CN108628861B - Method and device for pushing information - Google Patents
Method and device for pushing information Download PDFInfo
- Publication number
- CN108628861B CN108628861B CN201710152537.3A CN201710152537A CN108628861B CN 108628861 B CN108628861 B CN 108628861B CN 201710152537 A CN201710152537 A CN 201710152537A CN 108628861 B CN108628861 B CN 108628861B
- Authority
- CN
- China
- Prior art keywords
- keyword
- information
- associated information
- piece
- attribute information
- 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.)
- Active
Links
Images
Abstract
The application discloses a method and a device for pushing information. One embodiment of the method comprises: for each keyword in the keyword set, acquiring at least one piece of associated information of the keyword; for each piece of associated information in at least one piece of associated information of each keyword, importing the associated information into a determined model trained in advance for the keyword to be matched, and obtaining attribute information of the associated information, wherein the attribute information comprises a result keyword and feature information of an entity indicated by the result keyword, and the determined model trained in advance for the keyword is used for representing a corresponding relation between the associated information of the keyword and the attribute information; determining importance information related to the keyword set based on the obtained attribute information; and pushing the importance information. The implementation improves the effectiveness of importance information push.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to the field of internet technologies, and in particular, to a method and an apparatus for pushing information.
Background
Information push, also called "network broadcast", is a technology for reducing information overload by pushing information required by users on the internet through a certain technical standard or protocol. The information push technology can reduce the time spent by the user in searching on the network by actively pushing information to the user.
However, in the existing information pushing technology, the information pushed to the user often only considers factors obviously related to the content of the pushed information, for example, in asset configuration information pushing, factors such as the asset value, the historical profitability and the like of related asset categories (such as stock market, bond market, gold market, crude oil market and cargo-based market) are generally considered, and potential factors (such as forecast information made by a financial website on future trends of various asset categories) influencing the information pushing result are considered less. Therefore, the information push technology has the problems of insufficient utilization of network information related data and low validity of push information.
Disclosure of Invention
The present application aims to propose an improved method and apparatus for pushing information to solve the technical problems mentioned in the background section above.
In a first aspect, an embodiment of the present application provides a method for pushing information, where the method includes: for each keyword in the keyword set, acquiring at least one piece of associated information of the keyword; for each piece of associated information in at least one piece of associated information of each keyword, importing the associated information into a determined model trained in advance for the keyword to be matched, and obtaining attribute information of the associated information, wherein the attribute information comprises a result keyword and feature information of an entity indicated by the result keyword, and the determined model trained in advance for the keyword is used for representing a corresponding relation between the associated information of the keyword and the attribute information; determining importance information related to the keyword set based on the obtained attribute information; and pushing the importance information.
In some embodiments, after obtaining at least one piece of association information of each keyword in the keyword set, the method further includes: for each keyword in the keyword set, for each associated information in the obtained at least one piece of associated information of the keyword, executing the following operations: extracting abstract information of the associated information; deleting the piece of associated information from at least one piece of associated information of the keyword; and determining the extracted summary information as the associated information of the keyword.
In some embodiments, the method further comprises the step of training a deterministic model, the step of training a deterministic model comprising: and aiming at each keyword in the keyword set, training to obtain a determined model aiming at the keyword by utilizing a machine learning method based on the history associated information of the manually marked keyword and the result keyword and the characteristic information corresponding to the history associated information.
In some embodiments, the feature information of the entity indicated by the result keyword includes prediction information of a future rate of return of the entity indicated by the result keyword; and the determining importance information related to the keyword set based on the obtained attribute information includes: acquiring asset market value data and historical profitability data of an entity indicated by each keyword in the keyword set; and determining importance information related to the keyword set based on the acquired asset market value data, the historical yield data and the acquired attribute information.
In some embodiments, the determining importance information related to the keyword set based on the obtained property market value data, the historical profitability data and the obtained attribute information includes: obtaining a target yield; and determining importance information related to the keyword set corresponding to the target profitability based on the acquired property market value data, the historical profitability data and the acquired attribute information.
In a second aspect, an embodiment of the present application provides an apparatus for pushing information, where the apparatus includes: the acquisition unit is configured to acquire at least one piece of associated information of each keyword in the keyword set; the matching unit is configured to import each piece of associated information into a pre-trained determined model for each keyword for matching to obtain attribute information of the associated information, wherein the attribute information comprises a result keyword and feature information of an entity indicated by the result keyword, and the pre-trained determined model for the keyword is used for representing a corresponding relationship between the associated information and the attribute information of the keyword; a determining unit configured to determine importance information related to the keyword set based on the obtained attribute information; and the pushing unit is configured to push the importance information.
