-enterprise association relation with the enterprise to be monitored in the enterprise relation graph;
calculating the Euclidean distance between the found embedded vector of the enterprise and the embedded vector of the enterprise to be monitored;
and if the Euclidean distance is smaller than or equal to the preset distance, determining the enterprise corresponding to the Euclidean distance as the recalling enterprise corresponding to the enterprise to be monitored.
According to yet another aspect of the present invention, there is provided a computing device comprising: the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the enterprise dynamic information recommendation method.
According to still another aspect of the present invention, a computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform an operation corresponding to the above enterprise dynamic information recommendation method.
According to the scheme provided by the invention, the generalized enterprise dynamic information recommendation is realized, enterprise dynamic information of related enterprises which potentially influence the monitored enterprise is extracted for the user from the enterprise monitored by the user, and the extracted enterprise dynamic information which influences other enterprises of the monitored enterprise is recommended to the user, so that the user can comprehensively and timely know the enterprise dynamics of the surrounding enterprises of the monitored enterprise, and the condition that the user omits the surrounding dynamics of the monitored enterprise to cause poor information is avoided.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow diagram illustrating a method for enterprise dynamic information recommendation, according to one embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for enterprise dynamic information recommendation according to another embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an enterprise dynamic information recommendation device according to an embodiment of the present invention;
FIG. 4 shows a block diagram of a computing device, according to one embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
FIG. 1 is a flowchart illustrating a method for recommending enterprise dynamic information according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
step S101, acquiring enterprises to be monitored, and acquiring a pre-constructed enterprise relation graph containing the enterprises to be monitored, wherein the enterprise relation graph is a relation graph constructed by taking the enterprises as nodes and taking the sum of the weights of all incidence relation information among the enterprises as a side.
Specifically, the enterprise to be monitored is an enterprise with an enterprise dynamic information monitoring requirement, and is an enterprise in which users are interested.
In this embodiment, an enterprise dynamic information recommendation page may be provided to a user, where the enterprise dynamic information recommendation page includes an enterprise input box to be monitored, the user may input an enterprise name to be monitored in the enterprise input box to be monitored, and the user submits the enterprise name, thereby obtaining an enterprise to be monitored; in addition, the method can also be realized in other manners, for example, an enterprise dynamic information recommendation page includes an enterprise name pull-down menu, and a user can determine the name of the enterprise to be monitored by inputting an enterprise name keyword to perform fuzzy matching with the enterprise name in the enterprise name pull-down menu, so as to obtain the enterprise to be monitored.
In this embodiment, an enterprise relationship graph is constructed in advance, and after acquiring an enterprise to be monitored, an enterprise relationship graph including the enterprise to be monitored may be further acquired, where the enterprise relationship graph represents relationships between enterprises in a graph form, and the enterprise relationship graph is a relationship graph constructed by using the enterprises as nodes and taking the sum of weights of all association relationship information between the enterprises as a side. The association relationship between enterprises may be embodied as investment relationship, co-occurrence of people, cooperation relationship, group relationship, etc., and is only for illustration and not limited.
And S102, acquiring the embedded vector of each enterprise in the enterprise relation graph, and acquiring the recalled enterprise corresponding to the enterprise to be monitored according to the embedded vector.
Specifically, each enterprise is represented in the enterprise relationship diagram in the form of an embedded vector, and in order to enable a user to comprehensively know the dynamic state of surrounding enterprises of the enterprise to be monitored, the embedded vector of each enterprise in the enterprise relationship diagram needs to be acquired, and the enterprise to be monitored is recalled according to the embedded vector. The recalling enterprise is an enterprise meeting specific conditions with the enterprise to be monitored in the enterprise relation diagram, for example, an enterprise whose euclidean distance with the enterprise to be monitored in the enterprise relation diagram does not exceed a preset distance, and there is a certain relevance between the recalling enterprise and the enterprise to be monitored, and the enterprise development of the recalling enterprise affects the development of the enterprise to be monitored.
And S103, determining the related enterprise dynamic information of the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise, and recommending the related enterprise dynamic information to the user.
