Data processing method and device, equipment and medium

Abstract

The embodiment of the invention discloses a data processing method and device, equipment and a medium. The method can be applied to scenes such as cloud technology, artificial intelligence, intelligent traffic and auxiliary driving. According to historical propagation data of the historical information propagation task, determining a first threshold probability that each object in the interaction graph becomes an information propagator and a second threshold probability that each object becomes an information invitee; determining a first random probability that each object in the interaction graph becomes an information propagator of the information to be propagated; determining the object of which the first random probability is greater than a first threshold probability as an information propagation object, and sending the to-be-propagated information to the information propagation object; determining a to-be-propagated object of each information propagation object in the plurality of objects, and determining a second random probability that each to-be-propagated object becomes an information invitee of the to-be-propagated information; and determining the object of which the second random probability is greater than a second threshold probability as a predicted propagation object, and propagating the to-be-propagated information to the predicted propagation object.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet, and particularly relates to a data processing method and device, equipment and medium. BACKGROUND

[0002] Network socialization is a main way of information dissemination. When some information needs to be promoted, the information needs to be spread through social networks to achieve the promotion of the information.

[0003] In the related art, a traditional propagation model is used to propagate information, so as to promote the information to multiple objects. When the information is propagated by using the traditional propagation model, each object is a propagation node. When a propagation node propagates information, the propagation node needs to propagate information according to the propagation probability between other nodes adjacent to the propagation node, for example, the next propagation node with a large propagation probability is selected as a propagation object of the information by the current propagation node.

[0004] When the information is propagated through network socialization, the behavior of an object actively propagating information through a social network is involved. One object can propagate information to multiple objects, and multiple objects can propagate information to one object. The propagation model in the related art does not consider this, so that the effect of information propagation prediction is poor, which does not meet the actual information propagation demand. SUMMARY

[0005] Embodiments of the present application provide a data processing method, device, equipment and medium. The effect of information propagation prediction can be improved.

[0006] According to an aspect of the present application, the embodiments of the present application provide a data processing method, comprising:

[0007] obtaining historical propagation data recorded in a historical information propagation task, and determining a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an invited information in the interaction graph according to the historical propagation data, the interaction graph comprising nodes generated for each object and edge connection structures between different nodes;

[0008] determining a first random probability of each object in the interaction graph becoming an information propagator of to-be-propagated information;

[0009] determining an object in the multiple objects whose first random probability is greater than the first threshold probability as an information propagation object, and sending the to-be-propagated information to the information propagation object;

[0010] determining a to-be-propagated object corresponding to each information propagation object in the multiple objects, and determining a second random probability of each to-be-propagated object becoming an invited information of the to-be-propagated information;

[0011] An object in the to-be-propagated objects with a second random probability greater than a second threshold probability is determined as a predicted propagation object, and the to-be-propagated information is propagated to the predicted propagation object.

[0012] According to an aspect of the present application, an embodiment of the present application provides a data processing apparatus, comprising:

[0013] The acquisition module is configured to acquire historical propagation data recorded under a historical information propagation task, and determine, according to the historical propagation data, a first threshold probability of each object in the interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee, the interaction graph comprising nodes generated for each object and edge connection structures between different nodes.

[0014] The first determination module is configured to determine a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information.

[0015] The second determination module is configured to determine, from the plurality of objects, an object with a first random probability greater than the first threshold probability as an information propagator, and send the to-be-propagated information to the information propagator.

[0016] The third determination module is configured to determine, from the plurality of objects, a to-be-propagated object corresponding to each information propagator, and determine a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information.

[0017] The propagation module is configured to determine, from the to-be-propagated objects, an object with a second random probability greater than a second threshold probability as a predicted propagation object, and propagate the to-be-propagated information to the predicted propagation object.

[0018] In some embodiments, the acquisition module comprises a first sub-acquisition module, which is configured to:

[0019] According to the historical propagation data, determine at least one target object type corresponding to the historical information propagator, and a first distribution probability of each target object type in all target object types.

[0020] According to the historical propagation data, determine a second distribution probability of the historical information propagator in the objects.

[0021] According to the historical propagation data, determine a third distribution probability of each object type corresponding to the object in all object types.

[0022] Determine, as the first threshold probability of each object in the interaction graph becoming an information propagator, a ratio of a product of the first distribution probability and the second distribution probability to the third distribution probability.

[0023] In some embodiments, the obtaining module is a second sub-obtaining module, and the second sub-obtaining module comprises a first determining unit, a second determining unit, a third determining unit and a fourth determining unit;

[0024] The first determining unit is configured to determine, according to the historical propagation data, a propagation list corresponding to a historical information propagator and a number of historical information invitees corresponding to each invited location in the propagation list;

[0025] The number of historical information invitees corresponding to each invited location is divided by the total number of historical information invitees to obtain a first location distribution probability of each invited location in all invited locations;

[0026] The second determining unit is configured to determine, according to the historical propagation data, a propagation distribution probability of the historical information invitees in all historical invitees corresponding to the historical information propagator;

[0027] The third determining unit is configured to determine, in the propagation list, a second location distribution probability of each invited location in all invited locations in the propagation list;

[0028] The fourth determining unit is configured to determine, as a second threshold probability of each object in the interaction graph becoming an information invitee, a ratio of a product of the first location distribution probability and the propagation distribution probability to the second location distribution probability.

[0029] In some embodiments, the second determining unit is configured to:

[0030] According to the historical propagation data, determine a first number of historical information propagators and a second number of invited locations in a propagation list corresponding to each historical information propagator, each invited location corresponding to a historical invitee;

[0031] Determine, as the total number of historical invitees, a product of the first number and the second number;

[0032] According to the historical propagation data, determine a third number of historical information invitees;

[0033] Divide the third number by the total number of historical invitees to obtain a propagation distribution probability of the historical information invitees in all historical invitees.

[0034] In some embodiments, the data processing apparatus further comprises a fourth determining module configured to:

[0035] According to the historical propagation data, determine a number of historical information invitees and a number of target historical information invitees who view historical information;

[0036] The target historical information inviter number is divided by the historical information inviter number to obtain a third threshold probability of each object in the interaction graph becoming an information viewer.

[0037] In some embodiments, the data processing apparatus further comprises an object determination module configured to:

[0038] After the to-be-propagated information is propagated to the predicted propagation object, a third random probability of each predicted propagation object becoming an information viewer of the to-be-propagated information is determined.

[0039] Among the plurality of predicted propagation objects, an object with a third random probability greater than the third threshold probability is determined as a predicted participant object viewing the to-be-propagated information.

[0040] In some embodiments, the object determination module is further configured to:

[0041] After the predicted participant object viewing the to-be-propagated information is determined among the plurality of predicted propagation objects, the predicted participant object is replaced with a new information propagation object, and

[0042] and returns to determine, among the plurality of objects, a second random probability of each information propagation object corresponding to the to-be-propagated object becoming an information inviter of the to-be-propagated information until a new predicted participant object cannot be determined.

[0043] In some embodiments, the data processing apparatus further comprises a propagation effect determination module configured to:

[0044] When a new predicted participant object cannot be determined, a predicted propagation number corresponding to the to-be-propagated information is determined.

[0045] According to the propagation relationship between the information propagation object and the predicted propagation object, a predicted propagation path corresponding to the to-be-propagated information is determined, and a path propagation number corresponding to each predicted propagation path is determined.

[0046] The predicted propagation number and the path propagation number are determined as a predicted propagation result corresponding to the to-be-propagated information.

[0047] In some embodiments, the propagation effect determination module is further configured to:

[0048] Obtain a predicted propagation number of the to-be-propagated information;

[0049] Statistical total propagation number of the to-be-propagated information in the plurality of predicted propagation times;

[0050] The total propagation number is divided by the predicted propagation number to obtain a predicted propagation number corresponding to the to-be-propagated information.

[0051] In some embodiments, the obtaining module further comprises a third sub-obtaining module configured to:

[0052] obtain a target information type corresponding to the information to be propagated;

[0053] determine historical information matching the information type and the target information type, and determine a historical information propagation task of the historical information;

[0054] obtain historical propagation data recorded under the historical information propagation task.

[0055] According to an aspect of the present application, an embodiment of the present application provides a computer readable storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute a data processing method provided by an embodiment of the present application.

[0056] According to an aspect of the present application, an embodiment of the present application provides a computer program product, which comprises a computer program or instructions, and the computer program or instructions are executed by a processor to implement a data processing method provided by an embodiment of the present application.

[0057] According to an aspect of the present application, an embodiment of the present application provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements a data processing method provided by an embodiment of the present application when executing the computer program.

[0058] In the embodiment of the present application, the historical propagation data recorded under the historical information propagation task is obtained, and the first threshold probability of each object in the interaction graph becoming an information propagator and the second threshold probability of becoming an information invitee are determined according to the historical propagation data, the interaction graph includes the nodes generated for each object and the edge connection structure between different nodes; the first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information is determined; the objects in the plurality of objects whose first random probability is greater than the first threshold probability are determined as information propagation objects, and the to-be-propagated information is sent to the information propagation objects; each information propagation object corresponding to a to-be-propagated object is determined in the plurality of objects, and the second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information is determined; the object in the to-be-propagated object whose second random probability is greater than the second threshold probability is determined as a predicted propagation object, and the to-be-propagated information is propagated to the predicted propagation object. In this way, the first threshold probability of the object in the interaction graph becoming an information propagator and the second threshold probability of becoming an information invitee are determined by using the historical propagation data of the historical information, when the first random probability of the object in the interaction graph is greater than the first threshold probability, the object can be used as an information propagation object of the to-be-propagated information, among the to-be-propagated objects corresponding to the information propagation object, the to-be-propagated object whose second random probability is greater than the second threshold probability can be determined as an information invitee of the to-be-propagated information, that is, a predicted propagation object, and then the to-be-propagated information is propagated to the predicted propagation object, so as to realize the invitation behavior in the information propagation process. Compared with the mechanical propagation scheme in the related art, the present application improves the diversity and authenticity of information propagation prediction, thereby improving the effect of information propagation prediction.

