CN108897853A - The method and apparatus for generating pushed information - Google Patents

The method and apparatus for generating pushed information Download PDF

Info

Publication number
CN108897853A
CN108897853A CN201810694913.6A CN201810694913A CN108897853A CN 108897853 A CN108897853 A CN 108897853A CN 201810694913 A CN201810694913 A CN 201810694913A CN 108897853 A CN108897853 A CN 108897853A
Authority
CN
China
Prior art keywords
target entity
preset
attribute
information
attribute value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810694913.6A
Other languages
Chinese (zh)
Inventor
曾启飞
陈思姣
罗雨
刁世亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201810694913.6A priority Critical patent/CN108897853A/en
Publication of CN108897853A publication Critical patent/CN108897853A/en
Pending legal-status Critical Current

Links

Abstract

The embodiment of the present application discloses the method and apparatus for generating pushed information.One specific embodiment of this method includes:The delta data of the attribute value of first preset attribute of multiple entities based on acquired preset kind within a preset period of time, determines at least one target entity;For the one of target entity determined, obtain in preset time period with the associated related information of the target entity;Determine the degree of association of the delta data of the attribute value of each related information corresponding with the target entity and the first preset attribute of the target entity;Target push information is determined from each related information corresponding with the target entity based on the degree of association.To be effectively utilized the relevance between the delta data of the attribute value of the first preset attribute of related information and target entity, determined pushed information can be improved to the specific aim of target entity.