In some embodiments, the above apparatus further comprises: the abstract information extraction unit is configured to execute the following operations for each keyword in the keyword set for each associated information in the acquired at least one piece of associated information of the keyword: extracting abstract information of the associated information; deleting the piece of associated information from at least one piece of associated information of the keyword; and determining the extracted summary information as the associated information of the keyword.
In some embodiments, the above apparatus further comprises: and the training unit is configured to train and obtain a determined model for each keyword in the keyword set by utilizing a machine learning method based on the manually marked historical associated information of the keyword and the result keyword and the characteristic information corresponding to the historical associated information.
In some embodiments, the feature information of the entity indicated by the result keyword includes prediction information of a future rate of return of the entity indicated by the result keyword; and the determining unit includes: the acquisition module is configured to acquire asset market value data and historical profitability data of an entity indicated by each keyword in the keyword set; and the determining module is configured to determine importance information related to the keyword set based on the acquired asset market value data, the acquired historical rate of return data and the acquired attribute information.
In some embodiments, the determining module is further configured to: obtaining a target yield; and determining importance information related to the keyword set corresponding to the target profitability based on the acquired property market value data, the historical profitability data and the acquired attribute information.
In a third aspect, an embodiment of the present application provides a server, where the server includes: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any implementation manner of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is implemented, when executed by a processor, to implement the method described in any implementation manner of the first aspect.
According to the method and the device for pushing the information, at least one piece of associated information of each keyword in a keyword set is obtained, the associated information is imported into a determination model trained in advance for the keyword for matching for each piece of associated information in the associated information of each keyword, attribute information of the associated information is obtained, importance information related to the keyword set is determined based on the obtained attribute information, and finally the importance information is pushed. Therefore, the associated information of the keywords in the keyword set is effectively utilized, and the significance information pushing effectiveness is improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2a is a flow diagram of one embodiment of a method for pushing information, according to the present application;
FIG. 2b is an exploded flow chart of step 203 of the flow chart of FIG. 2 a;
3a-3c are schematic diagrams of different importance information generated in a method for pushing information according to the present application, respectively;
FIG. 4 is a flow diagram of yet another embodiment of a method for pushing information according to the present application;
FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for pushing information according to the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the present method for pushing information or apparatus for pushing information may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various client applications, such as an information push application, a browser application, a financing application, a search application, a shopping application, a map application, a social platform application, a mailbox client, an instant messaging tool, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices supporting applications installed thereon, such as information push type applications, browser applications, financial type applications, and the like, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server that provides various services, such as a background server that supports information push type applications, browser applications, financial type applications, and the like displayed on the terminal apparatuses 101, 102, 103. The background server may process the received data such as the association information, and feed back a processing result (e.g., importance information) to the terminal device.
It should be noted that the method for pushing information provided by the embodiment of the present application is generally performed by the server 105, and accordingly, the apparatus for pushing information is generally disposed in the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to fig. 2a, a flow 200 of one embodiment of a method for pushing information according to the present application is shown. The method for pushing the information comprises the following steps:
In this embodiment, for each keyword in the keyword set, an electronic device (for example, a server shown in fig. 1) on which the method for pushing information operates may obtain at least one piece of associated information of the keyword from other electronic devices in communication connection with the electronic device locally or remotely.
Here, the keywords in the keyword set may be words indicating entities. The entity refers to things that exist objectively and can be distinguished from each other, and the entity may be a specific person, thing, object, or an abstract concept or connection. The entity can be both a tangible entity, e.g., an entity can be a building, a road, an item, a river, various organisms, and an intangible entity, e.g., an entity can be various institutions, organizations, and capital markets, such as a stock market, a gold market, a grocery market, a crude market, a bond market, and the like, as examples. For example, the keyword "stock" or "stock market" may be used to indicate a stock market, and the keyword "gold" or "gold market" may be used to indicate a gold market.
In this embodiment, the keyword set may be specified or selected according to a keyword known in advance, or may be generated according to data related to information to be pushed. For example, if the method of this embodiment is applied to asset configuration of a financing application, and the information to be pushed is the allocation proportion of investment funds among multiple asset classes, the electronic device may obtain the asset class names of the multiple asset classes in advance, and use the asset class names as keywords. At this time, the electronic device may group the asset class names into a keyword set. Or the electronic equipment can also receive at least one asset class name selected by the user in the financing application installed on the terminal from the terminal to form a keyword set. This is not limited in this application.
