Agriculture-related popular science information analysis and targeted transmission method

Abstract

The application relates to an analysis and directional propagation method of agricultural popular science information, which comprises the following steps: judging whether a directional propagation demand is triggered; if the directional propagation demand is triggered, determining target agricultural popular science information to be propagated and a propagation object; determining other objects related to the propagation object according to a relationship graph; and propagating the target agricultural popular science information to the propagation object and the other objects. The method provided by the application can actively determine a propagation object of agricultural popular science information according to a relationship graph, and propagate the agricultural popular science information to the propagation object, so that active propagation of the agricultural popular science information is realized, the propagation range is expanded, and the propagation effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the computer technical field, and particularly relates to an analysis and directional propagation method of agricultural popular science information. BACKGROUND

[0002] In recent years, the development of information technology has made great progress, and agricultural informatization construction is the top priority in the construction of modern agriculture in China.

[0003] Agricultural popular science information can help agricultural workers improve their agricultural knowledge reserves and assist them in making timely and accurate agricultural production decisions. Therefore, the propagation of agricultural popular science information is extremely important.

[0004] Traditional agricultural popular science information propagation mainly adopts a passive propagation mode, that is, agricultural popular science information is published on a fixed website (such as a government propaganda website), and when a user (such as an agricultural worker) needs to obtain agricultural popular science information, the user logs in to the fixed website to query the information.

[0005] The traditional mode relies on the user's self-query to realize the propagation of agricultural popular science information, and the propagation effect is only for the existing query users, the propagation range is small, and the propagation effect is poor. SUMMARY

[0006] (I) Technical problems to be solved

[0007] In order to solve the above problems, the present application provides an analysis and directional propagation method of agricultural popular science information.

[0008] (II) Technical scheme

[0009] In order to achieve the above purpose, the main technical scheme adopted by the present application includes:

[0010] An analysis and directional propagation method of agricultural popular science information, the method comprising:

[0011] determining whether a directional propagation demand is triggered;

[0012] if triggered, determining target agricultural popular science information to be propagated and a propagation object;

[0013] determining other objects related to the propagation object according to a relationship graph;

[0014] propagating the target agricultural popular science information to the propagation object and the other objects.

[0015] Optionally, determining whether a directional propagation demand is triggered comprises:

[0016] if a query request sent by any user is received, it is determined that the directional propagation demand is triggered;

[0017] determining target agricultural science popularization information to be propagated and a propagation object, comprising:

[0018] determining the agricultural science popularization information involved in the query request as the target agricultural science popularization information;

[0019] determining any user as the propagation object.

[0020] Optionally, the method further comprises:

[0021] if it is confirmed that there is new agricultural science popularization information to be propagated, it is determined that the demand for targeted propagation is triggered;

[0022] determining target agricultural science popularization information to be propagated and a propagation object, comprising:

[0023] determining the new agricultural science popularization information to be propagated as the target agricultural science popularization information;

[0024] determining the user involved in the new agricultural science popularization information to be propagated as the propagation object.

[0025] Optionally, the method further comprises:

[0026] acquiring new agricultural science popularization information in real time;

[0027] determining, among the current stored agricultural science popularization information, comparison agricultural science popularization information belonging to the same category as the new agricultural science popularization information;

[0028] extracting a feature vector of the new agricultural science popularization information ;

[0029] determining a similarity between the feature vector of the comparison agricultural science popularization information and the feature vector of the new agricultural science popularization information ; wherein, is an identifier of the comparison agricultural science popularization information; if

[0030] the similarity threshold value, it is determined that the new agricultural science popularization information is not new agricultural science popularization information to be propagated; if

[0031] the similarity threshold value, performing word segmentation on the new agricultural science popularization information, determining whether each segmented word is an entity segmented word, and determining an entity type corresponding to each entity segmented word; determining the value of the new agricultural science popularization information according to the entity segmented word and the corresponding entity type; when the propagation threshold value, and the value of the new agricultural science popularization information is not less than the value threshold value, it is determined that the new agricultural science popularization information is new agricultural science popularization information to be propagated, and the new agricultural science popularization information is stored; otherwise, it is determined that the new agricultural science popularization information is not new agricultural science popularization information to be propagated. ​