Description

The method and apparatus for generating pushed information
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field, more particularly to generate and push away It delivers letters the method and apparatus of breath.
Background technique
With the continuous development of information technology, people obtain the mode of information also gradually from information transition is actively searched for connect Receive the information from various media push.Such information acquiring pattern, it is possible to reduce user searches for the time used in information.
Above-mentioned pushed information may include the information of various aspects, for example, financial information, Financial Information, stock category information, Educational information, news information etc..
Summary of the invention
The embodiment of the present application proposes a kind of method and apparatus for generating pushed information.
In a first aspect, the embodiment of the present application provides a kind of method for generating pushed information, this method includes:Based on being obtained The delta data of the attribute value of first preset attribute of multiple entities of the preset kind taken within a preset period of time, determine to A few target entity;For the one of target entity determined, obtains in preset time period and closed with the target entity The related information of connection;Determine the attribute of each related information corresponding with the target entity and the first preset attribute of the target entity The degree of association of the delta data of value;Determine that target is pushed from each related information corresponding with the target entity based on the degree of association Information.
In some embodiments, determine that the first of each related information corresponding with the target entity and the target entity presets The degree of association of the delta data of the attribute value of attribute, including:The attribute value of determining and the target entity the first preset attribute Variation tendency indicated by delta data, variation tendency include increasing trend and decline trend;Each item and the target entity are closed The related information and variation tendency of connection are input to correlation analysis model trained in advance, determine that each and the target are real The degree of association of body associated related information and variation tendency.
In some embodiments, determine that the first of each related information corresponding with the target entity and the target entity presets The degree of association of the delta data of the attribute value of attribute, including:The attribute value of determining and the target entity the first preset attribute Variation tendency indicated by delta data, variation tendency include increasing trend and decline trend;Each item and the target entity are closed The related information of connection is input to disaggregated model trained in advance, determines each and the associated related information institute of the target entity The information type of category;Information type includes positive information type and negative sense information type;Positive information type and increasing trend phase It closes, negative sense information type is related to decline trend;For any bar and the associated related information of the target entity, closed based on this Connection information belongs to the probability of the information type belonging to it and variation tendency determines the pass of this related information and delta data Connection degree.
In some embodiments, this method further includes:For the one of target entity determined, the target is obtained The attribute value of multiple second preset attributes of entity;Default template is called, and according to the first preset attribute of the target entity Attribute value, multiple second preset attributes attribute value generation the article of the target entity is described.
In some embodiments, the attribute value of multiple second preset attributes of each target entity is obtained, including:For Either objective entity obtains the attribute value of multiple second preset attributes in the knowledge mapping pre-established.
Second aspect, the embodiment of the present application provide a kind of device for generating pushed information, which includes:First determines Unit is configured to the attribute value of the first preset attribute of multiple entities based on acquired preset kind in preset time period Interior delta data determines at least one target entity;Acquiring unit is configured to one of mesh for being determined Mark entity, obtain preset time period in the associated related information of the target entity;Second determination unit, be configured to determine with The corresponding each related information of the target entity is associated with the delta data of the attribute value of the first preset attribute of the target entity Degree;Generation unit is configured to determine that target is pushed from each related information corresponding with the target entity based on the degree of association Information.
In some embodiments, the second determination unit is further configured to:Determining first with the target entity is preset Variation tendency indicated by the delta data of the attribute value of attribute, variation tendency include increasing trend and decline trend;By each item It is input to correlation analysis model trained in advance with the associated related information of the target entity and variation tendency, is determined every One with the degree of association of the target entity associated related information and variation tendency.
In some embodiments, the second determination unit is further configured to:Determining first with the target entity is preset Variation tendency indicated by the delta data of the attribute value of attribute, variation tendency include increasing trend and decline trend;By each item It is input to disaggregated model trained in advance with the associated related information of the target entity, determines that each and the target entity are closed Information type belonging to the related information of connection;Information type includes positive information type and negative sense information type;Positive info class Type is related to increasing trend, and negative sense information type is related to decline trend;For any bar and the associated association of the target entity Information, the probability and variation tendency that the information type belonging to it is belonged to based on this related information determine this related information With the degree of association of delta data.
In some embodiments, generation unit is further configured to:For the one of target entity determined, Obtain the attribute value of multiple second preset attributes of the target entity;Default template is called, and according to the first of the target entity The attribute value of preset attribute, multiple second preset attributes attribute value generation the article of the target entity is described.
In some embodiments, generation unit is further configured to:For either objective entity, know what is pre-established Know the attribute value that multiple second preset attributes are obtained in map.
The third aspect, the embodiment of the present application provide a kind of server, which includes:One or more processors; Storage device is stored thereon with one or more programs, when said one or multiple programs are by said one or multiple processors When execution, so that said one or multiple processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, In, the method as described in implementation any in first aspect is realized when which is executed by processor.
The method and apparatus provided by the embodiments of the present application for generating pushed information, by being primarily based on acquired default class The delta data of the attribute value of first preset attribute of multiple entities of type within a preset period of time, determines at least one target Entity, then for the one of target entity determined, obtain in preset time period with the associated pass of the target entity Join information;Then the attribute value of each related information corresponding with the target entity and the first preset attribute of the target entity is determined Delta data the degree of association, finally determine that target is pushed away from each related information corresponding with the target entity based on the degree of association It delivers letters breath.To be effectively utilized between the delta data of the attribute value of the first preset attribute of related information and target entity Determined pushed information can be improved to the specific aim of target entity in relevance.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other Feature, objects and advantages will become more apparent upon:
Fig. 1 is that the method for the generation pushed information of one embodiment of the application can be applied to exemplary system therein Architecture diagram;
Fig. 2 is the flow chart according to one embodiment of the method for the generation pushed information of the application;
Fig. 3 is the schematic diagram according to an application scenarios of the method for the generation pushed information of the application;
Fig. 4 is the flow chart according to another embodiment of the method for the generation pushed information of the application;
Fig. 5 is the structural schematic diagram according to one embodiment of the device of the generation pushed information of the application;
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the server of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is that the method for the generation pushed information of one embodiment of the application can be applied to exemplary system therein Architecture diagram 100.
As shown in Figure 1, may include terminal device 101,102,103, network 104 and server in system architecture Figure 100 105.Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 It may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
Terminal device 101,102,103 is interacted by network 104 with server 105, to receive or send message etc..Terminal Various client applications, such as web browser applications, the application of shopping class, search can be installed in equipment 101,102,103 Class application, instant messaging tools etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard When part, it can be the various electronic equipments with display screen and supported web page browsing, including but not limited to smart phone, plate Computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic Image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, move State image expert's compression standard audio level 4) player, pocket computer on knee and desktop computer etc..When terminal is set Standby 101,102,103 when being software, may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or Software module (such as providing the software of Distributed Services or software module), also may be implemented into single software or software mould Block.It is not specifically limited herein.