In the present embodiment, the associated information of the keyword may be various information associated with the entity indicated by the keyword. As an example, the associated information of the keyword may be information indicating a future trend of the entity indicated by the keyword. For example, the associated information of the keyword "stock" may be various information associated with the stock market, wherein the various information associated with the stock market may be an article about the future trend of the stock market from a financial website, a future trend article about the stock market from a personal microblog issued by a financial analyst, or the like.
Optionally, in order to ensure timeliness of the associated information, the associated information acquired by the electronic device may be associated information of which the release time is within a preset time period. As an example, the preset time period may be within one week of time before the current time.
Optionally, the electronic device may obtain association information of each keyword in the keyword set from a preset address. Wherein the preset address includes but is not limited to at least one of the following: presetting a website address, a preset email address, a preset server address and preset database connection information.
In this embodiment, based on the at least one piece of associated information of each keyword obtained in step 201, for each piece of associated information in the at least one piece of associated information of each keyword, the electronic device (for example, the server shown in fig. 1) may import the piece of associated information into a predetermined model trained in advance for the keyword, and perform matching, so as to obtain attribute information of the piece of associated information. The attribute information may include a result keyword and feature information of an entity indicated by the result keyword. The determination model trained in advance for the keyword is used for representing the corresponding relationship between the associated information and the attribute information of the keyword. Here, the result keyword of the piece of attribute information of the associated information may include the keyword and/or a keyword that is in the above-described keyword set and is different from the keyword.
Here, since the entities indicated by different keywords in the keyword set are different, and the associated information of each entity also has a great difference when expressing the same feature information, in order to improve the matching efficiency of matching between the associated information and the attribute information, each keyword in the keyword set corresponds to a corresponding determination model.
Here, the feature information of the entity indicated by the result keyword may be various feature information of the above-described entity.
In some optional implementations of the embodiment, the feature information of the entity indicated by the result keyword may include future trend information of the entity, including a future rate of return change direction and a future rate of return change value. The future rate of return change direction is used to indicate that the future rate of return is increasing, decreasing, or constant. For example, a future rate of return increase may be indicated by a 1, a future rate of return decrease may be indicated by a-1, and a future rate of return may be unchanged by a 0. The future rate of return change value is used to indicate a particular value of future rate of return increase or decrease.
For example, the characteristic information of the futures market indicated by the result keyword "futures market" may be future trend information of the futures market. The characteristic information of the gold market indicated by the result keyword "gold market" may be future tendency information of the gold market.
In some optional implementations of this embodiment, the attribute information of the association information may further include credibility information indicating a trustworthiness degree of the association information. For example, each piece of related information may include source information of the piece of related information, and if the source information of the piece of related information shows that the piece of related information originates from a certain known financial website or a certain known financial expert, the reliability of the piece of related information is higher, whereas the reliability of the piece of related information is lower. By way of example, for a keyword set { "stock", "bond", "crude oil", "gold", "good base" }, an article "stock market future rate of return will rise by 1 point in a certain well-known finance website, while gold will continue to present the situation" is a piece of associated information about the keyword "stock", the piece of associated information is imported into a certain model corresponding to the keyword "stock", and the obtained attribute information is as follows: the future rate of return change direction information in the feature information corresponding to the result keyword "stock" is rising, the future rate of return change value is 1%, the future rate of return change direction information in the feature information corresponding to the result keyword "gold" is unchanged, and the reliability information of the piece of associated information is 0.8. An article "crude oil market will decline at least 2 points in the future" from a common user is a piece of associated information about the keyword "crude oil", and the associated information is imported into a determination model corresponding to the keyword "crude oil", and the obtained attribute information is as follows: the future rate of return change direction information in the characteristic information corresponding to the result keyword 'crude oil' is descending, the future rate of return change value is 2%, and the reliability information of the piece of associated information is 0.2.
In this embodiment, the electronic device on which the method for pushing information operates may determine importance information related to the keyword set based on the respective attribute information obtained in step 202.