[0059] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and achieved by means of the structures particularly pointed out in the description and claims, and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0061] Figure 1 is a system architecture diagram to which the data processing method provided by the embodiment of the present application is applied;

[0062] Figure 2 is a scene schematic diagram of information propagation prediction provided by the embodiment of the present application;

[0063] Figure 3a It is a schematic diagram of an interaction diagram provided in an embodiment of the present application;

[0064] Figure 3b is a schematic diagram of an independent cascade and invitation model provided in an embodiment of the present application;

[0065] Figure 3c This is another schematic diagram of the independent cascading and invitation model provided in an embodiment of the present application;

[0066] Figure 3d This is another schematic diagram of the independent cascading and invitation model provided in an embodiment of the present application;

[0067] Figure 3e This is another schematic diagram of the independent cascading and invitation model provided in an embodiment of the present application;

[0068] Figure 4 Schematic diagram of the data processing method provided in the embodiment of the present application;

[0069] Figure 5 is a schematic diagram of a process for determining a first threshold probability provided by an embodiment of the present application;

[0070] Figure 6 This is a distribution diagram of historical information disseminators during the dissemination of historical information provided by an embodiment of the present application;

[0071] Figure 7 2 is a schematic diagram comparing first distribution probabilities in different historical information provided by an embodiment of the present application;

[0072] Figure 8 This is a distribution diagram of the object types provided in the embodiments of the present application;

[0073] Figure 9 is a schematic diagram of a flow chart for determining a second threshold probability provided by an embodiment of the present application;

[0074] Figure 10 is a schematic diagram of a propagation list provided in an embodiment of the present application;

[0075] Figure 11 This is a distribution map corresponding to the invited locations provided in the embodiment of the present application;

[0076] Figure 12a This is a distribution diagram of target historical information invitees and invitation times provided by an embodiment of the present application;

[0077] Figure 12b This is another distribution diagram between the target historical information invitees and the number of invitations provided by the embodiment of the present application;

[0078] Figure 13ais a propagation effect schematic diagram of the independent cascade and invitation model provided by an embodiment of the present application;

[0079] Figure 13b is another propagation effect schematic diagram of the independent cascade and invitation model provided by an embodiment of the present application;

[0080] Figure 14 is another flow schematic diagram of the data processing method provided by an embodiment of the present application;

[0081] Figure 15 is a schematic diagram of the data processing apparatus provided by an embodiment of the present application;

[0082] Figure 16 is a structure schematic diagram of the server provided by an embodiment of the present application;

[0083] Figure 17 is a structure schematic diagram of the terminal provided by an embodiment of the present application. DETAILED DESCRIPTION

[0084] In order to enable persons skilled in the art to better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor fall within the scope of protection of the present application.

[0085] It can be understood that in the specific embodiments of the present application, the relevant data such as the corresponding propagation information data of the object is involved, and when the above embodiments of the present application are applied to specific products or technologies, the user's permission or consent needs to be obtained, and the collection, use and processing of the relevant data need to comply with relevant laws, regulations and standards.

[0086] It should be noted that in some processes described in the specification, claims and the above drawings, a plurality of steps appearing in a specific order are included, but it should be clearly understood that these steps can be executed or executed in parallel without the order in which they appear in this text, and the step number is only used to distinguish different steps, and the number itself does not represent any execution order. In addition, the description of "first", "second" or "target" and the like in this text is used to distinguish similar objects, and does not necessarily describe a specific order or sequence.

[0087] With reference to the drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work are within the scope of protection of the present application.

[0088] Before the embodiments of the present application are further described in detail, the terms and names involved in the embodiments of the present application are explained, and the terms and names involved in the embodiments of the present application are applicable to the following explanations:

[0089] Graph data: a data structure for representing entities and relationships in the form of points (Vertex / Node) and edges (Edge).

[0090] Bayes theorem (Bayes Theorem): also known as Bayes formula, is a theorem about the conditional probability or marginal probability of random events A and B, which means that when the sample size is close to the total population, the probability of the event in the sample will be close to the probability of the event in the total population. The unknown probability can be calculated by the known probability, for example, the probability of A is P(A), the probability of B is P(B), and the probability of B when A occurs is P(B|A). Then the probability of A when B occurs P(A|B) = P(A)*P(B|A) / P(B) can be calculated.

[0091] Independent cascade model (Independent Cascade Model): an information propagation model, which is an abstract description of the information propagation process. The basic assumption of this model is that the behavior of node u trying to activate its adjacent node v is an event with a probability of P U,V . And the probability of a node in an inactive state being activated by a neighbor node that has just entered an active state is independent of the activities of the neighbors who have tried to activate the node before. In addition, the model also makes the assumption that any node u in the network has only one opportunity to try to activate its neighbor node v, whether it succeeds or not. In the future, u itself will remain active, but it will no longer have influence, and this type of node is called an inactive node with no influence.

[0092] First, the technical problems existing in the related art are described.

[0093] Network socialization is the main way of information dissemination. When some information needs to be promoted, it needs to be spread through social networks to disseminate information and achieve information promotion.

[0094] In the related art, a traditional propagation model is used to propagate information, so as to popularize the information to multiple objects. When propagating information by using the traditional propagation model, each object is a propagation node, and a propagation node needs to propagate information according to a propagation probability between other nodes adjacent to the propagation node when propagating information. For example, the current propagation node selects a next propagation node with a large propagation probability as a propagation object of information.

[0095] When propagating information by using a network social, an object initiatively propagates information through a social network, and one object can propagate information to multiple objects, and multiple objects can propagate information to one object. The propagation model in the related art does not consider this, so that the effect of information propagation is poor, and does not meet the actual information propagation requirement.

[0096] In order to solve the above technical problem, a data processing method is provided in the embodiments of the present application, wherein a first threshold probability of an object in an interaction graph becoming an information propagator and a second threshold probability of the object becoming an information invitee are determined by using historical propagation data of historical information, when a first random probability corresponding to the object in the interaction graph is greater than the first threshold probability, the object can be determined as an information propagation object of to-be-propagated information, and in to-be-propagated objects corresponding to the information propagation object, a to-be-propagated object with a second random probability greater than the second threshold probability can be determined as an information invitee of the to-be-propagated information, that is, a predicted propagation object, and then the to-be-propagated information is propagated to the predicted propagation object, so as to simulate an invitation behavior in an information propagation process on a network. Compared with a mechanical propagation scheme in the related art, the present application improves the diversity and authenticity of information propagation prediction, so as to improve the effect of information propagation prediction.

[0097] The data processing method, device, equipment and medium provided by the embodiments of the present application will be described in detail below.

[0098] The embodiments of the present application provide a data processing method, device, equipment and medium. Specifically, the embodiments of the present application are described from the dimension of a data processing device, which can be integrated in a computer equipment. The computer equipment can be a server, a terminal or the like. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, a cloud server providing cloud services, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and basic cloud computing services such as big data and artificial intelligence platform. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a smart home appliance, a vehicle terminal, a smart voice interaction device, an aircraft, and the like, but is not limited thereto. The embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, intelligent transportation, and assisted driving.

[0099] It should be noted that the data processing method provided in the embodiments of the present application can be applied to a corresponding network system framework, so as to realize various information propagation scenarios such as game activity promotion, e-commerce information promotion, media information promotion and the like through the network system framework.

[0100] For details, please refer to Figure 1 , Figure 1 is a system architecture diagram to which the data processing method provided by the embodiments of the present application is applied. It includes a terminal 140, an Internet 130, a gateway 120, a server 110 and the like.

[0101] The terminal 140 includes but is not limited to a mobile phone, a computer, a smart voice interaction device, a smart home appliance, a vehicle terminal, an aircraft, and the like. The embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence and the like. In addition, it can be a single device or a combination of multiple devices. For example, multiple desktop computers are connected to each other through a local area network, share a display and the like to work cooperatively, and jointly constitute a terminal 140. The terminal 140 can communicate with the Internet 130 in a wired or wireless manner to exchange data.

[0102] The server 110 refers to a computer system capable of providing certain services to the terminal 140. Compared with the ordinary terminal 140, the server 110 has higher requirements in stability, security, performance and the like. The server 110 can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and basic cloud computing services such as big data and artificial intelligence platform.

[0103] Gateway 120, also known as a gateway or protocol converter, implements network interconnection at the transport layer and is a computer system or device that performs a conversion function. It acts as a translator between two systems using different communication protocols, data formats, languages, or even completely different architectures. Gateways can also provide filtering and security functions. Messages sent from terminal 140 to server 110 are sent through gateway 120 to the corresponding server 110. Messages sent from server 110 to terminal 140 are also sent through gateway 120 to the corresponding terminal 140.

[0104] The data processing method in the embodiment of the present application can be applied to a variety of scenarios, such as game activity promotion, e-commerce information promotion, media information promotion, etc. The scenarios to which the data processing method in the present application is applied are not limited here.

[0105] Please continue reading Figure 2 , Figure 2 This is a schematic diagram of the information dissemination prediction scenario provided by an embodiment of the present application.

[0106] like Figure 2 As shown in the figure, taking the information dissemination scenario of event promotion as an example, there are multiple objects in the network, and one object can be the information disseminator of the event. This object can receive the event information pushed by the service provider, and then participate in the event promoted by the service provider through the relevant entry of the event information. For example, the object can trigger participation in the event by clicking a link or the corresponding control in the application.

[0107] After an object participates in an activity, a corresponding communication list may be provided for the object. In the communication list, there are multiple other objects related to the object. The other objects may be the object's social network friends, or other objects that have intersected with the object on the network, such as teammates who have teamed up with the object in the game, objects that have interacted with the object, etc.

[0108] After presenting the broadcast list to an object, the object can choose to share the event with other objects in the broadcast list based on the broadcast list. For example, if the broadcast list has multiple invitation slots, each slot can correspond to an inviteable object. The object can click the invite control on the corresponding invitation slot to send the event-related information to the corresponding object.

[0109] After receiving information related to the event, other objects can participate in the event through the event-related entrance, thereby enabling the object to promote the event to other objects, and other objects become information invitees. After participating in the event, other objects can serve as new information disseminators and continue to spread and promote the event through the above methods.

[0110] It should be noted that, in the embodiments of the present application, the scenario involving information dissemination can be carried out through a preset information dissemination model. The preset information dissemination model can be an independent cascade with invitation model (ICI). Different from the independent cascade model, the information dissemination model involves an invitation mechanism. For example, objects in the network can invite other objects to realize the dissemination of information. One object can disseminate information to multiple objects, and multiple objects can also disseminate information to one object, thereby realizing the dissemination of information. The independent cascade model does not have an invitation mechanism. Therefore, in the process of information dissemination, the invitation behavior between objects will be ignored, resulting in the poor information dissemination effect of the independent cascade model, which will lead to inaccurate predictions of the number and scope of information dissemination. Therefore, the independent cascade and invitation model provided in the embodiments of the present application will take into account the invitation behavior between objects, so as to achieve better information dissemination effects.

[0111] For a more detailed understanding of the independent cascade and invitation model provided in the embodiments of this application, please refer to Figures 3a to 3e , Figure 3a It is a schematic diagram of the interaction diagram provided in the embodiment of the present application.

[0112] Among them, the interaction graph can be composed of multiple objects in the network and the association relationships between multiple objects. For example, taking the social network corresponding to the game as an example, the friend relationship and interaction relationship of the objects can be determined through the game log, and then the association relationship between different objects can be determined based on the friend relationship and interaction relationship.

[0113] Friendship can be established by adding friends between objects in the game, or by determining friendship through the social network friends of the objects.

[0114] Interaction relationships can be formed when an object plays against other objects in a game. For example, teammates and opponents can both serve as interaction objects, and objects can have interaction relationships with each other. In this way, friendships and interaction relationships can be used to determine the other objects to which each object is associated, thereby obtaining the associations between the objects and other objects, and ultimately constructing an interaction graph based on these associations.

[0115] Specifically, a corresponding node may be generated for each object, and the association relationship between objects may be used as an edge connection structure between different nodes.

[0116] like Figure 3aAs shown, the interaction graph comprises a plurality of nodes, each node can be understood as an object, each node has an associated node, and there is a corresponding edge between a node and its associated node, and the interaction graph is composed of nodes and edges.

[0117] Please continue to refer to Figure 3b , Figure 3b is a schematic diagram of an independent cascade and invitation model provided by an embodiment of the present application.