[0032] Optionally, the value of the new agricultural science popularization information is determined according to the entity segmentation and the corresponding entity type, and the value of the new agricultural science popularization information comprises:

[0033] According to determine the regional similarity of the new agricultural science popularization information ;

[0034] determine the publisher value of the new agricultural science popularization information ;

[0035] determine the value of the new agricultural science popularization information ; wherein, is the regional weight, is the entity segmentation quantity weight, is the entity segmentation type weight, is the total number of entity segmentations, is the total number of segmentations of the new agricultural science popularization information, is the number of entity types corresponding to all entity segmentations, is the number of entity types corresponding to the entity segmentations in the most similar comparison agricultural science popularization information.

[0036] Optionally, if the similarity threshold, the new agricultural science popularization information is determined to be the new agricultural science popularization information to be propagated after the most similar comparison agricultural science popularization information, and the method further comprises:

[0037] determine the publisher value of the new agricultural science popularization information , and the publisher value of the most similar comparison agricultural science popularization information ;

[0038] identify the semantics of the new agricultural science popularization information, and the semantics of the most similar comparison agricultural science popularization information;

[0039] determine the similarity between the semantics of the new agricultural science popularization information and the semantics of the most similar comparison agricultural science popularization information ;

[0040] If the semantic threshold, and , the most similar comparison agricultural science popularization information is updated to the new agricultural science popularization information.

[0041] Optionally, the relationship graph is composed of a plurality of points and edges;

[0042] Each point corresponds to a unique user;

[0043] If there is a relationship between two users, there is an edge between the points corresponding to the two users;

[0044] Each edge has an edge weight;

[0045] wherein the edge weight of any side , is an edge identifier, is an edge the number of agricultural popular science information co-browsed by the users corresponding to the two points connected, is an edge the total number of agricultural popular science information browsed by the user corresponding to one point connected, is an edge the total number of agricultural popular science information browsed by the user corresponding to the other point connected, is an edge the number of messages sent by the user corresponding to one point connected to the user corresponding to the other point connected, is an edge the number of messages sent by the user corresponding to the other point connected to the user corresponding to one point connected, is an edge the total number of messages sent by the user corresponding to one point connected, is an edge the total number of messages sent by the user corresponding to the other point connected, is an edge the time parameter of the users corresponding to the two points connected.

[0046] Optionally, ;

[0047] wherein, is an edge the active duration of the user corresponding to one point connected, is an edge the active duration of the user corresponding to the other point connected, is an edge the registration duration of the user corresponding to one point connected, is an edge the registration duration of the user corresponding to the other point connected.

[0048] Optionally, according to the relationship graph, other objects related to the propagation object are determined, including:

[0049] determining a target node in the relationship graph according to the propagation object;

[0050] taking the target node as a selection node;

[0051] determining other nodes having edges with the selection node; wherein the other nodes are non-selection nodes;

[0052] determining the similarity between the users corresponding to each other node and the propagation object ; wherein, is an other node identifier, other nodes the similarity between the user corresponding to the other nodes and the propagation object;

[0053] determining the stop value of each other node ; wherein, other nodes the number of edges between the target node and the other nodes, other nodes the identification of the edges between the target node and the other nodes, edges the maximum value of the number of edges between the two points connected and the target node;

[0054] If the stop value of a certain other node is not less than the stop threshold value, the other node is taken as a new selection node, and the steps of determining the other nodes having edges with the selection node and the subsequent steps are repeatedly executed; if all other nodes are stop nodes, the users corresponding to all selection nodes are other objects related to the propagation object;

[0055] wherein the stop values of the stop nodes are all less than the stop threshold value, or the stop nodes have no other nodes having edges.