In some optional implementation manners of this embodiment, the electronic device may perform statistics on feature information of an entity indicated by each result keyword in each obtained attribute information, and generate importance information related to the keyword set according to a statistical result. When the feature information includes future trend information of the entity indicated by the result keyword, for each keyword in the keyword set, the ratio of the future rate of return change direction in the same attribute information as the keyword in each obtained attribute information being ascending, descending and invariable in the attribute information as the number of pieces of attribute information as the same as the result keyword in each obtained attribute information may be counted, and each piece of ratio information obtained by the counting is used as the importance information related to the keyword set. As an example, fig. 3a shows a result after counting feature information in attribute information of at least one piece of associated information of each keyword in the keyword set { "stock", "bond", "crude oil", "gold" }. As shown in fig. 3a, the attribute information of the related information of "stock", "bond", "crude oil" and "gold" shows the ratio of the future rate of return change in the rising, constant and falling directions, respectively.
In some optional implementation manners of this embodiment, the electronic device may further classify, according to a statistical result generated in the optional implementation manner, each keyword in the keyword set into a preset category, and use the keyword classified into different categories as importance information related to the keyword set. By way of example, FIG. 3b shows the separation of the keyword set { "stocks", "bonds", "crude oils", "gold" } into two categories according to the statistics given in FIG. 3 a: the method comprises a high proportion category and a low proportion category, wherein the high proportion category comprises { "bonds" } and the low proportion category comprises { "stocks", "crude oil", "gold" }.
In some optional implementations of this embodiment, the feature information of the entity indicated by the result keyword may include prediction information of a future profitability of the entity indicated by the result keyword, and thus, step 203 may further include sub-step 2031 and sub-step 2032 shown in fig. 2 b:
As an example, asset market value data and historical rate of return data for the entity indicated by each keyword in the set of keywords may be obtained from various financial-type official websites or forums.
What is obtained in sub-step 2031 is historical profitability data and market value data about the entity indicated by each keyword in the set of keywords, which is equivalent to prior information about the profitability of the entity indicated by each keyword. Each attribute information obtained in step 202 is obtained from at least one piece of associated information about each keyword in the keyword set, and if the feature information of the entity indicated by the result keyword in the obtained attribute information may include prediction information of future profitability of the entity indicated by the result keyword, and the obtained attribute information is equivalent to posterior information (or called prediction information) of the profitability of the entity indicated by each keyword, the electronic device may determine importance information related to the keyword set based on the prior information and the posterior information by using a bayesian analysis method (e.g., a Black-Litterman model analysis method).
Alternatively, sub-step 2032 may be performed as follows:
first, a target profitability is obtained.
The target rate of return here may be a user-specified target rate of return received from the terminal device. Alternatively, one of the preset target rate of return sets may be selected as the target rate of return.
And then, determining importance information related to the keyword set corresponding to the target profitability based on the acquired property market value data, the historical profitability data and the acquired attribute information.
As an example, a specific implementation method for determining importance information related to the keyword set corresponding to achieving the target profitability based on the obtained property market data, the historical profitability data and the obtained attribute information by using a Black-Litterman model analysis method is provided below, and specifically includes the following sub-steps 20321 to 20329:
sub-step 20321, generating a covariance matrix of expected profitability of the entity indicated by each keyword in the keyword set according to the obtained historical profitability data.
Here, the covariance matrix is a matrix of N rows and N columns, N being the number of keywords in the keyword set, and N being a positive integer.
Here, the market equilibrium weight vector is an N-dimensional vector.
And a substep 20324 of forming a related information set from the obtained at least one piece of related information of each keyword in the keyword set.
Here, the mapping matrix is a matrix having K rows and N columns, K is the number of pieces of associated information in the associated information set, and K is a positive integer.
Here, the reliability matrix is a diagonal matrix of K rows and K columns.
Sub-step 20327, generating a predicted rate of return vector from the predicted information of the future rate of return of the entity indicated by the result keyword in the attribute information of each piece of associated information in the associated information set.
Here, the prediction yield vector is a K-dimensional vector.