After the recalling enterprise corresponding to the enterprise to be monitored is obtained according to step S102, enterprise dynamic information of the recalling enterprise is obtained, where the enterprise dynamic information refers to information type information issued for the enterprise, and may be, for example, enterprise operation information, publicity information, production and marketing information, and the like. And then, determining the enterprise dynamic information related to the enterprise to be monitored based on the enterprise dynamic information corresponding to the enterprise to be monitored, and recommending the enterprise dynamic information to the user, so that the user can know the enterprise dynamic information of the enterprise to be monitored, can know the enterprise dynamic information of the enterprise to be monitored in time, and can perform risk assessment on the enterprise to be monitored by combining the enterprise dynamic information of the enterprise to be recalled, thereby avoiding the loss of the user due to information acquisition lag.
The scheme provided by the embodiment of the invention realizes generalized enterprise dynamic information recommendation, and from the enterprise monitored by the user, the enterprise dynamic information of the related enterprise which is potential and possibly affects the monitored enterprise is extracted for the user, and the extracted enterprise dynamic information affecting other enterprises of the monitored enterprise is recommended to the user, so that the user can comprehensively and timely know the enterprise dynamics of the surrounding enterprises of the monitored enterprise, and the condition that the user omits the surrounding dynamics of the monitored enterprise to cause poor information is avoided.
Fig. 2 is a flowchart illustrating an enterprise dynamic information recommendation method according to another embodiment of the present invention. As shown in fig. 2, the method comprises the steps of:
step S201, acquiring the enterprise to be monitored, and acquiring a pre-constructed enterprise relation graph containing the enterprise to be monitored, wherein the enterprise relation graph is a relation graph constructed by taking the enterprise as a node and taking the sum of the weights of all the incidence relation information among the enterprises as an edge.
This step is similar to step S101 in the embodiment shown in fig. 1, and is not described here again.
In an optional implementation manner of the present invention, the process of constructing the enterprise relationship graph specifically includes:
extracting enterprise relation data from an enterprise database; and generating an enterprise relationship graph by taking each enterprise as a node and taking the enterprise relationship data as an edge.
Specifically, a large amount of enterprise related data are stored in the enterprise database, so that enterprise relational data can be extracted from the enterprise database, wherein the enterprise relational data refer to that two enterprises have the same or associated attributes, and the enterprise relational data mainly comprise investment relational data, personnel co-occurrence data, cooperation relational data, group relational data and the like; if no business relationship exists between the two businesses, no edge exists between the two businesses in the business relationship graph.
In this alternative embodiment, there may be a case where there are a plurality of same or associated attribute information between two, and for this case, a corresponding weight may be set for each business relationship data, and then the sum of the weights is calculated from all the business relationship data between the businesses as an edge between the two businesses. The enterprise relation graph is a same graph, only has enterprise nodes and edges, is simple in structure and convenient to expand, can be directly realized by adding the nodes and the edges when an enterprise is newly added, and is easy to introduce new enterprises and relationships among the enterprises.
Step S202, acquiring the embedded vector of each enterprise in the enterprise relation graph, and searching for the enterprise having the inter-enterprise association relation with the enterprise to be monitored in the enterprise relation graph.
In the enterprise relationship diagram, each enterprise is represented in the form of an embedded vector, and in order to enable a user to comprehensively know the dynamic state of surrounding enterprises of the enterprise to be monitored, the embedded vector of each enterprise in the enterprise relationship diagram needs to be acquired, and specifically, the embedded vector of the enterprise can be determined by the following method: sampling the enterprise relation graph to obtain a sampling sequence of each enterprise; and aiming at each enterprise, training the sampling sequence of the enterprise by adopting a preset natural language processing model to obtain the embedded vector of the enterprise. For example, each enterprise is taken as an origin to perform random walk in an enterprise relationship diagram to obtain a sampling sequence of each enterprise, each sequence at least comprises k nodes, each node starts sampling for m times, the sequence set is input into a preset natural language processing model (for example, a node2vec model and a word2vec model) in a sentence form to be trained, and a word embedding representation of each enterprise obtained through model training is an embedding vector of the enterprise. The embedded vector of the enterprise can be a vector with any dimension. Taking a 16-dimensional vector as an example:
the embedded vector for "Beijing AA technologies, inc" is expressed as: [ -0.6433484,1.9626732,2.9946766,3.4748187,0.8176478, -0.945684,1.0036267,1.8913803,1.430759,1.2809728,4.0172596,2.8226984, -1.9158391,0.17588441, -3.302099,1.3402888].
The embedded vector of "Beijing BB network technology, inc" is expressed as: [ -0.52615666, -1.8757683,2.3022957, -2.247738,3.6796074,0.26537383,1.8951517, -0.5244883,0.4057679,3.4313507, -0.7072354, -4.1955266, -1.4017067,1.5180964, -3.0574412,1.4780037].