[0056] Optionally, according to the propagation object, the target node is determined in the relationship graph, comprising:

[0057] If the point corresponding to the propagation object exists in the relationship graph, the point is determined as the target node;

[0058] If the point corresponding to the propagation object does not exist in the relationship graph, the similarity between the user corresponding to each node in the relationship graph and the propagation object is determined, and the point with the maximum similarity is determined as the target node.

[0059] (Three) beneficial effects

[0060] The present application relates to an analysis and directional propagation method of agricultural science popularization information, which comprises: judging whether the directional propagation demand is triggered; if triggered, determining the target agricultural science popularization information to be propagated and the propagation object; according to the relationship graph, determining the other objects related to the propagation object; propagating the target agricultural science popularization information to the propagation object and the other objects. The method provided by the present application can actively determine the propagation object of the agricultural science popularization information according to the relationship graph, and propagate the agricultural science popularization information to the propagation object, so as to realize the active propagation of the agricultural science popularization information, expand the propagation range, and improve the propagation effect. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 It is a flowchart of an analysis and directional propagation method of agricultural science popularization information provided by an embodiment of the present application;

[0062] Figure 2 A relationship graph schematic diagram provided for an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to better explain the present application, in order to facilitate understanding, the present application is described in detail below through specific embodiments in combination with the accompanying drawings.

[0064] The traditional popular agricultural information dissemination is mainly in the form of passive dissemination, that is, the popular agricultural information is published in a fixed website (such as a government propaganda website), and when a user (such as an agricultural worker) needs to obtain the popular agricultural information, the user logs in the fixed website to query by himself. The traditional method relies on the user's self-query to realize the dissemination of the popular agricultural information, and the dissemination effect is poor because the dissemination range is small.

[0065] Therefore, the present application relates to a method for analyzing and targeting the dissemination of popular agricultural information, which comprises: judging whether the targeting dissemination demand is triggered; if triggered, determining the target popular agricultural information to be disseminated and the dissemination object; determining other objects related to the dissemination object according to the relationship graph; and disseminating the target popular agricultural information to the dissemination object and the other objects. The method provided by the present application can actively determine the dissemination object of the popular agricultural information according to the relationship graph, and disseminate the popular agricultural information to the dissemination object, thereby realizing the active dissemination of the popular agricultural information, expanding the dissemination range, and improving the dissemination effect.

[0066] Referring to Figure 1 The present embodiment provides a method for analyzing and targeting the dissemination of popular agricultural information, and the implementation process of the method is as follows:

[0067] 101, judging whether the targeting dissemination demand is triggered.

[0068] For example, if a query request sent by any user is received, it is judged that the targeting dissemination demand is triggered. Alternatively, if it is confirmed that there is new popular agricultural information to be disseminated, it is judged that the targeting dissemination demand is triggered.

[0069] That is, the targeting dissemination demand is triggered when a user (such as a farmer) queries, or the targeting dissemination demand is triggered when there is new popular agricultural information to be disseminated.

[0070] 102, if triggered, determining the target popular agricultural information to be disseminated and the dissemination object.

[0071] Different triggering modes correspond to different determination schemes.

[0072] For example, if it is determined in step 101 that the demand for targeted propagation is triggered when a query request sent by any user is received, the agricultural science popularization information involved in the query request is determined as the target agricultural science popularization information, and any user is determined as the propagation object in step 102.

[0073] For another example, if it is determined in step 101 that the demand for targeted propagation is triggered when it is confirmed that there is new agricultural science popularization information to be propagated, the new agricultural science popularization information to be propagated is determined as the target agricultural science popularization information, and the user involved in the new agricultural science popularization information to be propagated is determined as the propagation object in step 102.