[0118] After obtaining the interaction graph, there are a plurality of objects in the interaction graph, and information propagators can be determined from the plurality of objects, and then the information propagators propagate the information. Among them, node A1 is an information propagator, which can also be understood as the most initial information propagation source, and the number of information propagators can be one or two or more. The nodes that are information propagators with node A1 can be activated nodes, and other nodes that are not information propagators are unactivated nodes.

[0119] In an embodiment of the present application, the determination method of the information propagator can be determined according to the object type of the object. Each node corresponds to an object, and each object has a corresponding object type. Taking a game scene as an example, the game corresponds to a plurality of objects, and the corresponding object type can be determined according to the game activity of each object, such as new players, weekly active players, weekly churn players, bi-weekly churn players, active players within three months, active players within six months, and a plurality of object types. One or more object types corresponding to the object can be determined as an information propagator.

[0120] In some embodiments, in the case where there are a plurality of object types, it is also necessary to determine the probability that each object type can become an information propagation type. If the probability that a certain object type can become an information propagation type is high, the object corresponding to the object type can be determined as an information propagator.

[0121] Please continue to refer to Figure 3c , Figure 3c is another schematic diagram of an independent cascade and invitation model provided by an embodiment of the present application.

[0122] After determining the information propagator from the plurality of objects, the information propagator can send information to other nodes, thereby realizing the propagation of the information. For example, taking node A1 as an information propagator and node B1 as an information invitee as an example, node A1 can propagate information to node B1, thereby activating node B1. Node B1 is an information invitee. If node B1 participates in the activity corresponding to the information according to the information, such as participating in the activity corresponding to the game, then node B1 becomes a new information propagator, and node B1 can continue to propagate the information.

[0123] In some embodiments, as an information disseminator, node A1 can have multiple to-be-invited objects, each of which has a certain invitation probability. For example, if the invitation probability of a to-be-invited object is greater than a threshold probability of invitation, the to-be-invited object can be invited by node A1, and node A1 can disseminate information to the node. Nodes that are not invited by node A1 cannot be activated by node A1.

[0124] Please continue to refer to Figure 3d , Figure 3d is another schematic diagram of the independent cascade and invitation model provided by the embodiments of the present application.

[0125] When node B1 receives the information, it participates in the activity according to the information, such as clicking the link corresponding to the information, thereby participating in the activity, and then node B1 can be an information disseminator, and node B1 can disseminate information to node C1.

[0126] Node B1 also has multiple to-be-invited objects, and node B1 can select some to-be-invited objects from the multiple to-be-invited objects for information dissemination. For example, node B1 has a dissemination list, and the dissemination list has multiple invitation positions, each of which can correspond to a to-be-invited object. The object corresponding to node B1 can click the corresponding invitation position in the dissemination list to send information to the to-be-invited object corresponding to the invitation position. For example, the to-be-invited object is node C1, and after receiving the information, node C1 is an information invitee. If node C1 participates in the activity according to the information, node C1 is a new information disseminator.

[0127] Please continue to refer to Figure 3e , Figure 3e is another schematic diagram of the independent cascade and invitation model provided by the embodiments of the present application.

[0128] In the multiple nodes, after each node is activated, the node can be a new information disseminator, and the new information disseminator does not need to consider whether other nodes have been activated when disseminating information. For example, node B1 is activated by node A1, and node C1 as an information disseminator can still disseminate information to node B1 to activate node B1.

[0129] It should be noted that, different from the independent cascade model, the independent cascade and invitation model in the embodiments of the present application involves an invitation mechanism between different objects, and the information propagation can also be achieved through the invitation mechanism, while the independent cascade model does not consider this point and does not apply the invitation mechanism. In the process of information propagation by using the independent cascade and invitation model, better information propagation effect can be achieved through the invitation mechanism, while the independent cascade model in the related art cannot achieve the technical effect.

[0130] The independent cascade and invitation model provided by the embodiments of the present application is introduced above. In the information propagation by using the independent cascade and invitation model, the specific data processing method will be continued to be introduced below.

[0131] Please refer to Figure 4 , Figure 4 is a flowchart of the data processing method provided by the embodiments of the present application. The data processing method can include the following steps:

[0132] Step 210, historical propagation data recorded under a historical information propagation task is acquired, and a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee are determined according to the historical propagation data;

[0133] Step 220, a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information is determined;

[0134] Step 230, objects in which the first random probability is greater than the first threshold probability in the plurality of objects are determined as information propagation objects, and the to-be-propagated information is sent to the information propagation objects;

[0135] Step 240, a to-be-propagated object corresponding to each information propagation object is determined in the plurality of objects, and a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information is determined;

[0136] Step 250, objects in which the second random probability is greater than the second threshold probability in the to-be-propagated objects are determined as predicted propagation objects, and the to-be-propagated information is propagated to the predicted propagation objects.

[0137] The steps 210 to 250 will be described in detail below.

[0138] In step 210, historical propagation data recorded under a historical information propagation task is acquired, and a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee are determined according to the historical propagation data, the interaction graph includes nodes generated for each object and edge connection structures between different nodes.

[0139] The main idea of the embodiments of the present application is briefly described as follows. In a plurality of objects in an interaction graph, a first threshold probability of each object becoming an information propagator and a second threshold probability of each object becoming an information invitee are determined according to historical propagation data of the object in a history information propagation task. The first threshold probability can be understood as the minimum probability of the object becoming an information propagator, and the second threshold probability can be understood as the minimum probability of the object becoming an information invitee.

[0140] If the first random probability of an object in the plurality of objects is greater than the first threshold probability, the object can be an information propagator. If the second random probability of an object in the plurality of objects corresponding to the information propagator is greater than the second threshold probability, the object can be an information invitee. In this way, the first threshold probability and the second threshold probability are used to determine the information propagator and the information invitee in the plurality of objects, and then information propagation is performed to simulate the invitation behavior in the real information propagation process, thereby improving the information propagation effect in the information propagation process.

[0141] In some embodiments, the historical propagation data recorded in the history information propagation task is obtained, including:

[0142] (1.1) obtaining a target information type corresponding to the to-be-propagated information;

[0143] (1.2) determining historical information whose information type matches the target information type, and determining a history information propagation task of the historical information;

[0144] (1.3) obtaining historical propagation data recorded in the history information propagation task.

[0145] The to-be-propagated information has a corresponding target information type. For example, the to-be-propagated information can be information for promoting various activities such as “game red packet grabbing”, “game character skin drawing”, and “advertisement promotion”. If the to-be-propagated information is information corresponding to the “game red packet grabbing” activity, the target information type of the to-be-propagated information is game promotion. If the to-be-propagated information is information corresponding to the “advertisement promotion” activity, the target information type of the to-be-propagated information is advertisement promotion.

[0146] Among the historical information, historical information of which the information type matches the target information type can be determined, for example, the target information type is game promotion, and historical information of game promotion can be found, and a historical information dissemination task corresponding to the historical information of game promotion is determined, and historical dissemination data recorded in the historical information dissemination task is obtained. In this way, historical dissemination data of historical information of the same information type as the information type of the to-be-disseminated information can be obtained, and related parameters required by the subsequent independent cascade and invitation model can be determined by using the historical dissemination data, which can improve the accuracy of the independent cascade and invitation model in predicting the dissemination of the to-be-disseminated information, thereby improving the prediction dissemination effect of the to-be-disseminated information.

[0147] The historical dissemination data includes various types of data, such as the object types of multiple objects of the historical information during dissemination, the number of people of different object types, the number of historical information disseminators of the historical information, and the object types of the historical information disseminators.

[0148] The historical information is disseminated among multiple objects in the interaction graph, and the interaction graph includes multiple nodes, each node being an object, and each node corresponding to other nodes associated therewith.

[0149] The interaction graph can be constructed based on multiple objects in a social network and the relationships between the objects, for example, in a game scenario, an object has game friends and opponents in a game match, and the interaction graph can be constructed according to the association relationship between the object and the game friends and the association relationship between the object and the opponents. Subsequently, when predicting the dissemination of the to-be-disseminated information, the information can be disseminated among the multiple objects in the interaction graph.

[0150] Please refer to Figure 5 , Figure 5 is a flowchart of a process for determining the first threshold probability provided by the embodiments of the present application.

[0151] In some embodiments, determining the first threshold probability of each object in the interaction graph becoming an information disseminator according to the historical dissemination data can include the following steps:

[0152] Step 301, determining at least one target object type corresponding to the historical information disseminator and a first distribution probability of each target object type in all target object types according to the historical dissemination data;

[0153] Step 302, determining a second distribution probability of the historical information disseminator in the objects according to the historical dissemination data;

[0154] Step 303, determining, according to the historical propagation data, a third distribution probability of each object type of the object in all object types corresponding to the object;

[0155] Step 304, determining, as a first threshold probability of each object in the interaction graph becoming an information propagator, a ratio of a product of the first distribution probability and the second distribution probability to the third distribution probability.

[0156] The steps 301 to 304 will be described in detail below.

[0157] In step 301, at least one target object type corresponding to a historical information propagator and a first distribution probability of each target object type in all target object types corresponding to the historical information propagator are determined according to historical propagation data.

[0158] According to the historical propagation data, the historical information propagator of the historical information under the historical information propagation task can be determined, and the historical information propagator can propagate the historical information, such as the historical information propagator sending the historical information to the historical information invitee.

[0159] The historical information propagator corresponds to at least one target object type, such as the target object type of the historical information propagator determined according to the activity of the historical information propagator in the network, and the activity can be determined by determining the login times of the historical information propagator.

[0160] Please refer to Figure 6 , Figure 6 is a distribution graph of the historical information propagator of the historical information in the process of propagation provided by the embodiments of the present application.

[0161] The horizontal coordinate is the target object type, and the vertical coordinate is the proportion of different target object types in all target object types.

[0162] For example, taking a game scenario as an example, -1 in the horizontal coordinate represents a new player type, 0 represents a weekly active player type, 1 represents a weekly churn player type, 2 represents a double-week churn player type, 3 represents a three-month active user type, and 4 represents a half-year active player type.

[0163] Each target object type corresponds to a certain number of historical information propagators, and the number of historical information propagators of each target object type is divided by the total number of historical information propagators to obtain the first distribution probability of each target object type in all target object types.

[0164] Please refer to Figure 7 , Figure 7 is a comparison diagram of the first distribution probability in different historical information provided by the embodiments of the present application.

[0165] Wherein, the horizontal coordinate is the target object type, and the vertical coordinate is the proportion of different target object types in all target object types.

[0166] In the contrast columnar bar corresponding to each target object type, the left columnar bar is the columnar bar corresponding to the historical information 1, and the right columnar bar is the columnar bar corresponding to the historical information 2. By comparison, it can be known that for different historical information, after the historical information propagates, the first distribution probability of each target object type corresponding to the historical information in all target object types is relatively close.

[0167] Therefore, when the historical information propagates, in the historical information propagator corresponding to the historical information, the first distribution probability of each target object type of the historical propagator in all target object types is relatively stable. Therefore, the first threshold probability of the object in the interaction graph becoming the information propagator is determined by using the first distribution probability, which can improve the accuracy of the determination of the first threshold probability.

[0168] In step 302, according to the historical propagation data, the second distribution probability of the historical information propagator in the object is determined.

[0169] Specifically, the number of historical information propagators can be determined according to the historical propagation data. Then the number of all objects in the interaction graph is determined, and all objects can be understood as all propagatable objects corresponding to the historical information when the historical information propagates.