Server 105 can be to provide the server of various services, for example, obtain preset kind multiple entities first The attribute value of preset attribute;And target entity is determined according to the delta data of the attribute value of the first preset attribute, then according to mesh The incidence relation for marking the delta data of the attribute value of the related information of entity and the first preset attribute of target entity is determined to push away It delivers letters breath.Pushed information can be sent to terminal device by above-mentioned server, for user's browsing.
It should be noted that the method for generating pushed information provided by the embodiment of the present application is generally held by server 105 Row, correspondingly, the device for generating pushed information is generally positioned in server 105.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software To be implemented as multiple softwares or software module (such as providing the software of Distributed Services or software module), also may be implemented At single software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the processes according to one embodiment of the method for the generation pushed information of the application 200.The method of the generation pushed information, includes the following steps:
Step 201, the attribute value of the first preset attribute of multiple entities based on acquired preset kind is when default Between delta data in section, determine at least one target entity.
In the present embodiment, the executing subject (such as server shown in FIG. 1) for generating the method for pushed information can be first First pass through wired connection mode or radio connection obtain multiple entities of preset kind in real time from internet first The attribute value of preset attribute.The attribute value of the first preset attribute of multiple entities of acquired preset kind is then based on pre- If the delta data in the period determines at least one target entity.
Here the entity of preset kind, which can be, belongs to pre-set any type of entity, it may for example comprise but not It is limited to the entity of stock type, the entity of car category.
Above-mentioned first preset attribute for example can be attribute that is pre-set, will changing with time fluctuation, Such as price, sales volume etc..
In application scenes, above-mentioned executing subject can be from website relevant to the preset kind (such as stock class Portal website) in obtain in real time the preset kind multiple entities the first preset attribute attribute value.
Above-mentioned executing subject can determine the attribute value of the first preset attribute of multiple entities of the preset kind pre- If the delta data in the period, the then change according to the attribute value of the first preset attribute of multiple entities within a preset period of time Change data and determines at least one target entity.
In application scenes, the attribute of the first preset attribute of the above-mentioned available above-mentioned multiple entities of executing subject The amplitude of variation of value within a preset period of time;At least one entity that amplitude of variation is greater than preset threshold is determined as target reality Body.
In other application scenarios, the attribute of the first preset attribute of the available above-mentioned multiple entities of aforementioned body The amplitude of variation of value within a preset period of time;Multiple entities are ranked up according to the descending sequence of amplitude of variation;It will row At least one entity that serial number is less than preset threshold is determined as target entity.
Step 202, it for the one of target entity determined, obtains in preset time period and is closed with the target entity The related information of connection.
In this application, above-mentioned related information can be various information, for example, educational information, news information, financial information, Financial Information etc..It is illustrated by taking news information as an example below.
In the present embodiment, based on target entity obtained in step 201, above-mentioned executing subject (such as clothes shown in FIG. 1 Business device) the multiple news informations issued within a preset period of time can be searched from internet, then pass through various analysis means It is determined from above-mentioned multiple news informations and the associated news information of the target entity.
In application scenes, if the target entity is the entity of stock type, above-mentioned news information for example be can be Various financial and economic news, such as:Change in policy, INDUSTRY OVERVIEW, monetary credit policy etc..
In application scenes, above-mentioned executing subject can be issued in above-mentioned preset time period from searching in internet , news information comprising the target entity title, as with the associated news information of the target entity.
Above-mentioned executing subject can be from the portal website for issuing news information relevant to the entity of above-mentioned preset kind Search news information issue in above-mentioned preset time period, comprising the target entity title.Here preset time period can To be the period being arbitrarily designated, such as 1 day, 2 days etc., it can not be repeated herein according to specifically being set.
In addition, above-mentioned executing subject can also analyze industry corresponding to the above-mentioned target entity.It then will be from internet Middle acquisition issue within a preset period of time, news information comprising industry corresponding to above-mentioned target entity, as with this The associated news information of target entity.When analyzing industry corresponding to the target entity, can carry out in accordance with the following steps:It is first First determine whether preset kind belonging to the target entity belongs to marketable securities.If the target entity is not belonging to marketable securities, The preset kind as belonging to target entity determines the corresponding industry of the target entity.If the target entity belongs to marketable securities, Determine that industry belonging to the company master commodity to be offered for issuing the target entity or service is the corresponding industry of the target entity. For example, can determine that the company of distribution target entity AA is BB when the preset kind of target entity AA is stock.Then It is steel by analysis company BB master commodity to be offered, it is determined that the corresponding industry of target entity AA is steel industry.Again For example, when the target entity is the automobile of a model, can the preset kind according to belonging to the target entity " automobile " it is true Industry corresponding to the fixed target entity is automobile industry.
For example, the entity (for example, a certain branch stock) of a stock type, above-mentioned execution master have been determined in step 201 Body can determine news information issue within a preset period of time, comprising the branch stock name from stock portal website. Alternatively, above-mentioned executing subject can determine that industry belonging to the branch issuance of stock company is internet industry.Above-mentioned execution Main body can determine that news information issue within a preset period of time, comprising above-mentioned internet industry is determined from internet For with the associated news information of target entity.
In other application scenarios, above-mentioned executing subject can also be by issuing of finding within a preset period of time A plurality of news information and target entity title are input in related information analysis model trained in advance, can be from above-mentioned a plurality of new It hears in information and determines and the associated news information of target entity.Here related information analysis model can be various types of Text-processing model, such as:Topic model, supporting vector machine model, model-naive Bayesian, k nearest neighbor model, decision tree mould Type, neural network model etc..
It should be noted that above-mentioned topic model, supporting vector machine model, model-naive Bayesian, k nearest neighbor model, certainly Plan tree-model, neural network model are the well-known techniques studied and applied extensively at present, are not repeated herein.
It is understood that using before related information analysis model, needing using being added to a plurality of of mark News information is trained the related information analysis model after being trained to initial association information analysis model.Here, each Mark added by news information can be the mark of the title of entity associated by this news information.Alternatively, each Mark added by news information can be the mark of film name corresponding to entity associated by this news information.
So, the available and associated a plurality of news information of target entity.
Step 203, each related information corresponding with the target entity and the first preset attribute of the target entity are determined The degree of association of the delta data of attribute value.
It is obtained in step 202 with after the associated a plurality of news information of the target entity, above-mentioned executing subject can lead to Cross the first preset attribute that various analysis means determine above-mentioned each news information corresponding with the target entity and the target entity Attribute value delta data within a preset period of time the degree of association.
In general, the information that people issue the cognition of things from medium.That is, news information is to people to thing The cognition of object has important influence.
In the present embodiment, above-mentioned to influence people to the target entity with the associated news information of the target entity Cognition.Influence of any news information to people to the degree of awareness of the target entity can reflect the first of the target entity In the variation of the attribute value of preset attribute within a preset period of time.First preset attribute of the different news informations to the target entity Attribute value variation within a preset period of time influence degree it is also different.
In the present embodiment, above-mentioned executing subject can according to one in the associated news information of the target entity Appearance, the source of news information, number of words of news information etc. belong to determine that this news information is preset to the first of the target entity The influence degree of the delta data of the attribute value of property.