[0074] The user involved in the new agricultural science popularization information to be propagated can be the user involved in the content of the new agricultural science popularization information to be propagated. For example, if the new agricultural science popularization information to be propagated is the XXXX of a wheat grower, the user involved in the new agricultural science popularization information to be propagated is the wheat grower. For another example, if the new agricultural science popularization information to be propagated is the XXXX of a corn, the user involved in the new agricultural science popularization information to be propagated is the corn-related user (such as a grower, a transportation personnel, etc.). The user involved in the new agricultural science popularization information to be propagated can also be the user involved in the surrounding of the new agricultural science popularization information to be propagated, such as a registered user of a platform for publishing the new agricultural science popularization information to be propagated, a user who follows a publisher of the new agricultural science popularization information to be propagated, etc.

[0075] In addition, the new agricultural science popularization information to be propagated is not all new agricultural science popularization information, but agricultural science popularization information that is valuable for propagation. For example, the new agricultural science popularization information to be propagated is determined through the following process:

[0076] 1. Real-time acquisition of new agricultural science popularization information.

[0077] For example, when a user uploads a new agricultural science popularization information, the new agricultural science popularization information is acquired.

[0078] 2. In the currently stored agricultural science popularization information, determine the comparison agricultural science popularization information belonging to the same category as the new agricultural science popularization information.

[0079] When the new agricultural science popularization information is uploaded, its category is determined, such as pest prevention, science popularization, etc. The comparison agricultural science popularization information of the same category is found in this step.

[0080] Furthermore, the agricultural science popularization information currently stored is valuable, not all agricultural science popularization information. In other words, the method provided in this embodiment maintains a valuable agricultural science popularization information database in real time. Whenever new valuable agricultural science popularization information is disseminated, it is added to this database. This step then searches for and compares agricultural science popularization information of the same category from this database.

[0081] 3. Extract feature vectors from new agricultural science popularization information. .

[0082] 4. Compare the feature vectors of agricultural science popularization information similarity between .

[0083] in, To compare agricultural science popularization information labels.

[0084] Similarity is determined using existing calculation methods.

[0085] 5. According to Identify new agricultural science information to be disseminated.

[0086] 1) If The similarity threshold indicates that the new agricultural science popularization information is very similar to the agricultural science popularization information that has already been stored. Since similar agricultural science popularization information has already been stored and disseminated in the database, the new agricultural science popularization information will no longer be disseminated. Therefore, it is determined that the new agricultural science popularization information is not a new agricultural science popularization information to be disseminated.

[0087] Furthermore, after determining that the new agricultural science popularization information is not new agricultural science popularization information to be disseminated, because it is very similar to the stored agricultural science popularization information, it will be determined whether to replace the stored agricultural science popularization information to ensure that the stored agricultural science popularization information is up-to-date. The determination process is as follows:

[0088] (1) Determine the value of the publisher of new agricultural science popularization information And the value of the publishers of agricultural science popularization information with the highest similarity. .

[0089] This value can be realized through existing methods, such as based on whether the publisher is certified or the number of information the publisher has already published. The publisher's value reflects the dissemination value of new agricultural science information. The lower the publisher's value, the lower the dissemination value of the new agricultural science information (e.g., the lower the authenticity, the less valuable the information), and the less likely the new agricultural science information is to be disseminated.

[0090] (2) identifying the semantics of the new agricultural science popularization information and the semantics of the most similar comparison agricultural science popularization information.

[0091] The existing semantic identification scheme can be used to identify the semantics of the agricultural science popularization information.

[0092] (3) determining the similarity between the semantics of the new agricultural science popularization information and the semantics of the most similar comparison agricultural science popularization information .

[0093] The existing similarity calculation scheme can be used to calculate the similarity .

[0094] (4) if the semantic threshold value, and , it means that the semantics of the new agricultural science popularization information and the stored comparison agricultural science popularization information are similar, and the publisher of the new agricultural science popularization information is more valuable than the publisher of the stored comparison agricultural science popularization information. Therefore, the most similar comparison agricultural science popularization information will be updated to the new agricultural science popularization information.

[0095] The semantic threshold value is a pre-set value.

