CN111210198B

CN111210198B - Information delivery method and device and server

Info

Publication number: CN111210198B
Application number: CN201911400698.5A
Authority: CN
Inventors: 姚婕; 费红琳; 肖巧巧; 丁杰
Original assignee: Guangzhou Gaoqi Cloud Information Technology Co ltd
Current assignee: Guangzhou Gaoqi Cloud Information Technology Co ltd
Priority date: 2019-12-30
Filing date: 2019-12-30
Publication date: 2020-08-21
Anticipated expiration: 2039-12-30
Also published as: CN111210198A

Abstract

The invention relates to the technical field of data processing, in particular to an information delivery method, an information delivery device and an information delivery server. According to the method and the system, enterprise portrait analysis is carried out on enterprise data, intelligent information delivery is carried out according to the policy information in the policy information pool, the policy information which is more in line with the conditions of the enterprises and the current research and development progress can be delivered to each enterprise, the policy declaration efficiency and the declaration matching degree are improved, and the labor cost and the time cost are further reduced.

Description

Information delivery method and device and server

Technical Field

The invention relates to the technical field of data processing, in particular to an information delivery method, an information delivery device and a server.

Background

At present, with increasing of innovative enterprises, various supporting forces of government policies on the innovative enterprises are gradually increased, and with increasing of policies, when the enterprises usually apply to various government policies, a great deal of time and manpower are needed to research whether a great number of policies meet self conditions and current research and development progress, so that the efficiency of policy application is very low, and a great risk is missed to push important policies.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, the present application aims to provide an information delivery method, an information delivery device, and a server, which can deliver policy information more conforming to the conditions of each enterprise and the current research and development progress for each enterprise, improve the policy declaration efficiency and the declaration matching degree, and further reduce the labor cost and the time cost.

In a first aspect, the present application provides an information delivery method, applied to a server, where the server is in communication connection with at least one information receiving terminal, and the method includes:

carrying out enterprise portrait analysis on the big data of each enterprise in the big data pool to obtain portrait analysis results of different enterprises;

matching the portrait analysis result of each enterprise with policy information in a policy information pool to obtain target policy information to be delivered to each enterprise;

and respectively delivering the matched target policy information to the information receiving terminal of each corresponding enterprise.

In a possible design of the first aspect, the step of performing enterprise representation analysis on the big data of each enterprise in the big data pool to obtain representation analysis results of different enterprises includes:

the method comprises the steps that a first big data behavior attribute of big data of each enterprise in a big data pool is obtained, wherein the first big data behavior attribute is used for representing time sequence node span and empty sequence node span of a big data acquisition process of the enterprise;

performing attribute identification on the first big data behavior attribute to obtain first data time sequence characteristic information and data space sequence characteristic information corresponding to the first data time sequence characteristic information;

acquiring first big data characteristic information and policy interaction information of big data of the enterprise, and extracting characteristic node information of the first big data characteristic information, wherein the characteristic node information of the first big data characteristic information comprises a policy item designated node;

acquiring policy item designated nodes of preset historical big data, and adjusting the policy item designated nodes of the first big data characteristic information according to the policy item designated nodes to enable the logical association relationship between the policy item designated nodes in the first big data characteristic information to be matched with the logical association relationship between the policy item designated nodes in the preset historical big data;

after the node information corresponding to the adjustment position of the policy item designated node is stored, the characteristic node information of second big data characteristic information is obtained, and the second big data characteristic information is generated according to the characteristic node information of the second big data characteristic information;

according to the policy interaction information and the feature node information of the second big data feature information, searching and obtaining data null sequence feature information matched with the policy interaction information and first data time sequence feature information corresponding to the data null sequence feature information, and performing time sequence adjustment on the first data time sequence feature information corresponding to the data null sequence feature information according to the feature node information of the second big data feature information to obtain second data time sequence feature information;

fusing the second data time sequence characteristic information and the second big data characteristic information to obtain fused portrait characteristic information of the enterprise;

and carrying out enterprise portrait analysis on the fusion portrait feature information of the enterprise to obtain a portrait analysis result of the enterprise.