[0170] The number of historical information propagators is divided by the number of all objects to obtain the second distribution probability of the historical information propagator in the object.

[0171] Wherein, the historical information propagator can be understood as the object that has viewed the historical information, that is, the object that has participated in the related activity corresponding to the historical information, such as the game activity promotion of the historical information. If the object clicks the game activity, it is considered that the object participates in the game activity, and the object is the historical information propagator of the historical information. Therefore, the second distribution probability of the historical information propagator in the object can also be considered as the proportion of the object that has viewed the historical information in the plurality of objects.

[0172] Please refer to Table 1, which is a schematic table of the second distribution probability of the historical information propagator in the object provided by the embodiment of the present application.

[0173] Historical information Macro area Second distribution probability Historical information 1 Macro area A 0.0528 Historical information 1 Macro area B 0.0503 Historical information 2 Macro area A 0.0778 Historical information 2 Macro area B 0.0681

[0174] Table 1

[0175] As shown in Table 1, the second distribution probabilities corresponding to different historical information are not much different, which indicates that the second distribution probability can accurately reflect the proportion of the historical information disseminator in all objects, and the first threshold probability of the object in the interaction graph becoming an information disseminator can be determined through the second distribution probability, thereby improving the accuracy of the determination of the first threshold probability.

[0176] In step 303, according to the historical dissemination data, a third distribution probability of each object type corresponding to the object in all object types is determined.

[0177] It can be understood that the plurality of objects in the interaction graph correspond to at least one object type, and the object type can be determined according to the activity of the object, for example, the object type of the object can be determined according to the activity of the object in the network, and the activity can be determined by determining the login times of the object.

[0178] The number of objects corresponding to each object type is divided by the total number of all objects to obtain the third distribution probability of each object type in all object types.

[0179] Please refer to Figure 8 , Figure 8 is a distribution graph of the object type provided by the embodiment of the application.

[0180] The horizontal coordinate is the object type corresponding to the object in the interaction graph, and the vertical coordinate is the proportion of the object type in all object types.

[0181] As shown in Figure 8 , the proportion of each object type in all object types corresponding to the tth day, the t-1th day, the t-2th day, and the t-3th day is provided. It can be seen that the proportions of the object types in all object types are roughly the same at different times and do not differ too much.

[0182] Therefore, the third distribution probability of each object type in all object types at a certain time can be determined, and the first threshold probability of the object in the interaction graph becoming an information disseminator can be determined according to the third distribution probability, thereby improving the accuracy of the determination of the first threshold probability.

[0183] In step 304, the ratio of the product of the first distribution probability and the second distribution probability to the third distribution probability is determined as the first threshold probability of each object in the interaction graph becoming an information disseminator.

[0184] After obtaining the first distribution probability, the second distribution probability and the third distribution probability, the first distribution probability and the second distribution probability can be multiplied to obtain a product, and then the product is divided by the third distribution probability, so that the first threshold probability of each object in the interaction graph becoming an information disseminator is obtained.

[0185] The specific principle is to determine the known probability through the historical dissemination data by using the Bayes theorem, and then determine the unknown probability by using the known probability. Among them, the first distribution probability, the second distribution probability and the third distribution probability are known probabilities, and the first threshold probability is an unknown probability.

[0186] In order to understand how the first threshold probability is determined in this application in more detail, please refer to the following mathematical formula:

[0187]

[0188] Among them, Pr (ap = 1 |type u ) is the first threshold probability. Pr (type u |ap = 1) is the first distribution probability, which can also be understood as Pr (ap = 1) is the second distribution probability, Pr (type u ) is the third distribution probability. ap = 1 can be understood as becoming an information disseminator, and type u u can be understood as the object type.

[0189] From the above content, it can be known that in the multiple objects in the interaction graph, the distribution of the objects becoming the historical information disseminator and the distribution of the object type are strongly related. Therefore, all objects in a certain object type can be determined as information disseminators.

[0190] Therefore, it can be considered that in the multiple objects, the probability of a certain object corresponding to becoming an information disseminator can be equivalent to the probability of the object type of the object corresponding to becoming an information disseminator. That is, Pr (ap = 1 |type u ) in the above formula.

[0191] It can be understood that the first threshold probability is the minimum probability of any object being able to become an information disseminator. Only when the probability of any object is greater than the first threshold probability, the object can become an information disseminator.

[0192] From steps 301 to 304, it can be known that the first threshold probability of each object in the interaction graph becoming an information disseminator is determined through the historical dissemination data, so that in the subsequent information dissemination, the information disseminator for information dissemination can be screened out through the first threshold probability, thereby improving the accuracy of determining the information disseminator.

[0193] Please refer toFigure 9 , Figure 9 is a flowchart of determining a second threshold probability provided by an embodiment of the present application.

[0194] In some embodiments, determining the second threshold probability of each object in the interaction graph becoming an information invitee according to historical propagation data can include the following steps:

[0195] Step 401, determining, according to historical propagation data, a propagation list corresponding to a historical information propagator and a number of historical information invitees corresponding to each invited position in the propagation list;

[0196] Step 402, dividing the number of historical information invitees corresponding to each invited position by a total number of historical information invitees to obtain a first position distribution probability of each invited position in all invited positions;

[0197] Step 403, determining, according to historical propagation data, a propagation distribution probability of historical information invitees in all historical invitees corresponding to a historical information propagator;

[0198] Step 404, determining, in the propagation list, a second position distribution probability of each invitation position in all invitation positions of the propagation list;

[0199] Step 405, determining, as the second threshold probability of each object in the interaction graph becoming an information invitee, a ratio of a product of the first position distribution probability and the propagation distribution probability to the second position distribution probability.

[0200] The steps 401 to 405 will be described in detail below.

[0201] In step 401, according to historical propagation data, a propagation list corresponding to a historical information propagator and a number of historical information invitees corresponding to each invited position in the propagation list are determined.

[0202] Each historical information propagator has corresponding historical invitees who can propagate historical information, and these historical invitees correspond to a propagation list, and there are multiple invitation positions in the propagation list, and each invitation position corresponds to a historical invitee.

[0203] In the historical information propagation scenario, the historical information propagator does not invite each historical invitee to propagate historical information, but invites historical invitees on some invitation positions. The invited historical invitees are historical information invitees corresponding to historical information.

[0204] Please refer to Figure 10 , Figure 10 is a schematic diagram of a propagation list provided in an embodiment of the present application.

[0205] When the historical information disseminator enters the information interface corresponding to the historical information, there is a corresponding dissemination list in the information interface, and the dissemination list has a plurality of invitation positions. The historical information disseminator can click a corresponding invitation position, so as to realize dissemination of the historical information to a historical invitee corresponding to the clicked invitation position. The invitation position that is clicked to generate an invitation is an invited position.

[0206] The number of invitation positions in the dissemination list of each historical information disseminator is the same, and the style of the invitation list is also the same. According to historical dissemination data, the number of historical information invitees corresponding to each invited position can be determined. For example, the historical information disseminators are A and B. For the first invitation position, A invites 1 time, and B invites 1 time. Therefore, the number of historical information invitees corresponding to the first invitation position is 2. In this way, the number of historical information invitees corresponding to each invited position can be determined.

[0207] In step 402, the number of historical information invitees corresponding to each invited position is divided by the total number of historical information invitees, to obtain a first position distribution probability of each invited position in all invited positions.

[0208] The total number of historical information invitees corresponding to all invited positions can be determined, and then the number of historical information invitees corresponding to each invited position is divided by the total number of historical information invitees, to obtain a first position distribution probability of each invited position in all invited positions.

[0209] Please refer to Figure 11 , Figure 11 is a distribution diagram of the invited positions provided by the embodiment of the present application.

[0210] The abscissa is different invitation positions, and the ordinate is the proportion of the number of historical information invitees corresponding to each invitation position in the total number of all historical information invitees. The farther to the left the abscissa is, the greater the proportion of the ordinate is, which indicates that the corresponding invited position is farther to the left in the dissemination list. In combination with Figure 10 , the invitation position is farther to the top. The farther to the right the abscissa is, the smaller the proportion of the ordinate is, which indicates that the corresponding invited position is farther to the right in the dissemination list, such as farther to the bottom in the dissemination list in Figure 10 .

[0211] From Figure 11It can be seen that the earlier the invitation position in the propagation list, the easier it is to be clicked, thereby inviting the historical to-be-invited object corresponding to the invitation position to propagate the historical information. For example, in the propagation list, the click rate of the top 10 invitation positions exceeds 85%, and the click rate of the top 25% invited positions exceeds 95%. This shows that the invitation position in the propagation list can be used to determine the information invitee corresponding to the to-be-propagated information that needs to be propagated subsequently.

[0212] In step 403, according to the historical propagation data, the propagation distribution probability of the historical information invitee in all historical to-be-invited objects corresponding to the historical information propagator is determined.

[0213] In some embodiments, according to the historical propagation data, the propagation distribution probability of the historical information invitee in all historical to-be-invited objects corresponding to the historical information propagator is determined, including:

[0214] (1.1) According to the historical propagation data, the first number of historical information propagators and the second number of invitation positions in the propagation list corresponding to each historical information propagator are determined, and each invitation position corresponds to one historical to-be-invited object;

[0215] (1.2) The product of the first number and the second number is determined as the total number of historical to-be-invited objects;

[0216] (1.3) According to the historical propagation data, the third number corresponding to the historical information invitee is determined;

[0217] (1.4) The third number is divided by the total number of historical to-be-invited objects to obtain the propagation distribution probability of the historical information invitee in all historical to-be-invited objects.

[0218] Wherein, the first number of historical information propagators can be determined according to the historical propagation data, and since each historical information propagator corresponds to his own propagation list, there are second number of invitation positions in each propagation list, and each invitation position can correspond to one historical to-be-invited object. Then, the first number and the second number can determine the total number of historical to-be-invited objects.

[0219] Then, the number of historical information invitees that have propagated historical information by each historical information propagator is determined, and the number of historical information invitees that have propagated historical information by each historical information propagator is added, thereby obtaining the third number of all historical information invitees.

[0220] Finally, the third number is divided by the total number of historical to-be-invited objects to obtain the propagation distribution probability of the historical information invitee in all historical to-be-invited objects. That is, the proportion of historical information invitees propagated by historical information propagators in all historical to-be-invited objects.

[0221] In step 404, a second position distribution probability of each invitation position in the propagation list in all invitation positions in the propagation list is determined.

[0222] If each invitation position in the propagation list is unique, then the number of each invitation position is 1, and if the number of all invitation positions is n, then the second position distribution probability of each invitation position in all invitation positions in the propagation list is 1 / n.

[0223] In step 405, a ratio of a product of the first position distribution probability and the propagation probability and the second position distribution probability is determined as a second threshold probability of each object in the interaction graph becoming an invited information receiver.

[0224] After obtaining the first position distribution probability, the propagation probability and the second position distribution probability, a product of the first position distribution probability and the propagation probability is obtained, and then the product is divided by the second position distribution probability, so that the second threshold probability of each object in the interaction graph becoming an invited information receiver is obtained.

[0225] The specific principle is to determine the known probability through the historical propagation data, and then determine the unknown probability according to the known probability. Among them, the first position distribution probability, the propagation probability and the second position distribution probability are known probabilities, and the second threshold probability is an unknown probability.