[0096] 2) if the similarity threshold value, it means that there is no similar agricultural science popularization information in the current library to the new agricultural science popularization information, so the new agricultural science popularization information may be valuable to spread. At this time, the following judgment will be made:

[0097] 201, performing word segmentation on the new agricultural science popularization information to determine whether each word segmentation is an entity word segmentation and to determine the entity type corresponding to each entity word segmentation.

[0098] The entity word segmentation is a word segmentation that can reflect the actual meaning, such as nouns, etc. In specific implementation, a white list of word types can be set. If the word type of a word segmentation is in the white list, it is an entity word segmentation, and the corresponding word type and entity type.

[0099] 202, determining the value of the new agricultural science popularization information according to the entity word segmentation and the corresponding entity type.

[0100] (1) determining the regional similarity of the new agricultural science popularization information according to .

[0101] This step determines the regional similarity by using the existing scheme . The regional similarity reflects whether the new agricultural science popularization information is related to the current region. The more relevant it is, the more likely it is to be the agricultural science popularization information to be spread. ​

[0102] (2) Determine the value of the new agricultural science popularization information publisher .

[0103] The value can be achieved by existing methods, such as whether the publisher has been authenticated, the number of information published by the publisher, etc. The publisher value reflects the dissemination value of the new agricultural science popularization information. If the publisher value is smaller, the dissemination value of the new agricultural science popularization information is lower (such as lower authenticity, smaller valuable information of the new agricultural science popularization information, etc.), and the new agricultural science popularization information is less likely to be the agricultural science popularization information to be disseminated.

[0104] (3) Determine the value of the new agricultural science popularization information .

[0105] Among them, is the regional weight, is the entity word quantity weight, is the entity word type weight, is the total number of entity words, is the total number of entity words of the new agricultural science popularization information, is the number of entity types corresponding to all entity words, is the number of entity types corresponding to the entity words in the most similar comparison agricultural science popularization information.

[0106] , , can be set in advance.

[0107] The larger, the more similar the region. The larger the value, the greater the dissemination value of the new agricultural science popularization information. Reflects the proportion of entity words in the new agricultural science popularization information. The larger the value, the more entity words included in the new agricultural science popularization information, representing the greater dissemination value of the new agricultural science popularization information. is the similarity of the entity words of the new agricultural science popularization information and the entity words of the possible dissemination agricultural science popularization information (i.e. the most similar comparison agricultural science popularization information). The larger the value, the more similar, the more likely to be disseminated. Therefore, embodies the value of the new agricultural science popularization information.

[0108] 203, when the dissemination threshold, and the value of the new agricultural science popularization information is not less than the value threshold, The similarity between the new agricultural science popularization information and the compared agricultural science popularization information fluctuates greatly, that is, the similarity of the compared agricultural science popularization information may differ greatly, indicating that it is not similar to the already spread agricultural science popularization information (i.e., the agricultural science popularization information stored in the library), and the fluctuation is relatively large, but the value of the new agricultural science popularization information is relatively high, that is, similar agricultural science popularization information has not been spread at present, but the value of the new agricultural science popularization information is high, so it needs to be spread, and therefore the new agricultural science popularization information is determined as new agricultural science popularization information to be spread, and the new agricultural science popularization information is stored (i.e., the new agricultural science popularization information is stored in the library).

[0109] Otherwise, the new agricultural science popularization information is determined as non-new agricultural science popularization information to be spread.

[0110] 103. According to the relationship graph, determine other objects related to the spread object.

[0111] The relationship graph is also pre-established and maintained in real time.

[0112] As shown in Figure 2 , the relationship graph is composed of multiple points and edges. Each point corresponds to a unique user. If there is a relationship between two users, there is an edge between the points corresponding to the two users.

[0113] Each edge has an edge weight.

[0114] The edge weight of any edge is .

[0115] The edge identifier is , the edge connecting the two points corresponding to the users browses the number of agricultural science popularization information, the edge connecting one point corresponds to the total number of agricultural science popularization information browsed by the user, the edge connecting the other point corresponds to the total number of agricultural science popularization information browsed by the user, the edge connecting one point corresponds to the number of messages sent by the user to the other point, the edge connecting the other point corresponds to the number of messages sent by the user to the one point, the edge connecting one point corresponds to the total number of messages sent by the user, the edge connecting the other point corresponds to the total number of messages sent by the user, the edge connecting the two points corresponds to the time parameters of the users.