In application scenes, if a certain news information is the positive coverage to the target entity, while the target When the attribute value of first preset attribute of entity increases in above-mentioned preset time period, then this news information is to the target entity The first preset attribute attribute value delta data influence degree be positive value.If a certain news information is the target entity Positive coverage, while when the attribute value of the first preset attribute of the target entity reduces in above-mentioned preset time period, then should News information is negative value to the influence degree of the delta data of the attribute value of the first preset attribute of the target entity.It is similar Ground, if news item information is the negative report to the target entity, while the attribute value of the first preset attribute of target entity When reduction, then this news is positive to the influence degree of the delta data of the attribute value of the first preset attribute of the target entity Value.If news item information is the negative report to the target entity, while the attribute value of the first preset attribute of target entity When growth, then this news information is to the influence degree of the delta data of the attribute value of the first preset attribute of the target entity Negative value.For example, reporting the said firm in news item information interior in a couple of days if the target entity is the stock of a company Registered capital will be increased.This news information is the positive news information of the said firm's stock, while the stock valence of the said firm's stock Lattice increase, then this news information is positive value to the influence degree of the growth of the price of the stock.
Further, it is also possible to the layout position according to the source of this news information, this news information in news hole And/or the number of words of this news information determines this news information to the attribute value of the first preset attribute of the target entity The influence degree of delta data.
For example, this news information for the news item information of identical content, from professional financial and economic news website To the influence degree of the delta data of the attribute value of the first preset attribute of the target entity, greater than on source and entertainment sites Influence degree of this news information to the delta data of the attribute value of the first preset attribute of the target entity.
For example, for 10,000 word and the associated news information of the target entity, to the first of the target entity The influence degree of the delta data of the attribute value of preset attribute, greater than 100 words and the target entity associated news information pair The influence degree of the delta data of the attribute value of first preset attribute of the target entity.
In another example in professional financial and economic news website with the associated top news information of the target entity to the target entity The first preset attribute attribute value delta data influence degree, greater than in professional financial and economic news website with target reality Influence degree of the associated non-top news information of body to the delta data of the attribute value of the first preset attribute of the target entity.
Above-mentioned each news information to the attribute value of the first preset attribute of the target entity within a preset period of time The influence degree of variation, it is believed that be the variation number of the attribute value of the news information and the first preset attribute of the target entity According to the degree of association.So, available each news information and the attribute value of the first preset attribute of the target entity The degree of association of delta data.
In some optional implementations of the present embodiment, the determination of above-mentioned steps 203 is corresponding with the target entity The degree of association of the delta data of the attribute value of first preset attribute of each news information and the target entity, may include following son Step:
Change indicated by the delta data of the attribute value of first preset attribute of sub-step 2031, determination and the target entity Change trend.
Above-mentioned executing subject can determine in above-mentioned preset time period, the attribute of the first preset attribute of the target entity Variation tendency indicated by the delta data of value.Above-mentioned variation tendency may include increasing trend and decline trend.
Above-mentioned increasing trend refers to the first preset attribute in the target entity in the end time of above-mentioned preset time period The attribute value at place is greater than the attribute value at the start time of above-mentioned preset time period.In the start time of above-mentioned preset time period Between end time, the attribute value of the first preset attribute of the target entity can not be monotonic increase.For example, if the mesh When mark entity is a stock, it is higher than in the closing price that the increasing trend of the stock of a certain day can be this day branch stock The opening price of this day branch stock.But between opening the set and closing in the day, the price of the branch stock can not be dullness and pass Increase.
Above-mentioned decline trend refers to the first preset attribute in the target entity in the end time of above-mentioned preset time period The attribute value at place is less than the attribute value at the start time of above-mentioned preset time period.In the start time of above-mentioned preset time period Between end time, the attribute value of the first preset attribute of the target entity can not be monotone decreasing.For example, if the mesh When mark entity is a stock, it is lower than in the closing price that the decline trend of the stock of a certain day can be this day branch stock The opening price of this day branch stock.But between opening the set and closing in the day, the price of the branch stock can not be dullness and pass Subtract.
Each item and the associated related information of the target entity and variation tendency are input to preparatory training by sub-step 2032 Correlation analysis model, determine the degree of association of each Yu the target entity associated related information and variation tendency.
Above-mentioned executing subject can input each item and the associated news information of the target entity and above-mentioned variation tendency Into correlation analysis model trained in advance, so that it is determined that the degree of association of each candidate pushed information and variation tendency out.
Above-mentioned correlation analysis model can be the analysis model of various processing texts, such as:Topic model, supporting vector Machine model, model-naive Bayesian, k nearest neighbor model, decision-tree model, neural network model etc..
Before stating correlation analysis model in use, a plurality of news for being added to mark is can be used in above-mentioned executing subject Information is trained initial association degree analysis model, the correlation analysis model after being trained.It is above-mentioned initial for training The mark of each news information of correlation analysis model, such as can be with this news information to increasing trend and successively decrease The degree of association of trend.
So, above-mentioned executing subject can be by presetting the attribute value of default first attribute of the target entity Variation tendency and each news information in period are input to correlation analysis model trained in advance, can be quick To the degree of association of each and the target entity associated news information and the target entity.To be conducive to accelerate to determine push The speed of information.
It should be noted that related information analysis model described in above-mentioned correlation analysis model and above-mentioned steps 202 It can be the same model, be also possible to different models.
In other optional implementations of the present embodiment, the determination of above-mentioned steps 203 is corresponding with the target entity Each news information and the target entity the first preset attribute attribute value delta data the degree of association, can also include such as Lower sub-step:
Change indicated by the delta data of the attribute value of first preset attribute of sub-step 2033, determination and the target entity Change trend.
Above-mentioned executing subject can determine the attribute of the first preset attribute of the target entity in above-mentioned preset time period Variation tendency indicated by the delta data of value.Above-mentioned variation tendency may include increasing trend and decline trend.
Each item and the associated related information of the target entity are input to disaggregated model trained in advance by sub-step 2034, Determine information type belonging to each and the associated related information of the target entity.
Each item and the associated news information of the target entity can be input to classification trained in advance by above-mentioned executing subject Model obtains information type belonging to each and the associated news information of the target entity.
Above- mentioned information type includes positive information type and negative sense information type.Wherein, positive information type usually with this The increasing trend of the attribute value of first preset attribute of target entity is related;Negative sense information type usually with the target entity The decline trend of the attribute value of one preset attribute is related.Such as:If news item information dissemination in financial and economic news website one Operating profit of the corresponding company of branch stock in the first half of the year records high, this news information will cause the stock of the branch stock The variation tendency of admission fee lattice within a preset period of time is increasing trend, then this news information and the stock price are in preset time Increasing trend in section is related.In another example:If one stock of news item information dissemination in financial and economic news website is corresponding Operating profit of the company in the first half of the year creates the new lowest record in history, this news information will cause the stock price of the branch stock default Variation tendency in period is decline trend, then this news information and the stock price within a preset period of time successively decrease Gesture is related.