In a possible design of the first aspect, the step of performing enterprise portrait analysis on the fusion portrait feature information of the enterprise to obtain a portrait analysis result of the enterprise includes:

the method comprises the steps of extracting fusion portrait behavior characteristic information and fusion portrait enterprise operation range characteristic information from fusion portrait characteristic information of an enterprise;

respectively carrying out feature splitting on the behavior feature information of the fused portrait and the enterprise operation range feature information of the fused portrait to obtain corresponding split feature information;

determining first to-be-determined splitting characteristic information corresponding to first corresponding last splitting characteristic information in the first splitting characteristic information; the first corresponding last splitting characteristic information is the corresponding last splitting characteristic information corresponding to the behavior characteristic information of the previous fused image;

determining second to-be-determined splitting characteristic information corresponding to second corresponding last splitting characteristic information in the second splitting characteristic information; the second corresponding last splitting characteristic information is the last splitting characteristic information corresponding to the previous operation range characteristic information of the enterprise with the fused image;

calculating the feature association degree between each splitting feature information in the first to-be-determined splitting feature information and the first corresponding last splitting feature information, if the first splitting characteristic information in the first to-be-determined splitting characteristic information has the minimum characteristic association degree with the first corresponding last splitting characteristic information and is within the set association degree range, selecting the first splitting characteristic information as first selected splitting characteristic information, calculating the characteristic association degree between each splitting characteristic information in the second characteristic information to be split and the second splitting characteristic information corresponding to the splitting characteristic information at the last time respectively, if the second splitting characteristic information in the second pending splitting characteristic information has the minimum characteristic association degree with the second corresponding last splitting characteristic information, and in the set association degree range, selecting the second splitting characteristic information as second selected splitting characteristic information;

according to the first selected splitting characteristic information, corresponding first splitting characteristic information corresponding to the first selected splitting characteristic information, second selected splitting characteristic information, corresponding second selected splitting characteristic information and corresponding second last splitting characteristic information corresponding to the second selected splitting characteristic information, determining first portrait characteristic information corresponding to the first selected splitting characteristic information and the second selected splitting characteristic information respectively, wherein the first portrait characteristic information comprises portrait type information and portrait characteristic node information based on an enterprise portrait, and the corresponding last splitting characteristic information is splitting characteristic information corresponding to the behavior characteristic information of a previous fused portrait of a current person and the enterprise operation range characteristic information of the previous fused portrait;

determining third to-be-determined splitting characteristic information corresponding to first splitting characteristic information in the second splitting characteristic information, selecting third selected splitting characteristic information corresponding to the first splitting characteristic information from the third to-be-determined splitting characteristic information, and determining characteristic node information corresponding to the third selected splitting characteristic information and the first splitting characteristic information respectively according to the third selected splitting characteristic information and the corresponding first splitting characteristic information, wherein the characteristic node information is characteristic node information of each splitting characteristic information relative to the fused portrait characteristic information, the first splitting characteristic information is splitting characteristic information corresponding to the fused portrait behavior characteristic information, and the second splitting characteristic information is splitting characteristic information corresponding to the fused portrait enterprise operation range characteristic information;

determining second portrait feature information corresponding to the split feature information respectively according to first portrait feature information and feature node information corresponding to the split feature information respectively, wherein the second portrait feature information comprises portrait type information and portrait feature node information, and if the identification value difference distance hierarchy degree of the portrait type information between any two split feature information is within a set association degree range, the identification value difference distance hierarchy degree of the portrait feature node information is within a set association degree range, and the difference value between the feature node information of any two split feature information is within a set association degree range, combining any two split feature information into one same fusion process to obtain the split feature information included in each fusion process;

and identifying the portrait analysis information corresponding to the split characteristic information in each time of fusion, and clustering the portrait analysis information corresponding to the split characteristic information in each time of fusion according to the respective corresponding preset portrait weights to obtain the portrait analysis result of the enterprise.

In a possible design of the first aspect, the step of matching the portrait analysis result of each enterprise with policy information in a policy information pool to obtain target policy information to be delivered to each enterprise includes:

matching the portrait analysis result of each enterprise with keywords in policy information in a policy information pool to obtain initial policy information, wherein the semantic meaning matching degree between the portrait analysis results of the enterprises in the policy information pool is greater than the set semantic meaning matching degree;

matching and controlling each unit policy information in the initial policy information according to a policy information control model configured for the enterprise in advance to generate a plurality of pieces of policy information with set semantic policy conditions and different sources of pending targets;

acquiring the information heat of each piece of pending target policy information, and calculating the information heat importance degree associated with the enterprise according to the information heat corresponding to each piece of pending target policy information;

carrying out condition association fusion weight processing on each policy of each undetermined target policy information through node conditions of the nodes and the information heat importance degree of the node conditions to obtain node conditions of a plurality of condition association fusion weights, and carrying out node clustering on the node conditions of the same condition association fusion weight;

performing time sequence correlation operation on the node clustering results of the node conditions with the same condition correlation fusion weight to generate time sequence hotspot policy information fusing each piece of policy information to be targeted;

and obtaining target policy information to be delivered to each enterprise according to the time sequence hotspot policy information of each piece of pending target policy information.