[0116] .

[0117] in, For the edge The valid duration of a user corresponding to a connection point. For the edge The valid duration of the user corresponding to the other point of connection. For the edge The registration duration of a user corresponding to a connection point. For the edge The registration duration of the user corresponding to the other point of the connection.

[0118] For example, the edge between point 3 and point 10, This represents the number of agricultural science information posts viewed by users corresponding to points 3 and 10 connected by this edge. This represents the total number of agricultural science popularization information viewed by the user corresponding to point 3. This represents the total number of agricultural science popularization information viewed by the user corresponding to point 10. The number of messages sent from the user at point 3 to the user at point 10. The number of messages sent from the user at point 10 to the user at point 3. The total number of messages sent to the user corresponding to point 3. The total number of messages sent to the user corresponding to point 10. For the edge The time parameters of the users corresponding to the two connected points.

[0119] This characterizes the similarity between the users corresponding to points 3 and 10. This characterizes the level of communication between the users corresponding to points 3 and 10. This represents the activity level of the users corresponding to points 3 and 10. Edge weights This represents the propagation value between the users corresponding to points 3 and 10.

[0120] The implementation process of step 103 is as follows:

[0121] 103-1, Based on the target of the propagation, determine the target node in the relationship graph.

[0122] For example, if a point in the relationship graph corresponds to the object being propagated, that point is identified as the target node. If a point in the relationship graph does not correspond to the object being propagated, the similarity between each node in the relationship graph and the object being propagated is determined, and the point with the highest similarity is identified as the target node.

[0123] 103-2, taking the target node as a selection node.

[0124] 103-3, determining other nodes having edges with the selection node.

[0125] wherein the other nodes are non-selection nodes.

[0126] 103-4, determining similarity between users corresponding to the other nodes and the propagation object.

[0127] wherein, identifying the other nodes, the similarity between users corresponding to the other nodes and the propagation object.

[0128] 103-5, determining a stop value of each of the other nodes.

[0129] wherein, the number of edges between the other nodes and the target node, identifying the number of edges between the other nodes and the target node, the maximum value of the number of edges between the two points connected by the edge and the target node.

[0130] 103-6, if the stop value of one of the other nodes is not less than the stop threshold value, taking the other node as a new selection node, and repeating the step of determining other nodes having edges with the selection node and the subsequent steps (i.e., repeating steps 103-3 to 103-6). If all of the other nodes are stop nodes, then the users corresponding to all of the selection nodes are other objects related to the propagation object.

[0131] wherein the stop values of the stop nodes are all less than the stop threshold value, or the stop nodes have no other nodes having edges.

[0132] For example, in step 103-1, the target node is determined to be point 4. In step 103-2, point 4 is taken as a selection node. In step 103-3, other nodes (i.e., point 1 and point 9) having edges with point 4 are determined. In step 103-4, the similarity between the user corresponding to point 1 and the propagation object is determined , and the similarity between the user corresponding to point 9 and the propagation object is determined . In step 103-5, the stop value of point 1 is determined and the stop value of point 9 is determined . If it is determined in step 106-6 that is not less than the stop threshold value, ​​​​​​If the similarity is not less than the stop threshold value, then both point 1 and point 9 are taken as new selection nodes, step 103-3 is repeated to determine other nodes having edges with point 9, since point 9 has no other nodes, point 9 is a stop node, the processing is stopped, step 103-3 is repeated to determine other nodes having edges with point 1 (i.e. point 2 and point 5). , the similarity between the user corresponding to point 2 and the propagation object , and the similarity between the user corresponding to point 5 and the propagation object is determined in step 103-5. If it is determined in step 106-6 that the similarity is not less than the stop threshold value, but is less than the stop threshold value, then point 5 is a stop node, the processing is stopped (but point 5 will not be taken as a new selection node). Point 2 is taken as a new selection node, step 103-3 is repeated to determine other nodes having edges with point 2, since point 2 has no other nodes, point 2 is a stop node, the processing is stopped.