Two ways of calculating the future expected rate of return vector are given here:
first, a future expected rate of return vector may be calculated using equation (1) as follows:
E[R]＝[(τΣ)-1+PTΩ-1P]-1[(τΣ)-1Π+PTΩ-1Q]formula (1)
Wherein:
ER is the calculated N-dimensional future expected yield vector, N is the above-mentioned keyword
The number of keywords in the set, N being a positive integer;
tau is a specific gravity constant of a posterior viewpoint relative to a prior viewpoint, and tau takes a value between 0 and 1;
Σ is the covariance matrix of N rows and N columns obtained in substep 20321;
p is the mapping matrix of K rows and N columns obtained in substep 20325, and K is the above relationship
The number of associated information in the associated information set, wherein K is a positive integer;
Ω is a diagonal matrix-reliability matrix of K rows and K columns obtained in substep 20326;
q is the K-dimensional predicted rate of return vector obtained in substep 20327;
II is an N-dimensional implicit equilibrium yield vector calculated according to the following formula (2);
Π＝δΣweqformula (2)
weqThe N-dimensional market equilibrium weight vector obtained in substep 20323;
δ is a preset risk avoidance coefficient.
Second, the future expected rate of return vector may also be calculated using equation (3) as follows:
the meaning of each parameter is the same as that of the corresponding parameter in formula (1), and is not described herein again.
The formula for calculating the future expected yield variance vector is given below:
σ2＝Σ+[(τΣ)-1Π+PTΩ-1P]formula (4)
Wherein σ2Calculating a resulting future expected yield variance vector;
the meanings of the other parameters are the same as those of the corresponding parameters in the formula (1), and are not described herein again.
First, the objective function is set as follows:
then, the limiting conditions are set:
allowing to sell:
or
Do not allow to sell:
wherein:
rpfor combined investment profitability;
i is a positive integer between 1 and N;
riis E [ R ]]The value of the ith dimension corresponds to the future expected yield of the entity indicated by the ith keyword in the keyword set;
xithe allocation proportion of the entity indicated by the ith keyword in the keyword set is calculated;
xjthe distribution proportion of the entity indicated by the jth keyword in the keyword set is obtained;
σ2(rp) Investment variance for portfolio (also called, total risk for portfolio);
Cov(ri-rj) Is the covariance between the future expected rate of return of the entity indicated by the ith keyword in the two sets of keywords and the future expected rate of return of the entity indicated by the jth keyword in the set of keywords.
Finally, x is solved under the above constraintsiMake the portfolio investment variance σ2(rp) And obtaining the importance information related to the keyword set at the minimum. As will be appreciated by those skilled in the art, x can be found by a Lagrangian functioni。
As an example, fig. 3c shows that the above set of keywords is the set of asset class names { "stocks", "bonds", "crude", "gold", "barter" }, and the target earnings obtained is 23%. The user-defined asset allocation ratio is, for example, as shown by an icon 301 in fig. 3c, according to the user-defined asset allocation ratio, the expected profitability of the user is calculated to be 15%, and the risk prediction is 22%. The recommended asset allocation ratio obtained according to the target rate of return of 23% is, for example, as shown by an icon 302 in fig. 3c, according to the recommended asset allocation ratio, the expected rate of return of the recommended asset allocation ratio is calculated to be 23%, the risk prediction is 20%, and it is seen that the expected rate of return is higher and the risk prediction is lower.
And step 204, pushing the importance information.
In this embodiment, the electronic device may push the importance information determined in step 203 to the terminal device, and the terminal device displays the importance information.
In some optional implementation manners of this embodiment, the method for pushing information may further include a step of training a determination model, where the step of training the determination model includes:
and aiming at each keyword in the keyword set, training to obtain a determined model aiming at the keyword by utilizing a machine learning method based on the history associated information of the manually marked keyword and the result keyword and the characteristic information corresponding to the history associated information. Here, the machine learning method may be various machine learning methods suitable for natural language processing, for example, an artificial neural network or the like.
The method provided by the embodiment of the application obtains at least one piece of associated information of each keyword in the keyword set, introduces the associated information into a determination model trained in advance for the keyword for each piece of associated information of each keyword, matches the associated information to obtain attribute information of the associated information, determines importance information related to the keyword set based on each obtained attribute information, and finally pushes the importance information. Therefore, the associated information of the keywords in the keyword set is effectively utilized, and the significance information pushing effectiveness is improved.
With further reference to fig. 4, a flow 400 of yet another embodiment of a method for pushing information is shown. The flow 400 of the method for pushing information comprises the following steps:
In this embodiment, the specific operation of step 401 is substantially the same as the operation of step 201 in the embodiment shown in fig. 2a, and is not described herein again.
Since not all the content in the associated information of the keyword is useful information for subsequent import determination models, there may be some redundant information that makes it inefficient to import the determination models for matching. Therefore, in order to improve the efficiency of model matching, the electronic device may extract summary information of the associated information.