In a possible design of the first aspect, the step of performing matching control operation on each unit policy information in the initial policy information according to a policy information control model configured for the enterprise in advance to generate a plurality of pieces of policy information to be targeted, which have set semantic policy condition paragraphs and are different in source, includes:

performing matching control operation on each unit policy information in the initial policy information according to a policy information control model configured for the enterprise in advance, and acquiring a matching control parameter and a policy passing node candidate set corresponding to each unit policy information in the initial policy information;

respectively and correspondingly generating a node target condition and an initial matching condition of each policy passing node in the policy passing node candidate set;

respectively obtaining condition history passing probability and condition history application probability of the node target condition and the initial matching condition, and respectively calculating the condition probability number of the node target condition and the initial matching condition;

respectively determining a target probability unit condition corresponding to the node target condition and an initial probability unit condition of the initial matching condition according to the conditional probability numbers of the node target condition and the initial matching condition;

sequentially calculating the condition characteristic information of each target probability unit condition and each initial probability unit condition to obtain the condition characteristic information of the target probability unit condition and the condition characteristic information of the initial probability unit condition;

respectively generating a corresponding target index support vector and an initial index support vector according to the conditional feature information of each target probability unit and the conditional feature information of the initial probability unit;

comparing the target index support vector with a corresponding initial index support vector, if the target index support vector is different from the corresponding initial index support vector, comparing the node target condition with the initial matching condition according to the matching control parameter, if the node target condition and the initial matching condition do not meet the matching control parameter, calculating an exclusion semantic condition of the node target condition and the initial matching condition, and if the number of the exclusion semantic conditions in the policy passing node candidate set is greater than a set number, taking unit policy information corresponding to the policy passing node candidate set as the pending target policy information which has the set semantic policy condition paragraphs and is different in source.

In a possible design of the first aspect, the step of obtaining target policy information to be delivered to each enterprise according to the time-series hotspot policy information includes:

acquiring each node policy information of the time sequence hotspot policy information, a probability distribution map corresponding to each node policy information, and each node policy information and the probability distribution map corresponding to each node policy information in other time sequence hotspot policy information except the time sequence hotspot policy information;

generating a first delivery probability hotspot graph of a probability distribution graph about the node policy information according to the node policy information of the time sequence hotspot policy information and the probability distribution graph corresponding to the node policy information, and generating a second delivery probability hotspot graph of the probability distribution graph about the node policy information according to the node policy information of other time sequence hotspot policy information and the probability distribution graph corresponding to the node policy information, wherein the node policy information of the time sequence hotspot policy information corresponds to the node policy information of other time sequence hotspot policy information;

sequentially comparing the probability distribution map corresponding to the policy information of each node in the second delivery probability hotspot graph with the probability distribution map corresponding to the policy information of each node in the first delivery probability hotspot graph, and judging whether the probability distribution map corresponding to the policy information of the node in the second delivery probability hotspot graph is larger than the probability distribution map corresponding to the policy information of the node in the first delivery probability hotspot graph;

for each piece of node policy information, when the probability distribution map of the second delivery probability hotspot map is larger than or smaller than the corresponding first delivery probability hotspot map, determining the difference value between the probability distribution map of the first delivery probability hotspot map and the probability distribution map of the second delivery probability hotspot map as a delivery probability hotspot comparison value corresponding to the node policy information, and generating the corresponding delivery probability hotspot comparison map according to the piece of node policy information and the delivery probability hotspot comparison value corresponding to the piece of node policy information;

acquiring a high-density area and a low-density area of the delivery probability hotspot comparison map, and comparing the high-density area and the low-density area with a set area range, wherein the set area range comprises a high-value range area and a low-value range area;

when the high-value range area is larger than the high-density area and the low-value range area is smaller than the low-density area, processing the second delivery probability hotspot graph according to the delivery probability hotspot comparison graph, and determining corresponding policy information in the processed second delivery probability hotspot graph as target policy information to be delivered to the enterprise;

and when the high-value range area is not larger than the high-density area and the low-value range area is not smaller than the low-density area, processing the first delivery probability hotspot graph according to the delivery probability hotspot comparison graph, and determining policy information corresponding to the processed first delivery probability hotspot graph as target policy information to be delivered to the enterprise.

In one possible design of the first aspect, the method further includes:

and updating policy behavior data in the big data of the enterprise according to the feedback information aiming at the target policy information and sent by the information receiving terminal of each corresponding enterprise, so as to optimize the matching process of the target policy information delivered to the enterprise next time according to the policy behavior data.