Specifically, the enterprise relationship graph is a relationship graph constructed by using enterprises as nodes and using the sum of the weights of all the association relationship information between the enterprises as an edge, and the relationship between the enterprises is represented in a graph form. Therefore, an enterprise having an inter-enterprise association relationship with the enterprise to be monitored can be searched in the enterprise relationship diagram, the inter-enterprise association relationship can be embodied by a connection relationship between two nodes in the enterprise relationship diagram, and if a connection line exists between the two nodes, the association relationship between the two enterprises can be considered to exist, for example, an enterprise having a connection relationship with the enterprise to be monitored can be searched. The association relationship between enterprises may be embodied as investment relationship, co-occurrence of people, cooperation relationship, group relationship, etc., and is only for illustration and not limited.
Step S203, calculating Euclidean distance between the found embedding vector of the enterprise and the embedding vector of the enterprise to be monitored.
In the enterprise relationship diagram, each enterprise is represented in the form of an embedded vector, and therefore, after the enterprise is found according to step S202, for each enterprise, the euclidean distance between the embedded vector of the enterprise and the embedded vector of the enterprise to be monitored is calculated. The detailed calculation process is not described herein.
And S204, if the Euclidean distance is smaller than or equal to the preset distance, determining the enterprise corresponding to the Euclidean distance as the recalling enterprise corresponding to the enterprise to be monitored.
After the euclidean distance is calculated according to step S203, the euclidean distance is compared with a preset distance, for example, the preset distance is 1, which is only an example, and the preset distance may be set according to actual needs, and is not suitable to be set too large, and an enterprise with the euclidean distance smaller than or equal to the preset distance is determined as a recalling enterprise corresponding to the enterprise to be monitored. By way of example only, it is possible to illustrate,
assuming that the embedded vectors of the enterprises to be monitored are represented as [0,0,0,0], the embedded vectors of the searched enterprises are represented as [0,0,0,0.5], [0,0.1,0.2,0], [0.3,0.4,0.1,0], and the preset distance is 1, through calculation, the Euclidean distances between the searched enterprises and the enterprises to be monitored are all smaller than 1, and the enterprises are determined to be the corresponding enterprise to be recalled of the enterprises to be monitored.
Step S205, calculating the embedding similarity between the embedding vector of the enterprise to be monitored and the embedding vector of the enterprise recalled.
After the enterprise is recalled according to step S204, the embedding similarity between the embedding vector of the enterprise to be monitored and the embedding vector of the enterprise to be recalled is calculated, for example, the cosine similarity calculation method may be utilized, or the euclidean distance and the cosine distance may be calculated, and the inverse of the euclidean distance and the inverse of the cosine distance may be used to represent the embedding similarity. Wherein, the higher the embedding similarity, the more relevant the two enterprises are, the greater the influence of the enterprise dynamics is, and vice versa.
And step S206, determining the dynamic score corresponding to each enterprise dynamic information of the recalled enterprise respectively.
Specifically, for each recalled enterprise, dynamic information of the enterprise that is recalled to the recalled enterprise may be obtained, and for each piece of dynamic information of the enterprise, a dynamic score corresponding to the dynamic information of the enterprise may be determined, for example, each piece of dynamic information of the enterprise has a corresponding information type, and a corresponding dynamic score is set for each information type in advance. For example, the information types are classified into high risk, warning, prompting and profit, and dynamic scores corresponding to each information type, such as high risk 4, warning 3, prompting 2 and profit 1, can be set according to the influence degree of the information types on the enterprises, so that the dynamic score corresponding to each enterprise dynamic information can be determined. This is by way of example only and is not intended to be limiting.
And step S207, calculating the influence value of the enterprise dynamic information on the enterprise to be monitored according to the embedding similarity and the dynamic value corresponding to the recalled enterprise.
After the embedding similarity and the dynamic score are obtained through calculation, the influence score of the enterprise dynamic information on the enterprise to be monitored can be calculated according to the embedding similarity and the dynamic score corresponding to the recalled enterprise, for example, the embedding similarity and the dynamic score corresponding to the recalled enterprise can be multiplied, and the calculation result is used as the influence score of the enterprise dynamic information on the enterprise to be monitored, and the specific formula is as follows: impact score = embedded similarity ×. Dynamic score.