[0133] The users corresponding to all the selection nodes (i.e. point 4, point 9, point 1, point 2) are other objects related to the propagation object.

[0134] 104, the target agricultural science popularization information is propagated to the propagation object and the other objects.

[0135] This step can adopt an existing propagation scheme, such as pushing the target agricultural science popularization information to the users in the form of a message.

[0136] The embodiment provides an analysis and directional propagation method of agricultural science popularization information, determines whether a directional propagation demand is triggered, determines target agricultural science popularization information to be propagated and a propagation object if the directional propagation demand is triggered, determines other objects related to the propagation object according to a relationship graph, and propagates the target agricultural science popularization information to the propagation object and the other objects. The method provided in the embodiment can actively determine a propagation object of agricultural science popularization information according to a relationship graph, and propagate the agricultural science popularization information to the propagation object, so that active propagation of the agricultural science popularization information is realized, the propagation range is expanded, and the propagation effect is improved.

[0137] It should be noted that the present application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order of the steps, after understanding the spirit of the present application.

[0138] ​It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in an order different from the embodiments, or several steps can be performed simultaneously.

[0139] Finally, it should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An analysis and targeted propagation method of agricultural popular science information, characterized in that, The method comprises: determining whether a directional propagation demand is triggered; if triggered, determining target agricultural science popularization information to be propagated and a propagation object; determining other objects related to the propagation object according to a relationship graph; propagating the target agricultural science popularization information to the propagation object and the other objects; wherein the relationship graph is composed of multiple points and edges; each point corresponds to a unique user; if there is a relationship between two users, there is an edge between the points corresponding to the two users; each edge has an edge weight; wherein the edge weight of any side , is an edge identifier, is an edge the number of agricultural popular science information that the users corresponding to the two points of the connection jointly browse, is an edge the total number of agricultural popular science information that the user corresponding to one point of the connection browses, is an edge the total number of agricultural popular science information that the user corresponding to the other point of the connection browses, is an edge the number of messages that the user corresponding to one point of the connection sends to the user corresponding to the other point of the connection, is an edge the number of messages that the user corresponding to the other point of the connection sends to the user corresponding to one point of the connection, is an edge the total number of messages that the user corresponding to one point of the connection sends, is an edge the total number of messages that the user corresponding to the other point of the connection sends, is an edge the time parameter of the users corresponding to the two points of the connection; determining other nodes having edges with the selection node, wherein the other nodes are non-selection nodes; if the stop value of a certain other node is not less than a stop threshold, the other node is taken as a new selection node, and the step of determining other nodes having edges with the selection node and subsequent steps are repeated; if all other nodes are stop nodes, the users corresponding to all selection nodes are other objects related to the propagation object; wherein the stop value of a stop node is less than the stop threshold, or a stop node has no other nodes having edges. The determination of whether the directional propagation demand is triggered comprises: determining a similarity between a user corresponding to each other node and the propagation object ; wherein, identifying other nodes, other nodes corresponding to a user and the propagation object; determining a stop value for each other node ; wherein, is the other node the number of edges between the other node and the target node, is the other node the identification of the edge between the other node and the target node, is the edge connecting the two points and the maximum number of edges between the other node and the target node; is the edge the edge weight of the edge; if a query request sent by any user is received, it is determined that the directional propagation demand is triggered. The determination of the target agricultural science popularization information to be propagated and the propagation object comprises:

2. The method of claim 1, wherein, the agricultural science popularization information involved in the query request is determined as the target agricultural science popularization information; the any user is determined as the propagation object. The determination of whether the directional propagation demand is triggered comprises: if it is confirmed that there is new agricultural science popularization information to be propagated, it is determined that the directional propagation demand is triggered. The determination of the target agricultural science popularization information to be propagated and the propagation object comprises:

3. The method of claim 1, wherein, the new agricultural science popularization information to be propagated is determined as the target agricultural science popularization information; the user involved in the new agricultural science popularization information to be propagated is determined as the propagation object. The method further comprises: real-time acquisition of new agricultural science popularization information; determination of comparison agricultural science popularization information belonging to the same category as the new agricultural science popularization information from currently stored agricultural science popularization information; 4. The method of claim 3, wherein, The determination of the value of the new agricultural science popularization information according to the entity segmentation and the corresponding entity type comprises: identification of the semantics of the new agricultural science popularization information and the semantics of the comparison agricultural science popularization information with the highest similarity; The determination of the target node in the relationship graph according to the propagation object comprises: Extracting a new feature vector of agricultural science popularization information ; determining a similarity between the feature vector of the agricultural popular science information and the feature vector of the comparison agricultural popular science information ; wherein the comparison agricultural popular science information is identified by the comparison agricultural popular science information identifier ; like If a similarity threshold is used, it is determined that the new agricultural science popularization information is not new agricultural science popularization information to be disseminated; If If the similarity is less than the similarity threshold, the new agricultural science popularization information is segmented, it is determined whether each segmented word is an entity segmented word, and an entity type corresponding to each entity segmented word is determined. The value of the new agricultural science popularization information is determined according to the entity segmented word and the corresponding entity type. If the similarity is less than the similarity threshold, the new agricultural science popularization information is segmented, it is determined whether each segmented word is an entity segmented word, and an entity type corresponding to each entity segmented word is determined. The value of the new agricultural science popularization information is determined according to the entity segmented word and the corresponding entity type. If the similarity is less than the similarity threshold, the new agricultural science popularization information is segmented, it is determined whether each segmented word is an entity segmented word, and an entity type corresponding to each entity segmented word is determined. The value of the new agricultural science popularization information is determined according to the entity segmented word and the corresponding entity type. If the similarity is less than the similarity threshold, the new agricultural science popularization information is segmented, it is determined whether each segmented word is an entity segmented word, and an entity type corresponding to each entity segmented word is determined. The value of the new agricultural science popularization information is determined according to the entity segmented word and the corresponding entity type.

5. The method of claim 4, wherein, if the point corresponding to the propagation object exists in the relationship graph, the point is determined as the target node; According to the method determining the regional similarity of the new agricultural science popularization information ; Determining the value of a new publisher of agricultural science popularization information ; determining the value of the new agricultural science popularization information ; wherein, is a regional weight, is an entity word segmentation quantity weight, is an entity word segmentation type weight, is the total number of entity word segmentations, is the total number of word segmentations of the new agricultural science popularization information, is the number of entity types corresponding to all entity word segmentations, is the number of entity types corresponding to the entity word segmentations in the most similar comparison agricultural science popularization information.

6. The method of claim 4, wherein, If If the similarity between the new agricultural science popularization information and the existing agricultural science popularization information is less than the similarity threshold, the determining that the new agricultural science popularization information is the agricultural science popularization information to be propagated further includes: Determine the release value of the new agricultural science popularization information , and the release value of the most similar comparison agricultural science popularization information ; if the point corresponding to the propagation object does not exist in the relationship graph, the similarity between each node corresponding to the propagation object is determined, and the point with the highest similarity is determined as the target node. determine a similarity between the semantics of the new agriculture-related popular science information and the semantics of the agriculture-related popular science information with the greatest similarity ; If the semantic threshold, and the comparison of the agricultural science popularization information with the greatest similarity is updated to the new agricultural science popularization information.

7. The method of claim 1, wherein, The ; wherein, is an edge the effective duration of the user corresponding to one point of the connection, is an edge the effective duration of the user corresponding to the other point of the connection, is an edge the registration duration of the user corresponding to one point of the connection, is an edge the registration duration of the user corresponding to the other point of the connection.

8. The method of claim 1, wherein, ​ ​ ​

Images