In a second aspect, an embodiment of the present application further provides an information delivery apparatus, which is applied to a server, where the server is in communication connection with at least one information receiving terminal, and the apparatus includes:

the image analysis module is used for carrying out enterprise image analysis on the big data of each enterprise in the big data pool to obtain image analysis results of different enterprises;

the matching module is used for matching the portrait analysis result of each enterprise with the policy information in the policy information pool to obtain target policy information to be delivered to each enterprise;

and the delivery module is used for respectively delivering the matched target policy information to the information receiving terminal of each corresponding enterprise.

In a third aspect, an embodiment of the present application further provides a server, where the server includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be communicatively connected to at least one information receiving terminal, the machine-readable storage medium is configured to store a program, an instruction, or code, and the processor is configured to execute the program, the instruction, or the code in the machine-readable storage medium to perform the information delivery method in the first aspect or any possible design of the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where instructions are stored, and when the instructions are detected on a computer, the instructions cause the computer to perform the information delivery method in the first aspect or any one of the possible designs of the first aspect.

Based on any one of the above aspects, the method and the device perform enterprise portrait analysis on the big data of each enterprise in the big data pool to obtain portrait analysis results of different users, match the portrait analysis results of each enterprise with the policy information in the policy information pool to obtain target policy information to be delivered to each enterprise, and then deliver the matched target policy information to the information receiving terminal of each corresponding enterprise respectively. Therefore, the policy information which is more in line with the conditions of the enterprises and the current research and development progress can be delivered to each enterprise, the policy declaration efficiency and the declaration matching degree are improved, and the labor cost and the time cost are further reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic view of an application scenario of an information delivery system according to an embodiment of the present application;

FIG. 2 is a flowchart illustrating an information delivery method according to an embodiment of the present application;

FIG. 3 is a flowchart illustrating the sub-steps included in step S120 shown in FIG. 2;

FIG. 4 is a second flowchart illustrating an information delivery method according to an embodiment of the present application;

FIG. 5 is a functional block diagram of an information delivery apparatus according to an embodiment of the present application;

fig. 6 is a block diagram schematically illustrating a structure of a server for implementing the information delivery method according to an embodiment of the present application.

Detailed Description

The present application will now be described in detail with reference to the drawings, and the specific operations in the method embodiments may also be applied to the apparatus embodiments or the system embodiments. In the description of the present application, "at least one" includes one or more unless otherwise specified. "plurality" means two or more. For example, at least one of A, B and C, comprising: a alone, B alone, a and B in combination, a and C in combination, B and C in combination, and A, B and C in combination. In this application, "/" means "or, for example, A/B may mean A or B; "and/or" herein is merely an association describing an association of devices, meaning that there may be three relationships, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.

FIG. 1 is an interaction diagram of an information delivery system 10 provided by one embodiment of the present application. The information delivery system 10 may include a server 100 and an information receiving terminal 200 communicatively connected to the server 100, and the server 100 may include a processor for executing an instruction operation. The information delivery system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the information delivery system 10 may also include only some of the components shown in fig. 1 or may also include other components.

In some embodiments, the server 100 may be a single server or a group of servers. The set of operating servers may be centralized or distributed (e.g., the server 100 may be a distributed system). In some embodiments, the server 100 may be local or remote to the information receiving terminal 200. For example, the server 100 may access information stored in the information receiving terminal 200 and a database, or any combination thereof, via a network. As another example, the server 100 may be directly connected to at least one of the information receiving terminal 200 and a database to access information and/or data stored therein. In some embodiments, the server 100 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (community cloud), a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof.

In some embodiments, the server 100 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. A processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a reduced Instruction Set computer (reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

The network may be used for the exchange of information and/or data. In some embodiments, one or more components (e.g., the server 100, the information receiving terminal 200, and the database) in the information delivery system 10 may send information and/or data to other components. In some embodiments, the network may be any type of wired or wireless network, or combination thereof. Merely by way of example, Network 130 may include a wired Network, a Wireless Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a WLAN, a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a ZigBee Network, a Near Field Communication (NFC) Network, or the like, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of the information delivery system 10 may connect to the network to exchange data and/or information.

The aforementioned database may store data and/or instructions. In some embodiments, the database may store data assigned to the information receiving terminal 200. In some embodiments, the database may store data and/or instructions for the exemplary methods described herein. In some embodiments, the database may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, and the like; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double data Rate Synchronous Dynamic RAM (DDR SDRAM); static RAM (SRAM), Thyristor-Based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like. In some embodiments, the database may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, across clouds, multiple clouds, or the like, or any combination thereof.

In some embodiments, a database may be connected to a network to communicate with one or more components in the information delivery system 10 (e.g., the server 100, the information receiving terminal 200, etc.). One or more components in the information delivery system 10 may access data or instructions stored in a database via a network. In some embodiments, the database may be directly connected to one or more components of the information delivery system 10 (e.g., the server 100, the information receiving terminal 200, etc.), or in some embodiments, the database may be part of the server 100.