[0226] In order to understand how the second threshold probability is determined in the present application in more detail, please refer to the following mathematical formula:

[0227]

[0228] Among them, Pr(invite|r i ) is the second threshold probability, Pr(r i |invite) is the first position distribution probability, Pr(invite) is the propagation probability, and Pr(r i ) is the second position distribution probability, wherein r i is the position of the invitation position r i in the propagation list, and invite is the corresponding invited position in the propagation list.

[0229] From the above content, it can be known that the invitation position is determined, and the probability of the object of the invitation position being invited can be reflected through the invitation position.

[0230] It should be noted that the second threshold probability can be understood as a minimum probability that a certain to-be-propagated object in the propagation list of a certain information propagator can become an information invitee. When the probability of a certain to-be-propagated object is greater than the second threshold probability, it indicates that the to-be-propagated object can be invited by the information propagator and thus become an information invitee.

[0231] In some embodiments, the maximum invitation position of the propagation list is r max , the number of historical information invitees is m invite , and the number of historical information propagators is n invite . Then the calculation formula of the above-mentioned second threshold probability can be simplified. The following formula is obtained:

[0232]

[0233] wherein, is the number of historical information invitees per historical information propagator.

[0234] That is, the total number of historical information propagators and the total number of historical information invitees can be determined according to the historical propagation data. The number of historical information invitees per historical information propagator is obtained by dividing the total number of historical information invitees by the total number of historical information propagators. Then, the second threshold probability of each object in the interaction graph becoming an information invitee is obtained by multiplying the number of historical information invitees per historical information propagator by the first position distribution probability.

[0235] Please refer to Table 2 together, which is a schematic table of the number of historical information invitees per historical information propagator corresponding to different historical information provided by the embodiments of the present application.

[0236] Historical information Macro area Number of historical invitees per capita Historical information 1 Macro area A 1.81 Historical information 1 Macro area B 1.97 Historical information 2 Macro area A 1.76 Historical information 2 Macro area B 2.06

[0237] Table 2

[0238] As can be seen from Table 2, when different historical information is propagated, the number of historical information invitees per historical information propagator is almost the same for all historical information propagators. Then it is indicated that the second threshold probability of each object in the interaction graph becoming an information invitee is determined by obtaining the number of historical information invitees per historical information propagator, which can improve the accuracy of determining the second threshold probability.

[0239] As can be seen from steps 401 to 405, the second threshold probability of each object in the interaction graph becoming an information invitee is determined by historical propagation data. Thus, in subsequent information propagation, the information invitees that can be invited among the to-be-propagated objects corresponding to the information propagator can be screened by the second threshold probability, thereby improving the accuracy of determining the information invitees.

[0240] In some embodiments, after the historical information is propagated to the historical information propagator, the method further comprises:

[0241] (2.1) According to the historical propagation data, the number of historical information invitees is determined, and the number of target historical information invitees who view the historical information is determined;

[0242] (2.2) The number of target historical information invitees is divided by the number of historical information invitees to obtain a third threshold probability of each object in the interaction graph becoming an information viewer.

[0243] Wherein, after the historical information propagator propagates the historical information to the historical information invitee, the historical information invitee can choose to view or not view the historical information, and the historical information invitee who views the historical information can be determined as the target historical information invitee, and the number of target historical information invitees is obtained. The target historical information invitee can be understood as an object participating in the corresponding activity according to the historical information.

[0244] Then the number of target historical information invitees is divided by the number of historical information invitees, so as to obtain the proportion of target historical information invitees who view the historical information among all historical information invitees. The proportion can be determined as the third threshold probability of each object in the interaction graph becoming an information viewer. The third threshold probability can be understood as the minimum probability of the object becoming an information viewer. If the corresponding probability of the information invitee receiving the information is greater than the third threshold probability, the information invitee is considered as an information viewer.

[0245] Please refer to Figure 12a and Figure 12b , Figure 12a is a distribution graph provided by the present application between the target historical information invitee and the number of invitations. Figure 12b is another distribution graph provided by the present application between the target historical information invitee and the number of invitations.

[0246] From Figure 12a It can be seen that through the historical propagation data, it can be determined that 95% of the target historical information invitees have the number of invitations in the historical information propagation process of two times or less. In addition, from Figure 12b It can be seen that although the proportion of historical information invitees who become target historical information invitees who view the historical information is affected by the number of invitations, the overall difference is small when the number of invitations is 2-4 times. From Figure 12a and Figure 12b It can be seen that most of the historical information invitees view the historical information to become target historical information invitees, which is almost not affected by the number of invitations.

[0247] Then the number of target historical information invitees can be divided by the number of historical information invitees to measure the probability that the historical information invitee becomes a target historical information invitee who views the historical information after the historical information is spread. The probability can be determined as the third threshold probability of each object in the interaction graph becoming an information viewer. In this way, the accuracy of the determined third threshold probability can be improved.

[0248] The above is a specific determination method of the first threshold probability of each object in the interaction graph becoming an information spreader, the second threshold probability of becoming an information invitee, and the third threshold probability of becoming an information viewer. The first threshold probability, the second threshold probability, and the third threshold probability are all determined by the historical spread data recorded by the historical information under the historical information spread task, and have a reference basis of real data. Therefore, the first threshold probability, the second threshold probability, and the third threshold probability have high accuracy, which helps to improve the accuracy of the subsequent prediction of the spread effect of the to-be-spread information in the prediction spread, thereby improving the prediction effect of the to-be-spread information.

[0249] The content of the prediction spread of the to-be-spread information will be described below.

[0250] In step 220, a first random probability of each object in the interaction graph becoming an information spreader of the to-be-spread information is determined.

[0251] The plurality of objects in the interaction graph can be objects of the to-be-spread information in the prediction spread. A first random probability can be randomly set for each object, and the value of the first random probability is between 0 and 1. The first random probability can be understood as the probability of the object becoming an information spreader of the to-be-spread information. Subsequently, the first random probability can be used to determine which objects in the plurality of objects can become information spreaders of the to-be-spread information.

[0252] The to-be-spread information in the prediction spread can be considered to be spread on the basis of the spread model of the independent cascade and invitation model provided in the embodiments of the present application.

[0253] In step 230, the objects in the plurality of objects whose first random probability is greater than the first threshold probability are determined as information spread objects, and the to-be-spread information is sent to the information spread objects.

[0254] As known from the above, the first threshold probability is the minimum probability of an object becoming an information spreader. If the first random probability of an object in the plurality of objects is greater than the first threshold probability, it means that the object can become an information spread object of the to-be-spread information. Then the to-be-spread information is sent to the information spread object.

[0255] For example, in the scenario of promoting a game activity, information propagation objects can be determined from a plurality of objects, and then the information to be propagated corresponding to the game activity is sent to the information propagation objects. The information propagation objects can continue to propagate the information to be propagated subsequently, so as to realize promotion of the game activity.

[0256] In step 240, a to-be-propagated object corresponding to each information propagation object is determined from a plurality of objects, and a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information is determined.

[0257] It can be understood that each information propagation object has a corresponding to-be-propagated object. For example, the friends of each information propagation object are not completely the same, and then the to-be-propagated objects that can be invited by each information propagation object are also different. Therefore, the to-be-propagated object corresponding to each information propagation object needs to be determined, and then the second random probability can be set for the to-be-propagated object of each information propagation object. The second random probability can be understood as the probability that the to-be-propagated object can be invited by the information propagation object to propagate the to-be-propagated information.

[0258] In step 250, an object with a second random probability greater than a second threshold probability in the to-be-propagated object is determined as a predicted propagation object, and the to-be-propagated information is propagated to the predicted propagation object.

[0259] In the to-be-propagated object, an object with a second random probability greater than a second threshold probability can be determined as a predicted propagation object, and the predicted propagation object is an object invited by the information propagation object to propagate the to-be-propagated information. If the predicted propagation object is understood as a node, when the information propagation object sends the to-be-propagated information to the predicted propagation object, the node can be considered to be activated, and the to-be-propagated information is successfully propagated to the node.

[0260] In some embodiments, after the to-be-propagated information is propagated to the predicted propagation object, the method further includes:

[0261] (1.1) determining a third random probability of each predicted propagation object becoming an information viewer of the to-be-propagated information;

[0262] (1.2) determining an object with a third random probability greater than a third threshold probability from a plurality of predicted propagation objects as a predicted participation object viewing the to-be-propagated information.

[0263] It can be understood that after the information propagation object sends the to-be-propagated information to the predicted propagation object, the predicted propagation object can choose to view the to-be-propagated information or not. Then a third random probability can be set for each predicted propagation object, and the third random probability is the probability that the predicted propagation object becomes an information viewer of the to-be-propagated information.

[0264] Then the object whose third random probability is greater than the third threshold probability is determined as a predicted participant of viewing the to-be-propagated information, and the predicted participant can be understood as an object that has viewed the to-be-propagated information. When the predicted participant views the to-be-propagated information, it is considered that the predicted participant participates in the activity corresponding to the to-be-propagated information.

[0265] In some embodiments, after the object whose third random probability is greater than the third threshold probability is determined as a predicted participant of viewing the to-be-propagated information in the plurality of predicted propagation objects, the method further includes:

[0266] (2.1) replacing the predicted participant with a new information propagation object;

[0267] (2.2) and returning to determine, in the plurality of objects, a to-be-propagated object corresponding to each information propagation object, and determine a second random probability that each to-be-propagated object becomes an information invitee of the to-be-propagated information, until a new predicted participant cannot be determined.

[0268] For example, after viewing the to-be-propagated information, the predicted participant can continue to propagate the predicted participant to other objects, and the predicted participant can be replaced with a new information propagation object.

[0269] Then the object whose third random probability is greater than the third threshold probability is determined as a predicted participant of viewing the to-be-propagated information, and the predicted participant can be understood as an object that has viewed the to-be-propagated information. When the predicted participant views the to-be-propagated information, it is considered that the predicted participant participates in the activity corresponding to the to-be-propagated information.

[0270] Then the object whose third random probability is greater than the third threshold probability is determined as a predicted participant of viewing the to-be-propagated information, and the predicted participant can be understood as an object that has viewed the to-be-propagated information. When the predicted participant views the to-be-propagated information, it is considered that the predicted participant participates in the activity corresponding to the to-be-propagated information.

[0271] That is, at this time, the to-be-propagated information in the plurality of objects in the interaction graph has no new object to view the to-be-propagated information, so there is no new predicted participant. At this time, it is considered that the propagation of the to-be-propagated information in the plurality of objects has stopped. Then, the related propagation data of the to-be-propagated information in this round of predicted propagation can be counted.

[0272] In some embodiments, the to-be-propagated information can be subjected to multiple rounds of predicted propagation, such as in multiple objects of the interaction graph, multiple rounds of predicted propagation can be performed, and when a new predicted participating object cannot be determined during the propagation of the to-be-propagated information in the multiple objects, it is considered that the propagation of the to-be-propagated information is terminated, and one round of predicted propagation of the to-be-propagated information is completed.