Above-mentioned disaggregated model for example can be the analysis model of various processing texts, such as:Topic model, support vector machines Model, model-naive Bayesian, k nearest neighbor model, decision-tree model, neural network model etc..
Before stating disaggregated model in use, a plurality of news information pair for being added to mark is can be used in above-mentioned executing subject Preliminary classification model is trained, the disaggregated model after being trained.It is above-mentioned to be used to train each of preliminary classification model new The mark for hearing information for example can be information type corresponding with this news information.
So, available each and the new affiliated information type of the associated news of the target entity.
Sub-step 2035 belongs to each and the associated related information of the target entity based on this related information The probability and variation tendency of information type belonging to it determine the degree of association of this related information and delta data.
Specifically, for each and the associated news information of the target entity, determine that this is new in sub-step 2034 Hear belonging to information after information type, determine information type belonging to this news information whether first with the target entity The variation tendency of the attribute value of preset attribute is related.If related, the degree of association is the positive degree of association, and otherwise, the degree of association is negative sense The degree of association.Then the determine the probability for belonging to the information type belonging to it in conjunction with this news information goes out this information and above-mentioned change Change the degree of association of data.
For example, the probability that news item information belongs to positive information type is 0.7, the probability for belonging to negative sense information type is 0.3.Then this news information belongs to positive information type, probability 0.7.If the attribute of the first preset attribute of the target entity The variation tendency of value is increasing trend, this news information and the variation of the attribute value of the first preset attribute of the target entity become Gesture is that the degree of association of increasing trend is 0.7.That is, the category of the first preset attribute of this news information and the target entity Property value delta data within a preset period of time the degree of association be 0.7.
In another example in the above example, it is assumed that the attribute value of the first preset attribute of the target entity is in preset time period Interior variation tendency is decline trend, then the attribute value of the first preset attribute of this news information and the target entity is default The degree of association of delta data in period is -0.7.
Step 204, target push information is determined from each related information corresponding with the target entity based on the degree of association.
First based on each news information corresponding with the target entity and the target entity that obtain in step 203 is pre- If the degree of association of the delta data of the attribute value of attribute, can be determined from each news information corresponding with the target entity Target push information.
Such as can be from a plurality of news information corresponding with the target entity, it will each news corresponding with the target entity Information and the maximum news item information of the degree of association of the delta data of the attribute value of the first preset attribute of the target entity are true It is set to target push information.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for the generation pushed information of the present embodiment Figure 30 0.In the application scenarios of Fig. 3, server 301 obtains the category of the first preset attribute of multiple entities of preset kind first The delta data 302 of property value within a preset period of time.Later, multiple entities of the server 301 based on acquired preset kind The first preset attribute attribute value delta data 302 within a preset period of time, determine at least one target entity 303. Then, server 301 is for one of target entity for being determined, in available preset time period with the target entity Associated related information 304.Then, above-mentioned server 301 can determine each related information corresponding with the target entity and be somebody's turn to do The degree of association 305 of the delta data of the attribute value of first preset attribute of target entity, then, server 301 can be based on upper It states the degree of association and determines target push information 306 from each related information corresponding with the target entity.Finally, server 301 Above-mentioned target push information 307 is sent to terminal device 308.Specific aim of the target push information determined to target entity It is relatively strong.
The method provided by the above embodiment of the application is by being primarily based on multiple entities of acquired preset kind The delta data of the attribute value of first preset attribute within a preset period of time, determines at least one target entity, then for The one of target entity determined, obtain preset time period in the associated related information of the target entity;Then really The delta data of the attribute value of first preset attribute of fixed each related information corresponding with the target entity and the target entity The degree of association finally determines target push information from each related information corresponding with the target entity based on the degree of association.To The relevance being effectively utilized between the delta data of the attribute value of the first preset attribute of related information and target entity, can be with Determined pushed information is improved to the specific aim of target entity.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for generating pushed information.The life At the process 400 of the method for pushed information, include the following steps:
Step 401, the attribute value of the first preset attribute of multiple entities based on acquired preset kind is when default Between delta data in section, determine at least one target entity.
Step 401 in the present embodiment is identical as the step 201 in embodiment illustrated in fig. 2, does not repeat herein.
Step 402, it for the one of target entity determined, obtains in preset time period and is closed with the target entity The related information of connection.
Step 402 in the present embodiment is identical as the step 202 in embodiment illustrated in fig. 2, does not repeat herein.
Step 403, each related information corresponding with the target entity and the first preset attribute of the target entity are determined The degree of association of the delta data of attribute value.
Step 403 in the present embodiment is identical as the step 203 in embodiment illustrated in fig. 2, does not repeat herein.
Step 404, target push information is determined from each related information corresponding with the target entity based on the degree of association.
Step 404 in the present embodiment is identical as the step 204 in embodiment illustrated in fig. 2, does not repeat herein.
Step 405, the attribute value of multiple second preset attributes of the target entity is obtained.
In the present embodiment, above-mentioned executing subject can also obtain the multiple second pre- of the target entity by all means If the attribute value of attribute.
In the present embodiment, above-mentioned first preset attribute and the second preset attribute can be the pre-set target respectively Entity attributes.
Above-mentioned first preset attribute can be the attribute that will be changed with the variation of time, such as price, sales volume Deng.
Above-mentioned second preset attribute and the first preset attribute can be in the features of different angle reflection target entity.
In application scenes, if the target entity is a stock, above-mentioned first preset attribute for example can be stock Admission fee lattice, above-mentioned second preset attribute can be the turnover rate of the same day branch stock, the transaction value of the same day branch stock, the branch stock Fund outflow/inflow of the exchange hand of ticket, the market value of the branch stock, the special mention agency ratings of the branch stock, the affiliated industry of branch stock One of state, fund-raising gap data for company corresponding to the branch stock of scoring of the branch stock etc..
When the target entity is the automobile of a known models, above-mentioned first preset attribute can be the car model Sales volume, and above-mentioned second preset attribute can be the correlation performance parameters etc. of the car model.
Above-mentioned executing subject can be to obtain the attribute values of above-mentioned multiple second preset attributes of the target entity in internet. Further, above-mentioned executing subject can obtain the upper of the target entity in the professional website about above-mentioned preset kind entity State the attribute value of multiple second preset attributes.
In some optional implementations of the present embodiment, multiple the second of above-mentioned each target entity of acquisition are default The attribute value of attribute, including:For either objective entity, multiple second preset attributes are obtained in the knowledge mapping pre-established Attribute value.
In these optional implementations, above-mentioned executing subject can creation should in local or in remote server The knowledge mapping of preset kind entity.It may include multiple entities in the knowledge mapping of the preset kind entity.Above-mentioned knowledge It can reflect the incidence relation between the entity of multiple preset kinds in map.In addition, can also include in above-mentioned knowledge mapping The multiple attributes and the corresponding attribute value of each attribute of each entity.It is understood that working as corresponding to preset kind The first preset attribute, the second preset attribute attribute value with time change when, above-mentioned knowledge mapping needs real-time update.
In these optional implementations, due to obtaining the multiple of the target entity in the knowledge mapping pre-established The attribute value of second preset attribute, so as to reduce multiple second preset attributes for obtaining the target entity from internet Time used in attribute value, is conducive to improve the target is described according to the attribute value generation of the second preset attribute of the target entity The speed of the article of entity.
Step 406, default template is called, and according to the attribute value of the first preset attribute of the target entity, multiple second The attribute value generation of preset attribute describes the article of the target entity.