And S208, screening the recalled enterprises according to the embedding similarity and/or screening the enterprise dynamic information corresponding to the recalled enterprises according to the influence scores, and recommending the screened enterprise dynamic information to a user as the related enterprise dynamic information of the enterprise to be monitored.
Specifically, after the embedding similarity and/or the influence score are obtained through calculation, the recalled enterprise may be screened according to the embedding similarity and/or the enterprise dynamic information corresponding to the recalled enterprise may be screened according to the influence score, and the screened enterprise dynamic information is recommended to the user as the enterprise dynamic information associated with the enterprise to be monitored.
Specifically, when performing enterprise dynamic information recommendation, the following situations can be distinguished: 1) The number of the recalling enterprises is multiple, and the enterprise dynamics of each recalling enterprise is multiple; 2) The recalling enterprise is one and the enterprise dynamics of the recalling enterprise is multiple; 3) The number of the recalling enterprises is multiple, and the enterprise dynamic of each recalling enterprise is one; 4) The recalling enterprise is one enterprise and the enterprise dynamic of the recalling enterprise is one, and different processing can be carried out according to each situation.
For example, 1) if there are a plurality of recalling enterprises and the enterprise dynamic of each recalling enterprise is a plurality of, the enterprise dynamic information corresponding to each recalling enterprise may be sorted according to the influence score, for example, the enterprise dynamic information corresponding to each recalling enterprise is sorted in an order from high to low or from low to high, for each recalling enterprise, a first preset number of enterprise dynamic information is screened from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored and recommended to the user, for example, a first preset number of enterprise dynamic information with the highest influence score is selected, for example, the first preset number is 5, and then 5 pieces of enterprise dynamic information with the highest influence score are selected for each recalling enterprise.
Further, before ranking the dynamic business information corresponding to each recalled business according to the impact score, the method further comprises: the recall enterprises with the second preset number are selected from the plurality of recall enterprises according to the embedding similarity, the higher the embedding similarity is, the more relevant the two enterprises are, and the greater the influence of the enterprise dynamics is, therefore, the plurality of recall enterprises can be sorted according to the embedding similarity, for example, the recall enterprises with the second preset number are sorted according to the sequence from high embedding similarity to low embedding similarity or from low embedding similarity to high embedding similarity, for example, the recall enterprises with the second preset number with the highest embedding similarity are selected, for example, the second preset number is 3, then the recall enterprises with the highest embedding similarity are selected from the plurality of recall enterprises, wherein the first preset number and the second preset number may be the same or different. And after screening out a second preset number of the recalled enterprises, sorting enterprise dynamic information corresponding to the recalled enterprises according to the influence value aiming at any one of the screened recalled enterprises, and then screening out a first preset number of enterprise dynamic information from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored and recommending the enterprise dynamic information to the user aiming at any one of the screened recalled enterprises.
2) If one and multiple enterprise dynamics of the recalled enterprises are available, screening the enterprise dynamic information according to the influence values, specifically, sorting the enterprise dynamic information corresponding to the recalled enterprises according to the influence values; and screening a first preset amount of enterprise dynamic information from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored, and recommending the enterprise dynamic information to the user. The specific implementation is similar to the case where the number of the recalling enterprises is multiple and the enterprise dynamics of each recalling enterprise is multiple, and details are not repeated here.
3) If the number of the recalling enterprises is multiple and the enterprise dynamics of each recalling enterprise is one, the enterprise dynamic information corresponding to the plurality of the recalling enterprises is ranked according to the influence score, for example, the enterprise dynamic information corresponding to the plurality of the recalling enterprises is ranked according to the sequence of the influence scores from high to low, and the ranked enterprise dynamic information is used as the associated enterprise dynamic information of the enterprise to be monitored and recommended to the user, so that the user can preferentially view the enterprise dynamic information with higher influence score.
Further, before ranking the dynamic business information corresponding to the plurality of recalled businesses based on the impact scores, the method may further comprise: the recall enterprises with the highest embedding similarity are selected from the plurality of recall enterprises, for example, the recall enterprises with the highest embedding similarity are selected if the third preset number is 3, wherein the third preset number may be the same as or different from the second preset number. After the third preset number of recalled enterprises are screened out, the enterprise dynamic information corresponding to the screened third preset number of recalled enterprises is ranked according to the influence score, for example, the enterprise dynamic information corresponding to a plurality of recalled enterprises is ranked in order of the influence score from high to low, and then the ranked enterprise dynamic information is recommended to the user.