Optionally, the electronic device may preset a corresponding summary keyword set for each keyword in the keyword set. In this way, for each piece of associated information in at least one piece of associated information of the keyword, a paragraph or a sentence, which includes the summary keyword corresponding to the keyword, in the piece of associated information may be extracted as summary information of the piece of associated information. For example, the abstract keyword corresponding to the keyword "stock" may be "stop", "diving", "cow city", "bear city", and the abstract keyword corresponding to the keyword "gold" may be "gold price", "withdraw", "go", "sword finger", "fall", "dollar", "ounce".
In this embodiment, the specific operation of step 403 is substantially the same as the operation of step 202 in the embodiment shown in fig. 2a, and is not described herein again.
In this embodiment, the specific operation of step 404 is substantially the same as the operation of step 203 in the embodiment shown in fig. 2a, and is not described herein again.
In this embodiment, the specific operation of step 405 is substantially the same as the operation of step 204 in the embodiment shown in fig. 2a, and is not described herein again.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2a, the flow 400 of the method for pushing information in the present embodiment has more steps of extracting summary information from the associated information of the keywords in the keyword set. Therefore, the scheme described in the embodiment can filter out redundant information in the associated information, thereby realizing more effective pushing of the importance information.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for pushing information, which corresponds to the method embodiment shown in fig. 2a, and which is particularly applicable to various electronic devices.
As shown in fig. 5, the apparatus 500 for pushing information of the present embodiment includes: an acquisition unit 501, a matching unit 502, a determination unit 503, and a pushing unit 504. The acquiring unit 501 is configured to acquire, for each keyword in the keyword set, at least one piece of associated information of the keyword; a matching unit 502 configured to, for each piece of associated information in at least one piece of associated information of each keyword, import the piece of associated information into a predetermined model pre-trained for the keyword to perform matching, and obtain attribute information of the piece of associated information, where the attribute information includes a result keyword and feature information of an entity indicated by the result keyword, and the predetermined model pre-trained for the keyword is used to represent a corresponding relationship between the associated information of the keyword and the attribute information; a determining unit 503 configured to determine importance information related to the keyword set based on the obtained attribute information; a pushing unit 504 configured to push the importance information.
In this embodiment, specific processes of the obtaining unit 501, the matching unit 502, the determining unit 503, and the pushing unit 504 of the apparatus 500 for pushing information and technical effects brought by the specific processes can refer to the related descriptions of step 201, step 202, step 203, and step 204 in the corresponding embodiment of fig. 2a, which are not described herein again.
In some optional implementations of the present embodiment, the apparatus 500 for pushing information may further include: the summary information extraction unit 502' is configured to, for each keyword in the keyword set, perform the following operations for each piece of acquired at least one piece of associated information of the keyword: extracting abstract information of the associated information; deleting the piece of associated information from at least one piece of associated information of the keyword; and determining the extracted summary information as the associated information of the keyword. The detailed processing of the summary information extraction unit 502' and the technical effects thereof can refer to the related description of step 402 in the corresponding embodiment of fig. 4, which is not repeated herein.
In some optional implementation manners of this embodiment, the apparatus 500 for pushing information may further include a training unit 505 configured to, for each keyword in the keyword set, train, by using a machine learning method, to obtain a determination model for the keyword based on the history associated information of the manually labeled keyword and the result keyword and feature information corresponding to the history associated information. The detailed processing of the training unit 505 and the technical effects thereof can refer to the related description of step 204 in the corresponding embodiment of fig. 2a, and are not repeated herein.
In some optional implementations of this embodiment, the feature information of the entity indicated by the result keyword may include prediction information of a future rate of return of the entity indicated by the result keyword; and the determining unit 503 may include: an obtaining module 5031 configured to obtain asset market value data and historical profitability data of an entity indicated by each keyword in the keyword set; a determining module 5032 configured to determine importance information related to the keyword set based on the obtained property market value data, the historical profitability data and the obtained attribute information. The specific processing of the obtaining module 5031 and the determining module 5032 and the technical effects thereof can refer to the related descriptions of the sub-step 2031 and the sub-step 2032 in the corresponding embodiment of fig. 2b, which are not repeated herein.