In the present embodiment, the template of various article's styles can be set in above-mentioned executing subject.When a text has been determined After chapter type, above-mentioned executing subject can call template corresponding with this article type.First in the target entity is pre- If the attribute value of the attribute value of attribute and multiple second preset attributes is put into the designated position in the default template, can be generated The article of the target entity is described.
It in the present embodiment, can also include by the of the target entity in the article generated for describing the target entity The change curve that delta data of the attribute value of one preset attribute in above-mentioned preset time period generates.It is real describing the target The change curve of the attribute value of the first preset attribute of the above-mentioned target entity within a preset period of time is added in the article of body, Can be used family intuitively observe the target entity the first preset attribute attribute value variation.Be conducive to user to article Understanding.Further, above-mentioned executing subject can also add at least one second preset attribute in above-mentioned change curve Attribute value.
It is generated using default template and describes the article of the target entity and can be further improved generation to describe the target real The speed of the article of body.
Figure 4, it is seen that compared with the corresponding embodiment of Fig. 2, the method for the generation pushed information in the present embodiment Process 400 highlight the attribute value for obtaining multiple second preset attributes of the target entity, and call default template, according to The attribute value generation of the attribute value of first preset attribute of the target entity and multiple second preset attributes describes target reality The step of article of body.The scheme of the present embodiment description also generates while generating pushed information and describes the target as a result, Entity article.So that increasing more information contents in pushed information generated, it is various to can satisfy user Demand.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides a kind of generation push to believe One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer For in various electronic equipments.
As shown in figure 5, the device 500 of the generation pushed information of the present embodiment includes:First determination unit 501 obtains list First 502, second determination unit 503 and generation unit 504.Wherein, the first determination unit 501, is configured to based on acquired The delta data of the attribute value of first preset attribute of multiple entities of preset kind within a preset period of time, determines at least one A target entity;Acquiring unit 502 is configured to one of target entity for being determined, obtains preset time period The interior and associated related information of the target entity;Second determination unit 503 is configured to determine corresponding with the target entity each The degree of association of the delta data of the attribute value of first preset attribute of related information and the target entity;Generation unit 504 is matched It is set to and target push information is determined from each related information corresponding with the target entity based on the degree of association.
In the present embodiment, the first determination unit 501, the acquiring unit 502, second of the device 500 of pushed information are generated The specific processing of determination unit 503 and generation unit 504 and its brought technical effect can refer to Fig. 2 corresponding embodiment respectively Middle step 201, step 202, the related description of step 203 and step 204, details are not described herein.
In some optional implementations of the present embodiment, the second determination unit 503 is further configured to:Determine with Variation tendency indicated by the delta data of the attribute value of first preset attribute of the target entity, variation tendency include being incremented by Gesture and decline trend;Each item is input to trained in advance be associated with the associated related information of the target entity and variation tendency Analysis model is spent, determines the degree of association of each Yu the target entity associated related information and variation tendency.
In some optional implementations of the present embodiment, the second determination unit 503 is further configured to:Determine with Variation tendency indicated by the delta data of the attribute value of first preset attribute of the target entity, variation tendency include being incremented by Gesture and decline trend;Each item and the associated related information of the target entity are input to disaggregated model trained in advance, determined Information type belonging to each and the associated related information of the target entity;Information type includes positive information type and negative sense Information type;Positive information type is related to increasing trend, and negative sense information type is related to decline trend;For any bar and it is somebody's turn to do The associated related information of target entity belongs to the probability and variation tendency of the information type belonging to it based on this related information Determine the degree of association of this related information and delta data.
In some optional implementations of the present embodiment, generation unit 504 is further configured to:For determining One of target entity out obtains the attribute value of multiple second preset attributes of the target entity;Default template is called, and Target reality is described according to the attribute value generation of the attribute value of the first preset attribute of the target entity, multiple second preset attributes The article of body.
In some optional implementations of the present embodiment, generation unit 504 is further configured to:For any mesh Entity is marked, the attribute value of multiple second preset attributes is obtained in the knowledge mapping pre-established.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the server for being suitable for being used to realize the embodiment of the present application Structural schematic diagram.Server shown in Fig. 6 is only an example, should not function and use scope band to the embodiment of the present application Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU, Central Processing Unit) 601, it can be according to the program being stored in read-only memory (ROM, Read Only Memory) 602 or from storage section 608 programs being loaded into random access storage device (RAM, Random Access Memory) 603 and execute various appropriate Movement and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.CPU 601,ROM 602 and RAM 603 is connected with each other by bus 604.Input/output (I/O, Input/Output) interface 605 is also connected to Bus 604.
I/O interface 605 is connected to lower component:Importation 606 including keyboard, mouse etc.;It is penetrated including such as cathode Spool (CRT, Cathode Ray Tube), liquid crystal display (LCD, Liquid Crystal Display) etc. and loudspeaker Deng output par, c 607;Storage section 608 including hard disk etc.;And including such as LAN (local area network, Local Area Network) the communications portion 609 of the network interface card of card, modem etc..Communications portion 609 is via such as internet Network executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to from the calculating read thereon Machine program is mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium On computer program, which includes the program code for method shown in execution flow chart.In such reality It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media 611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or Computer readable storage medium either the two any combination.Computer readable storage medium for example can be --- but Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination. The more specific example of computer readable storage medium can include but is not limited to:Electrical connection with one or more conducting wires, Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium Program code can transmit with any suitable medium, including but not limited to:Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang Any appropriate combination stated.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof Machine program code, programming language include object oriented program language-such as Java, Smalltalk, C++, also Including conventional procedural programming language-such as " C " language or similar programming language.Program code can be complete It executes, partly executed on the user computer on the user computer entirely, being executed as an independent software package, part Part executes on the remote computer or executes on a remote computer or server completely on the user computer.It is relating to And in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or extensively Domain net (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service Quotient is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard The mode of part is realized.Described unit also can be set in the processor, for example, can be described as:A kind of processor packet Include the first determination unit, acquiring unit, the second determination unit and generation unit.Wherein, the title of these units is in certain situation Under do not constitute restriction to the unit itself, for example, the first determination unit is also described as " based on acquired default The delta data of the attribute value of first preset attribute of multiple entities of type within a preset period of time, determines at least one mesh Mark the unit of entity ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be Included in device described in above-described embodiment;It is also possible to individualism, and without in the supplying device.Above-mentioned calculating Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should Device:The variation of the attribute value of first preset attribute of multiple entities based on acquired preset kind within a preset period of time Data determine at least one target entity;For the one of target entity determined, obtain in preset time period with The associated related information of the target entity;It determines the first of corresponding with the target entity each related information and the target entity in advance If the degree of association of the delta data of the attribute value of attribute;It is true from each related information corresponding with the target entity based on the degree of association Make target push information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein Can technical characteristic replaced mutually and the technical solution that is formed.