4) And if the recalling enterprise is one and the enterprise dynamic of the recalling enterprise is one, taking the enterprise dynamic information corresponding to the recalling enterprise as the related enterprise dynamic information of the enterprise to be monitored and recommending the related enterprise dynamic information to the user.
It should be noted that, in an optional implementation manner of the present invention, the recalled enterprises may also be screened only according to the embedding similarity, for example, screening a fourth preset number of recalled enterprises, and then, using the enterprise dynamic information of the screened recalled enterprises as the related enterprise dynamic information of the enterprise to be monitored, and recommending the related enterprise dynamic information to the user
The scheme provided by the embodiment of the invention realizes generalized enterprise dynamic information recommendation, and from the enterprise monitored by the user, the enterprise dynamic information of the related enterprise which is potential and possibly affects the monitored enterprise is extracted for the user, and the extracted enterprise dynamic information affecting other enterprises of the monitored enterprise is recommended to the user, so that the user can comprehensively and timely know the enterprise dynamics of the surrounding enterprises of the monitored enterprise, and the condition that the user omits the surrounding dynamics of the monitored enterprise to cause poor information is avoided. The embedding similarity is used for screening the recalled enterprises and/or the influence value is used for screening the dynamic information of the enterprises, so that the relevance between the dynamic information of the enterprises recommended to the user and the enterprises to be monitored can be improved, the user is prevented from screening from dynamic information of a plurality of enterprises, and the time of the user is saved.
Fig. 3 is a schematic structural diagram of an enterprise dynamic information recommendation device according to an embodiment of the present invention. As shown in fig. 3, the apparatus 30 includes:
the first obtaining module 301 is adapted to obtain an enterprise to be monitored, and obtain a pre-constructed enterprise relationship graph including the enterprise to be monitored, where the enterprise relationship graph is a relationship graph constructed by taking the enterprise as a node and taking the sum of the weights of all the association relationship information between the enterprises as an edge;
the second obtaining module 302 is adapted to obtain an embedded vector of each enterprise in the enterprise relationship diagram, and obtain a recall enterprise corresponding to the enterprise to be monitored according to the embedded vector;
and the recommending module 303 is adapted to determine the enterprise dynamic information related to the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise, and recommend the enterprise dynamic information to the user.
Optionally, the apparatus further comprises: the embedded vector determining module is suitable for sampling the enterprise relational graph to obtain a sampling sequence of each enterprise;
and aiming at each enterprise, training the sampling sequence of the enterprise by adopting a preset natural language processing model to obtain the embedded vector of the enterprise.
Optionally, the apparatus further comprises: the computing module is suitable for computing the embedding similarity between the embedding vector of the enterprise to be monitored and the embedding vector of the enterprise to be recalled;
determining dynamic scores corresponding to each enterprise dynamic information of the recalled enterprises respectively;
and calculating the influence value of the dynamic information of the enterprise to be monitored according to the embedding similarity and the dynamic value corresponding to the recalled enterprise.
Optionally, the recommendation module is further adapted to: if the enterprise dynamic of the recalled enterprise is multiple, sorting enterprise dynamic information corresponding to the recalled enterprise according to the influence value;
and screening a first preset amount of enterprise dynamic information from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored, and recommending the enterprise dynamic information to the user.
Optionally, the recommendation module is further adapted to: if the number of the recalling enterprises is multiple, screening a second preset number of the recalling enterprises from the multiple recalling enterprises according to the embedding similarity;
and aiming at any one of the screened recalling enterprises, sequencing the enterprise dynamic information corresponding to the recalling enterprise according to the influence value.
Optionally, the recommendation module is further adapted to: if the number of the recalling enterprises is multiple and the enterprise dynamic of each recalling enterprise is one, ranking the enterprise dynamic information corresponding to the plurality of recalling enterprises according to the influence value;
and taking the sequenced enterprise dynamic information as the related enterprise dynamic information of the enterprise to be monitored and recommending the related enterprise dynamic information to the user.
Optionally, the recommendation module is further adapted to: screening a third preset number of recalling enterprises from the plurality of recalling enterprises according to the embedding similarity;
and sequencing the enterprise dynamic information corresponding to the third preset number of the selected recalled enterprises according to the influence scores.
Optionally, the calculation module is further adapted to: and multiplying the embedding similarity and the dynamic score corresponding to the recalled enterprise, and taking the calculation result as the influence score of the enterprise to be monitored as the dynamic information of the enterprise.