[0273] In some embodiments, the predicted propagation effect corresponding to the to-be-propagated information can be determined according to the related propagation data of the multiple rounds of predicted propagation of the to-be-propagated information. Specifically, it includes:

[0274] (3.1) When a new predicted participating object cannot be determined, the predicted propagation number corresponding to the to-be-propagated information is determined;

[0275] (3.2) According to the propagation relationship between the information propagation object and the predicted propagation object, the predicted propagation path corresponding to the to-be-propagated information is determined, and the path propagation number corresponding to each predicted propagation path is determined;

[0276] (3.3) The predicted propagation number and the path propagation number are determined to be the predicted propagation result corresponding to the to-be-propagated information.

[0277] The predicted propagation number corresponding to the to-be-propagated information can be an average propagation number determined after the to-be-propagated information is subjected to multiple rounds of predicted propagation.

[0278] Specifically, when a new predicted participating object cannot be determined, the predicted propagation number corresponding to the to-be-propagated information can include:

[0279] (3.1.1) Obtain the predicted propagation number of the to-be-propagated information;

[0280] (3.1.2) Statistically determine the total propagation number of the to-be-propagated information in multiple predicted propagations;

[0281] (3.1.3) Divide the total propagation number by the predicted propagation number to obtain the predicted propagation number corresponding to the to-be-propagated information.

[0282] For example, first determine the predicted propagation number of the to-be-propagated information as N, then add the number of each predicted propagation to obtain the total propagation number M, and then divide the total propagation number M by the predicted propagation number N to obtain the predicted propagation number corresponding to the to-be-propagated information.

[0283] By subjecting the to-be-propagated information to multiple rounds of predicted propagation, and then obtaining the average of the propagation numbers corresponding to the multiple rounds of predicted propagation, the predicted propagation number corresponding to the to-be-propagated information in one round of predicted propagation is obtained. In this way, the accuracy of the determined predicted propagation number can be improved.

[0284] The propagation relationship between the information propagation object and the predicted propagation object can also be determined, and according to the propagation relationship between the information propagation object and the predicted propagation object, the predicted propagation path corresponding to the to-be-propagated information is determined, and the path propagation number corresponding to each predicted propagation path is determined. For example, object A sends the to-be-propagated information to object B, and object B sends the to-be-propagated information to object C, thereby forming a propagation relationship of object A-B-C. According to the propagation relationship, the corresponding predicted propagation path A-B-C can be determined, and the path propagation number corresponding to the predicted propagation path is determined to be 3. In this way, the path propagation number corresponding to each predicted propagation path can be determined.

[0285] Finally, the predicted propagation number and the path propagation number are determined to be the predicted propagation result corresponding to the to-be-propagated information. The predicted propagation result can also include the predicted number of participants in the activity corresponding to the to-be-propagated information. For example, the number of people viewing the to-be-propagated information at each time of predicted propagation can be obtained, then the number of people viewing the to-be-propagated information at each time of predicted propagation is added to obtain a sum, and finally the sum is divided by the number of times of predicted propagation, thereby obtaining the predicted number of participants in the activity corresponding to the to-be-propagated information.

[0286] As can be known from the above, in the embodiment of the present application, the historical propagation data recorded under the historical information propagation task is acquired, and the first threshold probability of each object in the interaction graph becoming an information propagator and the second threshold probability of each object becoming an information invitee are determined according to the historical propagation data, and the interaction graph comprises the nodes generated for each object and the edge connection structure between different nodes; the first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information is determined; the objects in the plurality of objects whose first random probability is greater than the first threshold probability are determined as information propagation objects, and the to-be-propagated information is sent to the information propagation objects; the to-be-propagated object corresponding to each information propagation object in the plurality of objects is determined, and the second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information is determined; the object in the to-be-propagated object whose second random probability is greater than the second threshold probability is determined as a predicted propagation object, and the to-be-propagated information is propagated to the predicted propagation object. In this way, the first threshold probability of an object in the interaction graph becoming an information propagator and the second threshold probability of the object becoming an information invitee are determined by using the historical propagation data of the historical information, when the first random probability of the object in the interaction graph is greater than the first threshold probability, the object can be used as an information propagation object of the to-be-propagated information, among the to-be-propagated objects corresponding to the information propagation object, the to-be-propagated object whose second random probability is greater than the second threshold probability can be determined as an information invitee of the to-be-propagated information, that is, a predicted propagation object, and then the to-be-propagated information is propagated to the predicted propagation object, so as to realize the simulation of the invitation behavior in the information propagation process on the network. Compared with the mechanical propagation scheme in the related art, the present application improves the diversity and authenticity of information propagation prediction, thereby improving the effect of information propagation prediction.

[0287] In addition, it should be noted that in the embodiment of the present application, the to-be-propagated information is predicted to be propagated based on the propagation model of the independent cascade and invitation model provided in the embodiment of the present application during the propagation process, that is, the data processing method provided in the embodiment of the present application can be applied to the independent cascade and invitation model.

[0288] Please refer to Figure 13a , Figure 13a is a propagation effect diagram of the independent cascade and invitation model provided in the embodiment of the present application.

[0289] Among them, Figure 13a The column under Model in the table is different information propagation model, and TXG-A, TXG-B, TXG-C, TXG-D, Diggs and Twitter are different test data sets.

[0290] ICI is the independent cascade and invitation model provided in the embodiment of the present application. Compared with other information propagation models, the independent cascade and invitation model provided in the embodiment of the present application has a root mean square error (RMSE). The root mean square error is the square root of the ratio of the square of the deviation between the predicted value and the true value to the number of observations n. In actual measurements, the number of observations n is always limited, and the true value can only be replaced by the most reliable (optimal) value.

[0291] Depend on Figure 13a As can be seen, the independent cascade and invitation models provided in the embodiments of the present application all have low root mean square errors under different data sets, indicating that when the independent cascade and invitation models predict the propagation of information to be propagated, the difference between their predicted propagation effect and the actual propagation effect is small, and the predicted propagation effect is better. Therefore, the independent cascade and invitation models provided in the embodiments of the present application have good information propagation effects.

[0292] Please also refer to Figure 13b , Figure 13b This is another schematic diagram of the propagation effect of the independent cascade and invitation model provided in an embodiment of the present application.

[0293] ICI is the independent cascade and invitation model provided in this embodiment, while IC is the traditional independent cascade model. The number of people who have spread the message is the number of people who have spread the message after the predicted spread, and the number of layers is the number of layers of spread relative to the initial source of the message.

[0294] Compared with the data after the information to be disseminated is disseminated in a real dissemination environment, the independent cascade and invitation model in this application has a smaller error with the real data, for example, the relative error is only 2.54%. The error of the independent cascade model is 12.68%. It can be seen that the independent cascade and invitation model provided in the embodiment of this application can more accurately predict the effect of information dissemination.

[0295] Please continue reading Figure 14 , Figure 14 is another flow chart of the data processing method provided in an embodiment of the present application. The data processing method may further include the following steps:

[0296] Step 501: Obtain historical propagation data recorded under the historical information propagation task, and determine, based on the historical propagation data, at least one target object type corresponding to the historical information disseminator, and a first distribution probability corresponding to each target object type among all target object types;

[0297] Step 502: Determine a second distribution probability of historical information disseminators in the object based on the historical dissemination data;

[0298] Step 503, determining, according to the historical propagation data, a third distribution probability of each object type of the object in all object types;

[0299] Step 504, determining, as a first threshold probability of each object in the interaction graph becoming an information propagator, a ratio of a product of the first distribution probability and the second distribution probability to the third distribution probability;

[0300] Step 505, determining, according to the historical propagation data, a propagation list corresponding to the historical information propagator, and a number of historical information invitees corresponding to each invited position in the propagation list;

[0301] Step 506, dividing the number of historical information invitees corresponding to each invited position by a total number of historical information invitees to obtain a first position distribution probability of each invited position in all invited positions;

[0302] Step 507, determining, according to the historical propagation data, a propagation distribution probability of the historical information invitee in all historical invitees corresponding to the historical information propagator;

[0303] Step 508, determining, in the propagation list, a second position distribution probability of each invitation position in all invitation positions of the propagation list;

[0304] Step 509, determining, as a second threshold probability of each object in the interaction graph becoming an information invitee, a ratio of a product of the first position distribution probability and the propagation distribution probability to the second position distribution probability;

[0305] Step 510, determining a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information;

[0306] Step 511, determining, as information propagation objects, objects in the plurality of objects whose first random probability is greater than the first threshold probability, and sending the to-be-propagated information to the information propagation objects;

[0307] Step 512, determining, in the plurality of objects, a to-be-propagated object corresponding to each information propagation object, and determining a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information;

[0308] Step 513, determining, as a predicted propagation object, an object in the to-be-propagated object whose second random probability is greater than the second threshold probability, and propagating the to-be-propagated information to the predicted propagation object.

[0309] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the data processing method, which will not be described here.

[0310] Please refer to Figure 15 ,Figure 15 FIG. 1 is a schematic diagram of a data processing apparatus provided by an embodiment of the present application. The data processing apparatus is arranged in a computer device, and can be used to execute the data processing method described in the above embodiments.

[0311] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined target, and can be implemented entirely or partially by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an integral module or unit that includes the functions of the module or unit.

[0312] The information prediction propagation apparatus 600 can include:

[0313] The acquisition module 610 is configured to acquire historical propagation data recorded under a historical information propagation task, and determine, according to the historical propagation data, a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an invited information receiver, the interaction graph including nodes generated for each object and an edge connection structure between different nodes.

[0314] The first determination module 620 is configured to determine a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information.

[0315] The second determination module 630 is configured to determine, from the plurality of objects, an object whose first random probability is greater than the first threshold probability as an information propagation object, and send the to-be-propagated information to the information propagation object.

[0316] The third determination module 640 is configured to determine, from the plurality of objects, a to-be-propagated object corresponding to each information propagation object, and determine a second random probability of each to-be-propagated object becoming an invited information receiver of the to-be-propagated information.

[0317] The propagation module 650 is configured to determine, from the to-be-propagated objects, an object whose second random probability is greater than the second threshold probability as a predicted propagation object, and propagate the to-be-propagated information to the predicted propagation object.

[0318] In some embodiments, the acquisition module 610 includes a first sub-acquisition module, which is configured to:

[0319] According to the historical propagation data, determine at least one target object type corresponding to the historical information propagator, and a first distribution probability of each target object type in all target object types.

[0320] determine, according to the historical propagation data, a second distribution probability of the historical information propagator in the object;

[0321] determine, according to the historical propagation data, a third distribution probability of each object type corresponding to the object in all object types;

[0322] determine, as a first threshold probability of each object in the interaction graph becoming an information propagator, a ratio of a product of the first distribution probability and the second distribution probability to the third distribution probability.

[0323] In some embodiments, the obtaining module 610 includes a second sub-obtaining module, and the second sub-obtaining module includes a first determining unit, a second determining unit, a third determining unit, and a fourth determining unit;

[0324] The first determining unit is configured to determine, according to the historical propagation data, a propagation list corresponding to the historical information propagator, and a number of historical information invitees corresponding to each invited position in the propagation list;

[0325] divide the number of historical information invitees corresponding to each invited position by a total number of historical information invitees to obtain a first position distribution probability of each invited position in all invited positions;

[0326] The second determining unit is configured to determine, according to the historical propagation data, a propagation distribution probability of the historical information invitee in all historical invitees corresponding to the historical information propagator;

[0327] The third determining unit is configured to determine, in the propagation list, a second position distribution probability of each invitation position in all invitation positions of the propagation list;

[0328] The fourth determining unit is configured to determine, as a second threshold probability of each object in the interaction graph becoming an information invitee, a ratio of a product of the first position distribution probability and the propagation distribution probability to the second position distribution probability.