Claims (12)

1. a kind of method for generating pushed information, including:
The variation of the attribute value of first preset attribute of multiple entities based on acquired preset kind within a preset period of time Data determine at least one target entity;
For the one of target entity determined, obtains in preset time period and believe with the associated association of the target entity Breath;
Determine the variation of the attribute value of each related information corresponding with the target entity and the first preset attribute of the target entity The degree of association of data;
Target push information is determined from each related information corresponding with the target entity based on the degree of association.
2. according to the method described in claim 1, wherein, the determination each related information corresponding with the target entity and the mesh The degree of association of the delta data of the attribute value of the first preset attribute of entity is marked, including:
Variation tendency indicated by the determining delta data with the attribute value of the first preset attribute of the target entity, the variation Trend includes increasing trend and decline trend;
Each item and the associated related information of the target entity and the variation tendency are input to the degree of association trained in advance point Model is analysed, determines the degree of association of each Yu the target entity associated related information and the variation tendency.
3. according to the method described in claim 1, wherein, the determination each related information corresponding with the target entity and the mesh The degree of association of the delta data of the attribute value of the first preset attribute of entity is marked, including:
Variation tendency indicated by the determining delta data with the attribute value of the first preset attribute of the target entity, the variation Trend includes increasing trend and decline trend;
Each item and the associated related information of the target entity are input to disaggregated model trained in advance, each is determined and is somebody's turn to do Information type belonging to the associated related information of target entity;The information type includes positive information type and negative sense info class Type;The forward direction information type is related to the increasing trend, and the negative sense information type is related to the decline trend;
For any bar and the associated related information of the target entity, the information type belonging to it is belonged to based on this related information Probability and the variation tendency determine the degree of association of this related information Yu the delta data.
4. according to the method described in claim 1, wherein, the method also includes:
For the one of target entity determined, the attribute value of multiple second preset attributes of the target entity is obtained;
Default template is called, and according to the attribute value of the first preset attribute of the target entity, the category of multiple second preset attributes Property value generate describe the target entity article.
5. according to the method described in claim 4, wherein, multiple second preset attributes for obtaining each target entity Attribute value, including:
For either objective entity, the attribute value of multiple second preset attributes is obtained in the knowledge mapping pre-established.
6. a kind of device for generating pushed information, including:
First determination unit is configured to the attribute value of the first preset attribute of multiple entities based on acquired preset kind Delta data within a preset period of time determines at least one target entity;
Acquiring unit, is configured to one of target entity for being determined, obtain in preset time period with the target The related information of entity associated;
Second determination unit, be configured to determine each related information corresponding with the target entity and the target entity first are pre- If the degree of association of the delta data of the attribute value of attribute;
Generation unit is configured to determine target from each related information corresponding with the target entity based on the degree of association Pushed information.
7. device according to claim 6, wherein second determination unit is further configured to:
Variation tendency indicated by the determining delta data with the attribute value of the first preset attribute of the target entity, the variation Trend includes increasing trend and decline trend;
Each item and the associated related information of the target entity and the variation tendency are input to the degree of association trained in advance point Model is analysed, determines the degree of association of each Yu the target entity associated related information and the variation tendency.
8. device according to claim 6, wherein second determination unit is further configured to:
Variation tendency indicated by the determining delta data with the attribute value of the first preset attribute of the target entity, the variation Trend includes increasing trend and decline trend;
Each item and the associated related information of the target entity are input to disaggregated model trained in advance, each is determined and is somebody's turn to do Information type belonging to the associated related information of target entity;The information type includes positive information type and negative sense info class Type;The forward direction information type is related to the increasing trend, and the negative sense information type is related to the decline trend;
For any bar and the associated related information of the target entity, the information type belonging to it is belonged to based on this related information Probability and the variation tendency determine the degree of association of this related information Yu the delta data.
9. device according to claim 6, wherein the generation unit is further configured to:
For the one of target entity determined, the attribute value of multiple second preset attributes of the target entity is obtained;
Default template is called, and according to the attribute value of the first preset attribute of the target entity, the category of multiple second preset attributes Property value generate describe the target entity article.
10. device according to claim 9, wherein the generation unit is further configured to:For either objective reality Body obtains the attribute value of multiple second preset attributes in the knowledge mapping pre-established.
11. a kind of server, including:
One or more processors;
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor Such as method as claimed in any one of claims 1 to 5.
CN201810694913.6A 2018-06-29 2018-06-29 The method and apparatus for generating pushed information Pending CN108897853A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810694913.6A CN108897853A (en) 2018-06-29 2018-06-29 The method and apparatus for generating pushed information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810694913.6A CN108897853A (en) 2018-06-29 2018-06-29 The method and apparatus for generating pushed information