To solve the technical problem in the foregoing background, fig. 2 is a flowchart illustrating an information delivery method according to an embodiment of the present application, where the information delivery method according to the present application may be executed by the server 100 shown in fig. 1, and the information delivery method is described in detail below.

Step S110, enterprise portrait analysis is carried out on the big data of each enterprise in the big data pool, and portrait analysis results of different enterprises are obtained.

And step S120, matching the portrait analysis result of each enterprise with the policy information in the policy information pool to obtain target policy information to be delivered to each enterprise.

Step S130, delivering the matched target policy information to the information receiving terminal 200 of each corresponding enterprise.

Based on the above design, in the embodiment, after portrait analysis results of different users are obtained by performing enterprise portrait analysis on big data of each enterprise in the big data pool, the portrait analysis results of each enterprise are matched with policy information in the policy information pool to obtain target policy information to be posted to each enterprise, and then the matched target policy information is delivered to the information receiving terminal 200 of each corresponding enterprise. Therefore, the policy information which is more in line with the conditions of the enterprises and the current research and development progress can be delivered to each enterprise, the policy declaration efficiency and the declaration matching degree are improved, and the labor cost and the time cost are further reduced.

In one possible design, for step S110, the present embodiment may obtain, for the big data of each enterprise in the big data pool, a first big data behavior attribute of the big data of the enterprise, where the first big data behavior attribute is used to characterize a time-sequence node span and a null-sequence node span of a big data collection process of the enterprise.

Then, attribute identification can be performed on the first big data behavior attribute, and first data time sequence feature information and data empty sequence feature information corresponding to the first data time sequence feature information are obtained.

Then, first big data characteristic information and policy interaction information of big data of the enterprise can be obtained, and characteristic node information of the first big data characteristic information is extracted, wherein the characteristic node information of the first big data characteristic information comprises a policy item designated node.

Then, a policy item specifying node of the preset historical big data can be obtained, and the policy item specifying node of the first big data characteristic information is adjusted according to the policy item specifying node, so that the logical association relationship between the policy item specifying nodes in the first big data characteristic information is matched with the logical association relationship between the policy item specifying nodes in the preset historical big data.

Then, after the node information corresponding to the adjustment position of the policy item-specifying node is stored, the feature node information of the second big data feature information is obtained, and the second big data feature information is generated according to the feature node information of the second big data feature information.

Then, according to the policy interaction information and the feature node information of the second big data feature information, data null sequence feature information matched with the policy interaction information and first data time sequence feature information corresponding to the data null sequence feature information are searched and obtained, and according to the feature node information of the second big data feature information, time sequence adjustment is performed on the first data time sequence feature information corresponding to the data null sequence feature information, and second data time sequence feature information is obtained.

Then, the second data time sequence characteristic information and the second big data characteristic information can be fused to obtain the fused image characteristic information of the enterprise.

Then, enterprise image analysis can be performed on the fusion image feature information of the enterprise to obtain an image analysis result of the enterprise.

Based on the design, the time sequence node span and the empty virtual node span in the big data process are considered, the portrait analysis is comprehensively carried out by combining the big household number characteristics and the policy interaction information, and the portrait analysis method can be combined to the specific policy interaction process to greatly improve the accuracy of the portrait analysis result.

In one possible design, in the process of analyzing the enterprise portrait by performing enterprise portrait analysis on the fusion portrait feature information of the enterprise to obtain a portrait analysis result of the enterprise, specifically, fusion portrait behavior feature information and fusion portrait enterprise operation range feature information extracted from the fusion portrait feature information of the enterprise are extracted, and then feature splitting is performed on the fusion portrait behavior feature information and the fusion portrait enterprise operation range feature information respectively to obtain corresponding split feature information.

Then, in the first splitting feature information, first to-be-determined splitting feature information corresponding to the first corresponding last splitting feature information may be determined. The first corresponding last splitting characteristic information is the corresponding last splitting characteristic information corresponding to the behavior characteristic information of the previous fused image.

Then, in the second splitting feature information, second to-be-determined splitting feature information corresponding to the second corresponding last splitting feature information may be determined. The second corresponding last splitting characteristic information is the corresponding last splitting characteristic information corresponding to the previous operation range characteristic information of the enterprise with the fused image.

Then, the feature association degree between each splitting feature information in the first to-be-determined splitting feature information and the first corresponding last splitting feature information can be calculated, if the first splitting characteristic information in the first to-be-determined splitting characteristic information has the minimum characteristic association degree with the first corresponding last splitting characteristic information and is within the set association degree range, selecting the first splitting characteristic information as the first selected splitting characteristic information, calculating the characteristic association degree between each splitting characteristic information in the second characteristic information to be split and the second splitting characteristic information corresponding to the splitting characteristic information at the last time respectively, if the second splitting characteristic information in the second pending splitting characteristic information has the minimum characteristic association degree with the second corresponding last splitting characteristic information, and in the set association degree range, selecting the second splitting characteristic information as the second selected splitting characteristic information.