Optionally, the calculation module is further adapted to: and determining the information type of each piece of enterprise dynamic information of the recalled enterprise, and determining a dynamic score corresponding to the enterprise dynamic information according to the information type.
Optionally, the second obtaining module is further adapted to: searching enterprises which have inter-enterprise association relation with the enterprise to be monitored in the enterprise relation graph;
calculating the Euclidean distance between the found embedded vector of the enterprise and the embedded vector of the enterprise to be monitored;
and if the Euclidean distance is smaller than or equal to the preset distance, determining the enterprise corresponding to the Euclidean distance as a recalling enterprise corresponding to the enterprise to be monitored.
The scheme provided by the embodiment of the invention realizes generalized enterprise dynamic information recommendation, and from the enterprise monitored by the user, the enterprise dynamic information of the related enterprise which is potential and possibly affects the monitored enterprise is extracted for the user, and the extracted enterprise dynamic information affecting other enterprises of the monitored enterprise is recommended to the user, so that the user can comprehensively and timely know the enterprise dynamics of the surrounding enterprises of the monitored enterprise, and the condition that the user omits the surrounding dynamics of the monitored enterprise to cause poor information is avoided.
The embodiment of the application also provides a nonvolatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the enterprise dynamic information recommendation method in any method embodiment.
Fig. 4 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor (processor) 402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408.
A communication interface 404 for communicating with network elements of other devices, such as clients or other servers.
The processor 402 is configured to execute the program 410, and may specifically execute the relevant steps in the embodiment of the enterprise dynamic information recommendation method.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU, or an Application Specific Integrated Circuit ASIC (Application Specific Integrated Circuit), or one or more Integrated circuits configured to implement an embodiment of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may be specifically configured to enable the processor 402 to execute the enterprise dynamic information recommendation method in any of the method embodiments described above. For specific implementation of each step in the program 410, reference may be made to corresponding steps and corresponding descriptions in units in the above-described enterprise dynamic information recommendation embodiment, which are not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limited to the order of execution unless otherwise specified.
Claims (13)
1. An enterprise dynamic information recommendation method comprises the following steps:
acquiring enterprises to be monitored, and acquiring a pre-constructed enterprise relationship diagram containing the enterprises to be monitored, wherein the enterprise relationship diagram is a relationship diagram constructed by taking the enterprises as nodes and taking the sum of the weights of all association relationship information among the enterprises as an edge;
acquiring an embedded vector of each enterprise in the enterprise relation graph, and acquiring a recall enterprise corresponding to the enterprise to be monitored according to the embedded vector;
and determining the related enterprise dynamic information of the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise, and recommending the related enterprise dynamic information to the user.
2. The method of claim 1, wherein the determining of the enterprise's embedded vectors comprises:
sampling the enterprise relation graph to obtain a sampling sequence of each enterprise;
and aiming at each enterprise, training the sampling sequence of the enterprise by adopting a preset natural language processing model to obtain the embedded vector of the enterprise.
3. The method of claim 1, wherein after retrieving the recalled enterprise corresponding to the enterprise to be monitored according to the embedded vector, the method further comprises:
calculating the embedding similarity between the embedding vector of the enterprise to be monitored and the embedding vector of the enterprise to be recalled;
determining dynamic scores respectively corresponding to each enterprise dynamic information of the recalled enterprises;
and calculating the influence value of the enterprise dynamic information on the enterprise to be monitored according to the embedding similarity corresponding to the recalled enterprise and the dynamic value.
4. The method of claim 3, wherein the determining and recommending to the user the enterprise dynamic information associated with the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise further comprises:
if the enterprise dynamic of the recalled enterprise is multiple, sequencing the enterprise dynamic information corresponding to the recalled enterprise according to the influence value;
and screening a first preset amount of enterprise dynamic information from the sorted enterprise dynamic information as the associated enterprise dynamic information of the enterprise to be monitored, and recommending the enterprise dynamic information to the user.
5. The method of claim 4, wherein prior to ranking business dynamic information corresponding to recalled businesses according to the impact score, the method further comprises: if the number of the recalling enterprises is multiple, screening a second preset number of the recalling enterprises from the multiple recalling enterprises according to the embedding similarity;
the sorting of the enterprise dynamic information corresponding to the recalled enterprise according to the influence score further comprises:
and aiming at any selected recalling enterprise, sequencing the enterprise dynamic information corresponding to the recalled enterprise according to the influence score.