[0329] In some embodiments, the second determining unit is configured to:

[0330] determine, according to the historical propagation data, a first number of historical information propagators and a second number of invitation positions in a propagation list corresponding to each historical information propagator, each invitation position corresponding to one historical invitee;

[0331] determine, as a total number of historical invitees, a product of the first number and the second number;

[0332] determine, according to the historical propagation data, a third number of historical information invitees;

[0333] Divide the third quantity by the total quantity of historical invitees to obtain a propagation distribution probability of the historical information invitee in all historical invitees.

[0334] In some embodiments, the data processing apparatus further comprises a fourth determination module configured to:

[0335] According to the historical propagation data, determine the quantity of historical information invitees, and determine the quantity of target historical information invitees who view the historical information;

[0336] Divide the quantity of target historical information invitees by the quantity of historical information invitees to obtain a third threshold probability of each object in the interaction graph becoming an information viewer.

[0337] In some embodiments, the data processing apparatus further comprises an object determination module configured to:

[0338] After propagating the to-be-propagated information to the predicted propagation object, determine a third random probability of each predicted propagation object becoming an information viewer of the to-be-propagated information;

[0339] Among the plurality of predicted propagation objects, determine an object whose third random probability is greater than the third threshold probability as a predicted participant object who views the to-be-propagated information.

[0340] In some embodiments, the object determination module is further configured to:

[0341] After determining, among the plurality of predicted propagation objects, an object whose third random probability is greater than the third threshold probability as a predicted participant object who views the to-be-propagated information, replace the predicted participant object with a new information propagation object;

[0342] And return to perform determining, among the plurality of objects, a second random probability of each information propagation object corresponding to the to-be-propagated object, and determining a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information, until no new predicted participant object can be determined.

[0343] In some embodiments, the data processing apparatus further comprises a propagation effect determination module configured to:

[0344] When no new predicted participant object can be determined, determine a predicted propagation quantity corresponding to the to-be-propagated information;

[0345] According to the propagation relationship between the information propagation object and the predicted propagation object, determine a predicted propagation path corresponding to the to-be-propagated information, and determine a path propagation quantity corresponding to each predicted propagation path;

[0346] Determine the predicted propagation result corresponding to the to-be-propagated information according to the predicted propagation quantity and the path propagation quantity.

[0347] In some embodiments, the propagation effect determination module is further configured to:

[0348] obtain a predicted propagation number of the to-be-propagated information;

[0349] count a total propagation population of the to-be-propagated information in the multiple times of predicted propagation;

[0350] divide the total propagation population by the predicted propagation number to obtain a predicted propagation population corresponding to the to-be-propagated information.

[0351] In some embodiments, the obtaining module 610 further includes a third sub-obtaining module configured to:

[0352] obtain a target information type corresponding to the to-be-propagated information;

[0353] determine historical information matching the information type and the target information type, and determine a historical information propagation task of the historical information;

[0354] obtain historical propagation data recorded in the historical information propagation task.

[0355] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the data processing method, which will not be described here.

[0356] In the embodiment of the present application, the acquisition module 610 acquires historical propagation data recorded under historical information propagation tasks, and determines a first threshold probability of each object in the interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee according to the historical propagation data, the interaction graph including nodes generated for each object and edge connection structures between different nodes; the first determination module 620 determines a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information; the second determination module 630 determines objects in the plurality of objects whose first random probability is greater than the first threshold probability as information propagation objects, and sends the to-be-propagated information to the information propagation objects; the third determination module 640 determines a to-be-propagated object corresponding to each information propagation object in the plurality of objects, and determines a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information; the propagation module 650 determines an object in the to-be-propagated object whose second random probability is greater than the second threshold probability as a predicted propagation object, and propagates the to-be-propagated information to the predicted propagation object. In this way, the first threshold probability of an object in the interaction graph becoming an information propagator and the second threshold probability of becoming an information invitee are determined by using historical propagation data of historical information, when the first random probability of the object in the interaction graph is greater than the first threshold probability, the object can be used as an information propagation object of the to-be-propagated information, among to-be-propagated objects corresponding to the information propagation object, a to-be-propagated object whose second random probability is greater than the second threshold probability can be determined as an information invitee of the to-be-propagated information, that is, a predicted propagation object, and then the to-be-propagated information is propagated to the predicted propagation object, so as to realize the simulation of the invitation behavior in the information propagation process on the network. Compared with the mechanical propagation scheme in the related art, the present application improves the diversity and authenticity of information propagation prediction, thereby improving the effect of information propagation prediction.

[0357] The computer device provided in the embodiment of the present application can be a server, as shown in the figure, which shows a structural schematic diagram of the server related to the embodiment of the present application, in particular: Figure 16

[0358] The server can include a processor 701 with one or more processing cores, a memory 702 with one or more computer readable storage media, a power supply 703, and an input unit 704, and the like. Those skilled in the art can understand that the server structure shown in the figure does not constitute a limitation on the server, and can include more or fewer components than the figure, or combine certain components, or different component arrangements. Among them: Figure 16

[0359] ​​The processor 701 is the control center of the server, connects the various parts of the entire server with various interfaces and lines, and performs various functions of the server and processes data by running or executing software programs and / or modules stored in the memory 702 and calling data stored in the memory 702, thereby overall controlling the server. Optionally, the processor 701 can include one or more processing cores; preferably, the processor 701 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 701.

[0360] The memory 702 can be used to store software programs and modules, and the processor 701 executes various functions and data processing by running the software programs and modules stored in the memory 702. The memory 702 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data created according to the use of the server, etc. In addition, the memory 702 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 702 can also include a memory controller to provide access for the processor 701 to the memory 702.

[0361] The computer device further includes a power supply 703 for supplying power to various components. Optionally, the power supply 703 can be logically connected to the processor 701 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 703 can also include one or more than one direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power state indicator, and any other components.

[0362] The computer device can further include an input unit 704, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0363] Although not shown, the computer device can also include a display unit, etc., which will not be described here. Specifically, in the present embodiment, the processor 701 in the computer device will load the executable file corresponding to the process of one or more than one application program into the memory 702 according to the following instructions, and run the application program stored in the memory 702 by the processor 701, thereby realizing the various method steps provided by the foregoing embodiments, as follows:

[0364] obtain historical propagation data recorded under a historical information propagation task, and determine, according to the historical propagation data, a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee, the interaction graph including nodes generated for each object and edge connection structures between different nodes;

[0365] determine a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information;

[0366] determine, as information propagation objects, objects in the plurality of objects whose first random probability is greater than the first threshold probability, and send the to-be-propagated information to the information propagation objects;

[0367] determine, for each information propagation object in the plurality of objects, a to-be-propagated object corresponding to the information propagation object, and determine a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information;

[0368] determine, as a predicted propagation object, an object in the to-be-propagated object whose second random probability is greater than the second threshold probability, and propagate the to-be-propagated information to the predicted propagation object.

[0369] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the data processing method, which will not be described here.

[0370] Embodiments of the present application also provide a computer device, which can be a terminal, as shown in the structure schematic diagram of the terminal involved in the embodiments of the present application, specifically: Figure 17

[0371] The computer device can include radio frequency (RF) circuit 801, memory 802 including one or more computer readable storage media, input unit 803, display unit 804, sensor 805, audio circuit 806, wireless fidelity (WiFi) module 807, processor 808 including one or more processing cores, and power supply 809, and the like. Those skilled in the art can understand that the structure of the terminal shown in the above embodiment does not constitute a limitation on the terminal, and can include more or fewer components than the diagram, or combine certain components, or different component arrangements. Among them: Figure 17

[0372] ​​The RF circuit 801 can be used for receiving and sending signals in the process of information or communication, in particular, receiving the downlink information from the base station and sending the uplink data to the base station. Generally, the RF circuit 801 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, etc. In addition, the RF circuit 801 can also communicate with the network and other devices through wireless communication. The wireless communication can use any communication standards or protocols, including but not limited to Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0373] The memory 802 can be used to store software programs and modules, and the processor 808 can execute various functions and information retrieval by running the software programs and modules stored in the memory 802. The memory 802 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; the data storage area can store data created according to the use of the terminal (such as audio data, a phone book, etc.), etc. In addition, the memory 802 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 802 can also include a memory controller to provide access for the processor 808 and the input unit 803 to the memory 802.

[0374] The input unit 803 can be configured to receive input of numbers or characters, and to generate a key signal, a mouse signal, a joystick signal, an optical or a track ball signal associated with object setting and function control. Specifically, in one embodiment, the input unit 803 can include a touch-sensitive surface and other input devices. The touch-sensitive surface, also known as a touch display or a touch pad, can gather information relative to the object's touch operation (e.g., the object's operation on or near the touch-sensitive surface using a finger, a stylus, or any suitable object or accessory) and drive a corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface can include two parts, a touch detection device and a touch controller. The touch detection device detects the object's touch position and detects a signal caused by the touch operation, and transmits the signal to the touch controller. The touch controller receives the touch information from the touch detection device, converts it into touch coordinates, and sends it to the processor 808, and can also receive commands from the processor 808 and execute them. In addition, the touch-sensitive surface can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface, the input unit 803 can also include other input devices. Specifically, the other input devices can include one or more of a physical keyboard, function keys (e.g., volume control keys, on / off keys, etc.), a trackball, a mouse, a joystick, etc.

[0375] The display unit 804 can be configured to display information input by the object or information provided to the object, and various graphical object interfaces of the terminal, which can be composed of graphics, text, icons, video, and any combination thereof. The display unit 804 can include a display panel, which can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch-sensitive surface can cover the display panel, and when the touch-sensitive surface detects a touch operation on or near it, it transmits to the processor 808 to determine the type of touch event, and then the processor 808 provides corresponding visual output on the display panel according to the type of touch event. Although in the above description, the touch-sensitive surface and the display panel are implemented as two independent components to realize input and output functions, in some embodiments, the touch-sensitive surface and the display panel can be integrated to realize input and output functions. Figure 17

[0376] ​The terminal can also include at least one sensor 805, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor can include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel according to the brightness of ambient light, and the proximity sensor can turn off the display panel and / or backlight when the terminal is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and when at rest, it can detect the magnitude and direction of gravity, which can be used for applications such as identifying the posture of the mobile phone (such as switching between landscape and portrait screens, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometers, tapping), and the like. As for other sensors that the terminal can also be configured, such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, they will not be described here.

[0377] The audio circuit 806, the speaker, and the microphone can provide an audio interface between the object and the terminal. The audio circuit 806 can convert the received audio data into an electrical signal and transmit it to the speaker, which converts it into a sound signal output. On the other hand, the microphone collects sound signals and converts them into electrical signals, which are received by the audio circuit 806 and converted into audio data. After being processed by the processor 808, the audio data is output to the RF circuit 801 for transmission to another terminal, for example, or to the memory 802 for further processing. The audio circuit 806 can also include an earphone jack to provide communication between an external earphone and the terminal.

[0378] WiFi is a short-range wireless transmission technology. The terminal can help the object to send and receive emails, browse web pages, and access streaming media through the WiFi module 807, which provides the object with wireless broadband Internet access. Although Figure 17 The WiFi module 807 is shown, but it is understood that it does not belong to the essential components of the terminal and can be omitted as needed without changing the essence of the application.