Then, according to the first selected splitting characteristic information and the corresponding first corresponding last splitting characteristic information, and the second selected splitting characteristic information and the corresponding second corresponding last splitting characteristic information, first image characteristic information corresponding to the first selected splitting characteristic information and the second selected splitting characteristic information respectively is determined, the first image characteristic information comprises image type information and image characteristic node information based on the enterprise image, and the corresponding last splitting characteristic information is splitting characteristic information corresponding to the current previous fused image behavior characteristic information and the previous fused image enterprise operation range characteristic information.

Then, in the second splitting characteristic information, third to-be-determined splitting characteristic information corresponding to the first splitting characteristic information is determined, third selected splitting characteristic information corresponding to the first splitting characteristic information is selected from the third to-be-determined splitting characteristic information, according to the third selected splitting characteristic information and the corresponding first splitting characteristic information, characteristic node information corresponding to the third selected splitting characteristic information and the first splitting characteristic information respectively is determined, the characteristic node information is characteristic node information of each splitting characteristic information relative to the fusion portrait characteristic information, the first splitting characteristic information is splitting characteristic information corresponding to the fusion portrait behavior characteristic information, and the second splitting characteristic information is splitting characteristic information corresponding to the fusion portrait enterprise operation range characteristic information.

Then, second image feature information corresponding to the split feature information is determined according to first image feature information and feature node information corresponding to the split feature information respectively, the second image feature information comprises portrait type information and portrait feature node information, if the identification value difference of the portrait type information between any two split feature information is within a set association degree range, the identification value difference of the portrait feature node information is within a set association degree range, and the difference between the feature node information of any two split feature information is within a set association degree range, any two split feature information are merged into the same fusion process, and the split feature information included in each fusion process is obtained.

Then, the portrait analysis information corresponding to the split feature information in each pass of fusion can be identified, and the portrait analysis information corresponding to the split feature information in each pass of fusion is clustered according to the respective corresponding preset portrait weights, so as to obtain the portrait analysis result of the enterprise.

Based on the design, the reliability of the portrait analysis is further improved, and the calculation amount is reduced on the basis of ensuring the reliability.

In one possible design, referring to fig. 3 in conjunction with step S120, the following steps may be further implemented:

and a substep S121, matching the portrait analysis result of each enterprise with the keywords in the policy information pool, and obtaining initial policy information with the semantic meaning matching degree between the portrait analysis results of the enterprises and the portrait analysis information in the policy information pool being greater than the set semantic meaning matching degree.

And a substep S122 of performing matching control operation on each unit policy information in the initial policy information according to a policy information control model configured for the enterprise in advance, and generating a plurality of pieces of pending target policy information with set semantic policy condition paragraphs and different sources.

And a substep S123 of obtaining the information heat of each piece of pending target policy information and calculating the information heat importance degree associated with the enterprise according to the information heat corresponding to each piece of pending target policy information.

And a substep S124 of performing condition association fusion weight processing on each policy of each undetermined target policy information through the node condition of the node and the information heat importance degree of the node to obtain node conditions of a plurality of condition association fusion weights, and performing node clustering on the node conditions of the same condition association fusion weight.

And a substep S125, performing a time sequence association operation on the node clustering results of the node conditions with the same condition association fusion weight to generate time sequence hotspot policy information fusing each policy information to be targeted.

And a substep S126, obtaining target policy information to be delivered to each enterprise according to the time sequence hotspot policy information of each piece of pending target policy information.

In a possible design, for the substep S122, specifically, a matching control operation may be performed on each unit policy information in the initial policy information according to a policy information control model configured for the enterprise in advance, so as to obtain a matching control parameter and a policy passing node candidate set corresponding to each unit policy information in the initial policy information. Then, node target conditions and initial matching conditions of policy passing nodes in the node candidate set are generated correspondingly, condition history passing probabilities and condition history application probabilities of the node target conditions and the initial matching conditions are obtained respectively, and the condition probability numbers of the node target conditions and the initial matching conditions are calculated respectively.

On this basis, the target probability unit condition corresponding to the node target condition and the initial probability unit condition of the initial matching condition can be respectively determined according to the conditional probability number of the node target condition and the initial matching condition, then the condition feature information of each target probability unit condition and each initial probability unit condition is sequentially calculated to obtain the target probability unit condition feature information and the initial probability unit condition feature information, and the corresponding target index support vector and the initial index support vector are respectively generated according to each target probability unit condition feature information and the initial probability unit condition feature information.