Publications (1)

Publication Number Publication Date
CN108897853A true CN108897853A (en) 2018-11-27

Family

ID=64346761

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810694913.6A Pending CN108897853A (en) 2018-06-29 2018-06-29 The method and apparatus for generating pushed information

Country Status (1)

Country Link
CN (1) CN108897853A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110309234A (en) * 2019-06-14 2019-10-08 广发证券股份有限公司 A kind of client of knowledge based map holds position method for early warning, device and storage medium
CN112399339A (en) * 2020-11-19 2021-02-23 杭州云深科技有限公司 Mobile device relevancy determination method based on wifi type, electronic device and medium
WO2021051587A1 (en) * 2019-09-17 2021-03-25 平安科技(深圳)有限公司 Search result sorting method and apparatus based on semantic recognition, electronic device, and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102571371A (en) * 2010-12-23 2012-07-11 腾讯科技(深圳)有限公司 Network information pushing method and system
US20140330837A1 (en) * 2013-04-17 2014-11-06 Tencent Technology (Shenzhen) Company Limited Method, apparatus and system for pushing micro-blogs
CN105868345A (en) * 2016-03-28 2016-08-17 北京麒麟合盛网络技术有限公司 Method and device for determining information

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102571371A (en) * 2010-12-23 2012-07-11 腾讯科技(深圳)有限公司 Network information pushing method and system
US20140330837A1 (en) * 2013-04-17 2014-11-06 Tencent Technology (Shenzhen) Company Limited Method, apparatus and system for pushing micro-blogs
CN105868345A (en) * 2016-03-28 2016-08-17 北京麒麟合盛网络技术有限公司 Method and device for determining information

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110309234A (en) * 2019-06-14 2019-10-08 广发证券股份有限公司 A kind of client of knowledge based map holds position method for early warning, device and storage medium
WO2021051587A1 (en) * 2019-09-17 2021-03-25 平安科技(深圳)有限公司 Search result sorting method and apparatus based on semantic recognition, electronic device, and storage medium
CN112399339A (en) * 2020-11-19 2021-02-23 杭州云深科技有限公司 Mobile device relevancy determination method based on wifi type, electronic device and medium

Similar Documents

Publication Publication Date Title
CN107908740A (en) Information output method and device
CN108897853A (en) The method and apparatus for generating pushed information
CN108932220A (en) article generation method and device
CN109783741A (en) Method and apparatus for pushed information
CN110134931A (en) Media title generation method, device, electronic equipment and readable medium
CN109213486A (en) Method and apparatus for generating customized visualization component
CN109785064A (en) A kind of mobile e-business recommended method and system based on Multi-source Information Fusion
CN108647239A (en) Talk with intension recognizing method and device, equipment and storage medium
CN109214501A (en) The method and apparatus of information for identification
CN108280200A (en) Method and apparatus for pushed information
CN109190123A (en) Method and apparatus for output information
CN109325121A (en) Method and apparatus for determining the keyword of text
CN110084658A (en) The matched method and apparatus of article
CN109710634A (en) For generating the method and device of information
CN109582825A (en) Method and apparatus for generating information
CN108573054A (en) Method and apparatus for pushed information
CN108933730A (en) Information-pushing method and device
CN108629011A (en) Method and apparatus for sending feedback information
CN108062423B (en) Information-pushing method and device
US11017773B2 (en) Voice-based time-sensitive task processing over a high generation cellular network
CN109299477A (en) Method and apparatus for generating text header
CN110263255A (en) Acquisition methods, system, server and the storage medium of customer attribute information
CN109584012A (en) Method and apparatus for generating article pushed information
CN108959087A (en) test method and device
CN110046254A (en) Method and apparatus for generating model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20181127

RJ01 Rejection of invention patent application after publication