[0379] The processor 808 is the control center of the terminal, which connects all parts of the mobile phone through various interfaces and lines, executes various functions of the terminal and processes data by running or executing software programs and / or modules stored in the memory 802 and calling data stored in the memory 802, thereby monitoring the mobile phone as a whole. Optionally, the processor 808 can include one or more processing cores; preferably, the processor 808 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, the object interface, and the application program, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 808.

[0380] The terminal also includes a power supply 809 (such as a battery) to supply power to each component. Preferably, the power supply can be logically connected to the processor 808 through a power management system, so that the power management system can manage charging, discharging, and power consumption management, etc. The power supply 809 can also include one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and any other components.

[0381] Although not shown, the terminal can also include a camera, a Bluetooth module, etc., which will not be described here. In particular, in the present embodiment, the processor 808 in the terminal will load the executable file corresponding to the process of one or more application programs into the memory 802 according to the following instructions, and run the application program stored in the memory 802 by the processor 808, so as to realize various functions:

[0382] Obtain historical propagation data recorded under the historical information propagation task, and determine a first threshold probability of each object in the interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee according to the historical propagation data, the interaction graph including nodes generated for each object and edge connection structures between different nodes;

[0383] Determine a first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information;

[0384] Determine the objects in the plurality of objects whose first random probability is greater than the first threshold probability as information propagation objects, and send the to-be-propagated information to the information propagation objects;

[0385] Determine the to-be-propagated objects corresponding to each information propagation object in the plurality of objects, and determine a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information;

[0386] Determine the objects in the to-be-propagated objects whose second random probability is greater than the second threshold probability as predicted propagation objects, and propagate the to-be-propagated information to the predicted propagation objects.

[0387] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the data processing method above, which will not be described here.

[0388] From the above, in the embodiments of the present application, by acquiring the historical propagation data recorded under the historical information propagation task, and determining the first threshold probability of each object in the interaction graph becoming an information propagator and the second threshold probability of becoming an information invitee according to the historical propagation data, the interaction graph contains the nodes generated for each object and the edge connection structure between different nodes; determining the first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information; determining the information propagation object as the object in the plurality of objects whose first random probability is greater than the first threshold probability, and sending the to-be-propagated information to the information propagation object; determining the to-be-propagated object corresponding to each information propagation object in the plurality of objects, and determining the second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information; determining the predicted propagation object as the object in the to-be-propagated object whose second random probability is greater than the second threshold probability, and propagating the to-be-propagated information to the predicted propagation object. In this way, the first threshold probability of the object in the interaction graph becoming an information propagator and the second threshold probability of becoming an information invitee are determined by using the historical propagation data of the historical information, when the first random probability of the object in the interaction graph is greater than the first threshold probability, the object can be used as an information propagation object of the to-be-propagated information, among the to-be-propagated objects corresponding to the information propagation object, the to-be-propagated object whose second random probability is greater than the second threshold probability can be determined as an information invitee of the to-be-propagated information, that is, a predicted propagation object, and then the to-be-propagated information is propagated to the predicted propagation object, so as to realize the invitation behavior in the information propagation process on the network. Compared with the mechanical propagation scheme in the related art, the present application improves the diversity and authenticity of information propagation prediction, thereby improving the effect of information propagation prediction.

[0389] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or controlled by instructions related to hardware.

[0390] Therefore, the embodiments of the present application provide a computer readable storage medium, which stores a plurality of instructions. The instructions can be loaded by a processor to execute the steps in any data processing method provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0391] Acquiring the historical propagation data recorded under the historical information propagation task, and determining the first threshold probability of each object in the interaction graph becoming an information propagator and the second threshold probability of becoming an information invitee according to the historical propagation data, the interaction graph contains the nodes generated for each object and the edge connection structure between different nodes;

[0392] Determining the first random probability of each object in the interaction graph becoming an information propagator of the to-be-propagated information;

[0393] determining, from the plurality of objects, an object whose first random probability is greater than a first threshold probability as an information propagation object, and sending the to-be-propagated information to the information propagation object;

[0394] determining, from the plurality of objects, a to-be-propagated object corresponding to each information propagation object, and determining a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information;

[0395] determining, from the to-be-propagated objects, an object whose second random probability is greater than a second threshold probability as a predicted propagation object, and propagating the to-be-propagated information to the predicted propagation object.

[0396] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the detailed description of the data processing method above, which will not be described here again.

[0397] According to an aspect of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the data processing method provided in any of the optional implementation manners provided in the above embodiments.

[0398] The specific implementation of each operation can be referred to the above embodiments, which will not be described here again.

[0399] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0400] Since the instructions stored in the computer readable storage medium can execute the steps in any of the data processing methods provided in the embodiments of the present application, the beneficial effects of any of the data processing methods provided in the embodiments of the present application can be achieved, which are described in detail in the above embodiments, and will not be described here again.

[0401] The above describes in detail the data processing method, device, equipment and medium provided in the embodiments of the present application. The principle and implementation manner of the present application are described by applying specific examples in this paper. The above embodiment description is only used to help understand the method and core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range can be changed; and in view of the above, the content of the present description should not be understood as a limitation of the present application.

Claims

1. A data processing method, characterized by, The method comprises: acquiring historical propagation data recorded under a historical information propagation task, and determining a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee, the interaction graph comprising nodes generated for each object and edge connection structures between different nodes; determining a first random probability of each object in the interaction graph becoming an information propagator of to-be-propagated information; determining, from a plurality of objects, an object whose first random probability is greater than the first threshold probability as an information propagation object, and sending the to-be-propagated information to the information propagation object; determining, from the plurality of objects, a to-be-propagated object corresponding to each information propagation object, and determining a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information; determining, from the to-be-propagated objects, an object whose second random probability is greater than the second threshold probability as a predicted propagation object, and propagating the to-be-propagated information to the predicted propagation object.

2. The data processing method according to claim 1, characterized in that, The method further comprises: determining, according to the historical propagation data, at least one target object type corresponding to a historical information propagator and a first distribution probability of each target object type in all target object types; determining, according to the historical propagation data, a second distribution probability of the historical information propagator in the objects; determining, according to the historical propagation data, a third distribution probability of each object type corresponding to the objects in all object types; determining, as the first threshold probability of each object in the interaction graph becoming an information propagator, a ratio of a product of the first distribution probability and the second distribution probability to the third distribution probability.

3. The data processing method of claim 1, wherein, The method further comprises: determining, according to the historical propagation data, a propagation list corresponding to a historical information propagator and a number of historical information invitees corresponding to each invited position in the propagation list; dividing the number of historical information invitees corresponding to each invited position by a total number of historical information invitees to obtain a first position distribution probability of each invited position in all invited positions; determining, according to the historical propagation data, a propagation distribution probability of the historical information invitees in all historical to-be-invited objects corresponding to the historical information propagator; determining, in the propagation list, a second position distribution probability of each invited position in all invited positions of the propagation list; determining, as the second threshold probability of each object in the interaction graph becoming an information invitee, a ratio of a product of the first position distribution probability and the propagation distribution probability to the second position distribution probability.

4. The data processing method according to claim 3, characterized in that, The method further comprises: According to the historical propagation data, a first quantity of the historical information propagators and a second quantity of invitation positions in the propagation list corresponding to each of the historical information propagators are determined, each of the invitation positions corresponding to a historical invitee; A product of the first quantity and the second quantity is determined as a total quantity of the historical invitees; According to the historical propagation data, a third quantity of the historical information invitees is determined; The third quantity is divided by the total quantity of the historical invitees to obtain a propagation distribution probability of the historical information invitee in all the historical invitees.

5. The data processing method of claim 1, wherein, Further comprising: According to the historical propagation data, a quantity of historical information invitees and a quantity of target historical information invitees who view historical information are determined; The quantity of the target historical information invitees is divided by the quantity of the historical information invitees to obtain a third threshold probability of each object in the interaction graph becoming an information viewer.

6. The data processing method according to claim 5, characterized in that, After the propagation of the to-be-propagated information to the predicted propagation object, further comprising: A third random probability of each of the predicted propagation objects becoming an information viewer of the to-be-propagated information is determined; In the plurality of predicted propagation objects, an object whose third random probability is greater than the third threshold probability is determined as a predicted participant object who views the to-be-propagated information.

7. The data processing method according to claim 6, characterized in that, After the plurality of predicted propagation objects, an object whose third random probability is greater than the third threshold probability is determined as a predicted participant object who views the to-be-propagated information, further comprising: The predicted participant object is replaced with a new information propagator; And returning to execute the determination of the to-be-propagated object corresponding to each of the information propagators in the plurality of objects and the determination of a second random probability of each of the to-be-propagated objects becoming an information invitee of the to-be-propagated information until a new predicted participant object cannot be determined.

8. The data processing method according to claim 7, characterized in that, Further comprising: When a new predicted participant object cannot be determined, a predicted propagation quantity corresponding to the to-be-propagated information is determined; According to the propagation relationship between the information propagator and the predicted propagation object, a predicted propagation path corresponding to the to-be-propagated information is determined, and a path propagation quantity corresponding to each of the predicted propagation paths is determined; The predicted propagation quantity and the path propagation quantity are determined as a predicted propagation result corresponding to the to-be-propagated information.

9. The data processing method according to claim 8, characterized in that, The determination of the predicted propagation quantity corresponding to the to-be-propagated information comprises: A predicted propagation frequency of the to-be-propagated information is obtained; A total propagation quantity of the to-be-propagated information in a plurality of times of predicted propagation is counted; The total propagation quantity is divided by the predicted propagation frequency to obtain the predicted propagation quantity corresponding to the to-be-propagated information.

10. The data processing method of claim 1, wherein, The obtaining of the historical propagation data recorded under the historical information propagation task comprises: A target information type corresponding to the to-be-propagated information is obtained; A historical information whose information type matches the target information type is determined, and a historical information propagation task of the historical information is determined; The historical propagation data recorded under the historical information propagation task is obtained.

11. A data processing apparatus, characterized by Comprising: An acquisition module is configured to acquire historical propagation data recorded under a historical information propagation task, and determine a first threshold probability of each object in an interaction graph becoming an information propagator and a second threshold probability of becoming an information invitee, the interaction graph including nodes generated for each object and edge connection structures between different nodes; A first determination module is configured to determine a first random probability of each object in the interaction graph becoming an information propagator of to-be-propagated information; A second determination module is configured to determine, from a plurality of objects, an object whose first random probability is greater than the first threshold probability as an information propagation object, and send the to-be-propagated information to the information propagation object; A third determination module is configured to determine, from the plurality of objects, a to-be-propagated object corresponding to each information propagation object, and determine a second random probability of each to-be-propagated object becoming an information invitee of the to-be-propagated information; A propagation module is configured to determine, from the to-be-propagated objects, an object whose second random probability is greater than the second threshold probability as a predicted propagation object, and propagate the to-be-propagated information to the predicted propagation object.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a plurality of instructions adapted to be loaded by the processor to execute the data processing method of any one of claims 1 to 10.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the data processing method of any one of claims 1 to 10.

14. A computer program product comprising computer programs or instructions, characterized in that, The computer program or instructions are executed by the processor to implement the data processing method of any one of claims 1 to 10.

Images