Then, the target index support vector and the corresponding initial index support vector can be compared, if the target index support vector is different from the corresponding initial index support vector, the node target condition and the initial matching condition are compared according to the matching control parameter, if the node target condition and the initial matching condition do not meet the matching control parameter, the excluded semantic condition of the node target condition and the initial matching condition is calculated, and if the number of the excluded semantic conditions in the policy passing node candidate set is larger than the set number, the unit policy information corresponding to the policy passing node candidate set is used as a plurality of pieces of pending target policy information with different set semantic policy conditions and different sources.

In one possible design, for the substep S126, the node policy information of the time-series hotspot policy information and the probability distribution map corresponding to the node policy information may be obtained, and the node policy information and the probability distribution map corresponding to the node policy information in other time-series hotspot policy information besides the time-series hotspot policy information may be obtained.

On the basis, a first delivery probability hotspot graph of the probability distribution graph about the node policy information can be generated according to the node policy information of the time sequence hotspot policy information and the probability distribution graph corresponding to the node policy information, and a second delivery probability hotspot graph of the probability distribution graph about the node policy information can be generated according to the node policy information of other time sequence hotspot policy information and the probability distribution graph corresponding to the node policy information, wherein the node policy information of the time sequence hotspot policy information corresponds to the node policy information of other time sequence hotspot policy information.

Next, the probability distribution map corresponding to the policy information of each node in the second delivery probability hotspot graph may be sequentially compared with the probability distribution map corresponding to the policy information of each node in the first delivery probability hotspot graph, and it may be determined whether the probability distribution map corresponding to the policy information of the node in the second delivery probability hotspot graph is greater than the probability distribution map corresponding to the policy information of the node in the first delivery probability hotspot graph.

Then, for each node policy information, when the probability distribution map of the second delivery probability hotspot graph is greater than or less than the corresponding first delivery probability hotspot graph probability distribution map, determining a difference value between the probability distribution map of the first delivery probability hotspot graph and the probability distribution map of the second delivery probability hotspot graph as a delivery probability hotspot comparison value corresponding to the node policy information, and generating a corresponding delivery probability hotspot comparison graph according to each node policy information and the delivery probability hotspot comparison value corresponding to each node policy information.

Then, the high-density area and the low-density area of the delivery probability hotspot comparison map can be obtained, and the high-density area and the low-density area are compared with a set area range, wherein the set area range comprises a high-value range area and a low-value range area.

And when the high-value range area is larger than the high-density area and the low-value range area is smaller than the low-density area, processing the second delivery probability hotspot graph according to the delivery probability hotspot comparison graph, and determining corresponding policy information in the processed second delivery probability hotspot graph as target policy information to be delivered to the enterprise.

And when the high-value range area is not larger than the high-density area and the low-value range area is not smaller than the low-density area, processing the first delivery probability hotspot graph according to the delivery probability hotspot comparison graph, and determining corresponding policy information in the processed first delivery probability hotspot graph as target policy information to be delivered to the enterprise.

In a possible design, please further refer to fig. 4, after step S130, the information delivery method provided in this embodiment may further include the following steps:

step S140, updating policy behavior data in the big data of each corresponding enterprise according to the feedback information aiming at the target policy information sent by the information receiving terminal 200 of the enterprise, so as to optimize the matching process of the target policy information delivered to the enterprise next time according to the policy behavior data.

In this embodiment, in order to improve the accuracy of delivering subsequent policy information and reduce the amount of calculation, an information feedback function may be provided for the information receiving terminal 200 of each enterprise, so that policy behavior data in big data of the enterprise may be continuously updated according to the feedback information, and the matching process of the target policy information delivered to the enterprise next time is optimized according to the policy behavior data.

Fig. 5 is a schematic functional module diagram of an information delivery apparatus 300 according to an embodiment of the present application, and the embodiment may divide the functional modules of the information delivery apparatus 300 according to the method embodiment executed by the server 100. For example, the functional blocks may be divided for the respective functions, or two or more functions may be integrated into one processing block. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, the division of the modules in the present application is schematic, and is only a logical function division, and there may be another division manner in actual implementation. For example, in the case of dividing each function module according to each function, the information delivery apparatus 300 shown in fig. 5 is only a schematic diagram of an apparatus. The information delivery apparatus 300 may include a representation analysis module 310, a matching module 320, and a delivery module 330, and the functions of the functional modules of the information delivery apparatus 300 will be described in detail below.

And the portrait analysis module 310 is configured to perform enterprise portrait analysis on the big data of each enterprise in the big data pool to obtain portrait analysis results of different enterprises.