6. The method of claim 3, wherein the determining associated business dynamic information for the business to be monitored based on the corresponding business dynamic information for the recalled business further comprises:
if the number of the recalling enterprises is multiple and the enterprise dynamic of each recalling enterprise is one, sequencing the enterprise dynamic information corresponding to the plurality of recalling enterprises according to the influence value;
and taking the sequenced enterprise dynamic information as the related enterprise dynamic information of the enterprise to be monitored and recommending the related enterprise dynamic information to the user.
7. The method of claim 6, wherein prior to ranking the business dynamics information corresponding to the plurality of recalled businesses according to the impact score, the method further comprises: screening a third preset number of recalling enterprises from the plurality of recalling enterprises according to the embedding similarity;
the step of sorting the enterprise dynamic information corresponding to each recalled enterprise according to the influence score further comprises the steps of:
and sequencing the enterprise dynamic information corresponding to the third preset number of the selected recalled enterprises according to the influence scores.
8. The method of any one of claims 3-7, wherein the calculating an impact score of the dynamic information of the business on the business to be monitored according to the embedding similarity and the dynamic score corresponding to the recalled business further comprises:
and multiplying the embedding similarity corresponding to the recalled enterprise and the dynamic score, and taking a calculation result as an influence score of the enterprise to be monitored by the dynamic information of the enterprise.
9. The method of any of claims 3-7, wherein the determining a dynamic score for each piece of business dynamic information for the recalled business further comprises:
and determining the information type of each piece of enterprise dynamic information of the recalled enterprise, and determining a dynamic score corresponding to the enterprise dynamic information according to the information type.
10. The method according to any one of claims 1-7, wherein the obtaining of the recalled enterprise corresponding to the enterprise to be monitored according to the embedded vector further comprises:
searching enterprises which have an inter-enterprise association relation with the enterprise to be monitored in the enterprise relation graph;
calculating the Euclidean distance between the found embedded vector of the enterprise and the embedded vector of the enterprise to be monitored;
and if the Euclidean distance is smaller than or equal to a preset distance, determining the enterprise corresponding to the Euclidean distance as a recalling enterprise corresponding to the enterprise to be monitored.
11. An enterprise dynamic information recommendation device, comprising:
the enterprise relationship graph is a relationship graph which is constructed by taking enterprises as nodes and taking the sum of the weights of all incidence relationship information among the enterprises as edges;
the second acquisition module is suitable for acquiring embedded vectors of all enterprises in the enterprise relation graph and acquiring the recalling enterprises corresponding to the enterprises to be monitored according to the embedded vectors;
and the recommending module is suitable for determining the related enterprise dynamic information of the enterprise to be monitored based on the enterprise dynamic information corresponding to the recalled enterprise and recommending the related enterprise dynamic information to the user.
12. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the enterprise dynamic information recommendation method according to any one of claims 1-10.
13. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the enterprise dynamic information recommendation method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211335850.8A CN115687721A (en) | 2022-10-28 | 2022-10-28 | Enterprise dynamic information recommendation method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211335850.8A CN115687721A (en) | 2022-10-28 | 2022-10-28 | Enterprise dynamic information recommendation method and device, computing equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115687721A true CN115687721A (en) | 2023-02-03 |
Family
ID=85045672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211335850.8A Pending CN115687721A (en) | 2022-10-28 | 2022-10-28 | Enterprise dynamic information recommendation method and device, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115687721A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239524A (en) * | 2017-05-26 | 2017-10-10 | 四川九洲电器集团有限责任公司 | A kind of object recommendation method and apparatus |
| CN109299362A (en) * | 2018-09-21 | 2019-02-01 | 平安科技（深圳）有限公司 | Similar enterprise's recommended method, device, computer equipment and storage medium |
| CN109919737A (en) * | 2019-03-20 | 2019-06-21 | 中电科大数据研究院有限公司 | A kind of recommended method and system of production and sales commodity |
| CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
| CN111506823A (en) * | 2020-03-11 | 2020-08-07 | 平安科技（深圳）有限公司 | Information recommendation method and device and computer equipment |
| CN113240309A (en) * | 2021-05-24 | 2021-08-10 | 量子数聚（北京）科技有限公司 | Enterprise dynamic monitoring method and device |
| CN113902546A (en) * | 2021-10-08 | 2022-01-07 | 中国农业银行股份有限公司东莞分行 | Credit risk early warning method and system based on knowledge graph |
| CN114140007A (en) * | 2021-12-07 | 2022-03-04 | 航天信息股份有限公司 | Risk enterprise identification method and device and storage medium |
| CN114519524A (en) * | 2022-02-18 | 2022-05-20 | 平安国际智慧城市科技股份有限公司 | Enterprise risk early warning method and device based on knowledge graph and storage medium |
| CN114896412A (en) * | 2022-04-27 | 2022-08-12 | 河南天眼查科技有限公司 | Embedded vector generation method, and method and device for classifying same-name personnel based on enterprise pairs |
-
2022
- 2022-10-28 CN CN202211335850.8A patent/CN115687721A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239524A (en) * | 2017-05-26 | 2017-10-10 | 四川九洲电器集团有限责任公司 | A kind of object recommendation method and apparatus |
| CN109299362A (en) * | 2018-09-21 | 2019-02-01 | 平安科技（深圳）有限公司 | Similar enterprise's recommended method, device, computer equipment and storage medium |
| CN109919737A (en) * | 2019-03-20 | 2019-06-21 | 中电科大数据研究院有限公司 | A kind of recommended method and system of production and sales commodity |
| CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
| CN111506823A (en) * | 2020-03-11 | 2020-08-07 | 平安科技（深圳）有限公司 | Information recommendation method and device and computer equipment |
| CN113240309A (en) * | 2021-05-24 | 2021-08-10 | 量子数聚（北京）科技有限公司 | Enterprise dynamic monitoring method and device |
| CN113902546A (en) * | 2021-10-08 | 2022-01-07 | 中国农业银行股份有限公司东莞分行 | Credit risk early warning method and system based on knowledge graph |
| CN114140007A (en) * | 2021-12-07 | 2022-03-04 | 航天信息股份有限公司 | Risk enterprise identification method and device and storage medium |
| CN114519524A (en) * | 2022-02-18 | 2022-05-20 | 平安国际智慧城市科技股份有限公司 | Enterprise risk early warning method and device based on knowledge graph and storage medium |
| CN114896412A (en) * | 2022-04-27 | 2022-08-12 | 河南天眼查科技有限公司 | Embedded vector generation method, and method and device for classifying same-name personnel based on enterprise pairs |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107992514B (en) | Structured information card search and retrieval | |
| US8290927B2 (en) | Method and apparatus for rating user generated content in search results | |
| CN103678418B (en) | Information processing method and message processing device | |
| US9934293B2 (en) | Generating search results | |
| CN111552870A (en) | Object recommendation method, electronic device and storage medium | |
| CN110637316B (en) | System and method for prospective object identification | |
| US20060287988A1 (en) | Keyword charaterization and application | |
| WO2018236732A1 (en) | Machine-learning system for servicing queries for digital content | |
| WO2010081238A1 (en) | Method and system for document classification | |
| WO2013192093A1 (en) | Search method and apparatus | |
| CN108153824A (en) | The determining method and device of targeted user population | |
| US20230214679A1 (en) | Extracting and classifying entities from digital content items | |
| TWI705411B (en) | Method and device for identifying users with social business characteristics | |
| JP2010039605A (en) | Person search system, person search method, program and recording medium | |
| CN116719997A (en) | Policy information pushing method and device and electronic equipment | |
| US20120059786A1 (en) | Method and an apparatus for matching data network resources | |
| CN114331698A (en) | Risk portrait generation method and device, terminal and storage medium | |
| JP7041299B1 (en) | Information processing equipment, information processing methods and information processing programs | |
| KR20170044408A (en) | System and method for recommending project | |
| CN110990701B (en) | Book searching method, computing device and computer storage medium | |
| Chen et al. | Automatic web services classification based on rough set theory | |
| CN108875014B (en) | Precise project recommendation method based on big data and artificial intelligence and robot system | |
| CN112685618A (en) | User feature identification method and device, computing equipment and computer storage medium | |
| CN116089616A (en) | Theme text acquisition method, device, equipment and storage medium | |
| JP2016197332A (en) | Information processing system, information processing method, and computer program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230801 Address after: 224008 Rooms 404-405 and 504, Building B-17-1, Big data Industrial Park, Kecheng Street, Yannan High tech Zone, Yancheng, Jiangsu Province Applicant after: Yancheng Tianyan Chawei Technology Co.,Ltd. Address before: 224008 room 501-503, building b-17-1, Xuehai road big data Industrial Park, Kecheng street, Yannan high tech Zone, Yancheng City, Jiangsu Province (CNK) Applicant before: Yancheng Jindi Technology Co.,Ltd. |