And the matching module 320 is used for matching the portrait analysis result of each enterprise with the policy information in the policy information pool to obtain target policy information to be delivered to each enterprise.

And the delivery module 330 is configured to deliver the matched target policy information to the information receiving terminal 200 of each corresponding enterprise.

Further, fig. 6 is a schematic structural diagram of a server 100 for performing the information delivery method according to an embodiment of the present application. As shown in FIG. 6, the server 100 may include a network interface 110, a machine-readable storage medium 120, a processor 130, and a bus 140. The processor 130 may be one or more, and one processor 130 is illustrated in fig. 6 as an example. The network interface 110, the machine-readable storage medium 120, and the processor 130 may be connected by a bus 140 or otherwise, as exemplified by the connection by the bus 140 in fig. 6.

The machine-readable storage medium 120 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the information delivery method in the embodiment of the present application (for example, the image analysis module 310, the matching module 320, and the delivery module 330 of the information delivery apparatus 300 shown in fig. 5). The processor 130 executes various functional applications and data processing of the terminal device by detecting the software programs, instructions and modules stored in the machine-readable storage medium 120, that is, the information delivery method is implemented, and details are not described herein.

The machine-readable storage medium 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the machine-readable storage medium 120 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memories of the systems and methods described herein are intended to comprise, without being limited to, these and any other suitable memory of a publishing node. In some examples, the machine-readable storage medium 120 may further include memory located remotely from the processor 130, which may be connected to the server 100 over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor 130 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 130. The processor 130 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.

The server 100 can perform information interaction with other devices (e.g., the information receiving terminal 200) through the communication interface 110. Communication interface 110 may be a circuit, bus, transceiver, or any other device that may be used to exchange information. Processor 130 may send and receive information using communication interface 110.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

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

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

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

It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to encompass such modifications and variations.

Claims

1. An information delivery method is applied to a server which is in communication connection with at least one information receiving terminal, and the method comprises the following steps:

delivering the matched target policy information to an information receiving terminal of each corresponding enterprise respectively;

the step of carrying out enterprise portrait analysis on the big data of each enterprise in the big data pool to obtain portrait analysis results of different enterprises comprises the following steps:

2. The information delivery method according to claim 1, wherein the step of performing enterprise image analysis on the fusion image feature information of the enterprise to obtain an image analysis result of the enterprise comprises:

determining second to-be-determined splitting characteristic information corresponding to second corresponding last splitting characteristic information in the second splitting characteristic information; the second corresponding last splitting characteristic information is the corresponding last splitting characteristic information corresponding to the previous operation range characteristic information of the enterprise with the fused image;

3. The information delivery method according to claim 1, wherein the step of matching the portrait analysis result of each enterprise with policy information in a policy information pool to obtain target policy information to be delivered to each enterprise comprises:

4. The information delivery method according to claim 3, wherein the step of performing matching control operation on each unit policy information in the initial policy information according to a policy information control model configured for the enterprise in advance to generate a plurality of pending target policy information having set semantic policy condition paragraphs and different sources comprises:

5. The information delivery method according to claim 3, wherein the step of obtaining target policy information to be delivered to each enterprise according to the time-series hotspot policy information of each piece of the target policy information comprises:

for each piece of node policy information, when the probability distribution map of the second delivery probability hotspot map is larger than or smaller than the corresponding first delivery probability hotspot map, determining the difference value between the probability distribution map of the first delivery probability hotspot map and the probability distribution map of the second delivery probability hotspot map as a delivery probability hotspot comparison value corresponding to the node policy information, and generating a corresponding delivery probability hotspot comparison map according to the piece of node policy information and the delivery probability hotspot comparison value corresponding to the piece of node policy information;

6. The information delivery method according to any one of claims 1 to 5, characterized in that the method further comprises:

7. An information delivery device, applied to a server, wherein the server is in communication connection with at least one information receiving terminal, the device comprises:

the delivery module is used for respectively delivering the matched target policy information to the information receiving terminal of each corresponding enterprise;

the portrait analysis module is used for carrying out enterprise portrait analysis on the big data of each enterprise in the big data pool in the following modes to obtain portrait analysis results of different enterprises:

8. A server, comprising a processor, a machine-readable storage medium, and a network interface, the machine-readable storage medium, the network interface, and the processor being connected via a bus system, the network interface being configured to communicatively connect to at least one information receiving terminal, the machine-readable storage medium being configured to store a program, instructions, or code, and the processor being configured to execute the program, instructions, or code in the machine-readable storage medium to perform the information delivery method of any one of claims 1-6.

9. A readable storage medium having stored therein machine executable instructions which when executed perform the method of information delivery of any one of claims 1-6.