In some optional implementations of this embodiment, the determining module 5032 may be further configured to: obtaining a target yield; and determining importance information related to the keyword set corresponding to the target profitability based on the acquired property market value data, the historical profitability data and the acquired attribute information. The detailed processing of the determining module 5032 and the technical effect thereof can refer to the related description of the sub-step 2032 in the corresponding embodiment of fig. 2b, and are not repeated herein.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 606 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An Input/Output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: a storage portion 606 including a hard disk and the like; and a communication section 607 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 607 performs communication processing via a network such as the internet. Drivers 608 are also connected to the I/O interface 605 as needed. A removable medium 609 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 608 as necessary, so that a computer program read out therefrom is mounted into the storage section 606 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 607 and/or installed from the removable medium 609. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a matching unit, a determination unit, and a push unit. Here, the names of these units do not constitute a limitation to the unit itself in some cases, and for example, the acquiring unit may also be described as a "unit that acquires association information".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: for each keyword in the keyword set, acquiring at least one piece of associated information of the keyword; for each piece of associated information in at least one piece of associated information of each keyword, importing the associated information into a determined model trained in advance for the keyword to be matched, and obtaining attribute information of the associated information, wherein the attribute information comprises a result keyword and feature information of an entity indicated by the result keyword, and the determined model trained in advance for the keyword is used for representing a corresponding relation between the associated information of the keyword and the attribute information; determining importance information related to the keyword set based on the obtained attribute information; and pushing the importance information.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (12)
1. A method for pushing information, the method comprising:
for each keyword in the keyword set, acquiring at least one piece of associated information of the keyword;
for each piece of associated information in at least one piece of associated information of each keyword, importing the associated information into a determined model pre-trained for the keyword to be matched, and obtaining attribute information of the associated information, wherein the attribute information comprises a result keyword and feature information of an entity indicated by the result keyword, and the determined model pre-trained for the keyword is used for representing a corresponding relation between the associated information of the keyword and the attribute information;
determining importance information related to the keyword set based on the obtained attribute information;
and pushing the importance information.
2. The method according to claim 1, wherein after obtaining at least one piece of association information of each keyword in the keyword set, the method further comprises:
for each keyword in the keyword set, for each associated information in the obtained at least one piece of associated information of the keyword, executing the following operations: extracting abstract information of the associated information; deleting the piece of associated information from at least one piece of associated information of the keyword; and determining the extracted summary information as the associated information of the keyword.
3. The method of claim 2, further comprising the step of training a deterministic model, said step of training a deterministic model comprising:
and aiming at each keyword in the keyword set, training to obtain a determined model aiming at the keyword by utilizing a machine learning method based on the history associated information of the manually marked keyword and the result keyword and the characteristic information corresponding to the history associated information.
4. The method of claim 3, wherein the feature information of the entity indicated by the result keyword includes prediction information of future profitability of the entity indicated by the result keyword; and
determining importance information related to the keyword set based on the obtained attribute information includes:
acquiring asset market value data and historical profitability data of an entity indicated by each keyword in the keyword set;
and determining importance information related to the keyword set based on the acquired asset market value data, the historical yield data and the acquired attribute information.
5. The method according to claim 4, wherein the determining importance information related to the keyword set based on the obtained property market value data, historical profitability data and the obtained attribute information comprises:
obtaining a target yield;
and determining importance information related to the keyword set corresponding to the target profitability based on the acquired property market value data, the historical profitability data and the acquired attribute information.
6. An apparatus for pushing information, the apparatus comprising:
the acquisition unit is configured to acquire at least one piece of associated information of each keyword in the keyword set;
the matching unit is configured to import each piece of associated information into a pre-trained determined model for each keyword for matching to obtain attribute information of the associated information, wherein the attribute information comprises a result keyword and feature information of an entity indicated by the result keyword, and the pre-trained determined model for the keyword is used for representing a corresponding relationship between the associated information and the attribute information of the keyword;
a determining unit configured to determine importance information related to the keyword set based on the obtained respective attribute information;
and the pushing unit is configured to push the importance information.
7. The apparatus of claim 6, further comprising:
the abstract information extraction unit is configured to execute the following operations for each keyword in the keyword set in terms of each acquired at least one piece of associated information of the keyword: extracting abstract information of the associated information; deleting the piece of associated information from at least one piece of associated information of the keyword; and determining the extracted summary information as the associated information of the keyword.
8. The apparatus of claim 7, further comprising:
and the training unit is configured to train to obtain a determined model for each keyword in the keyword set by utilizing a machine learning method based on the manually labeled historical associated information of the keyword and the result keyword and the characteristic information corresponding to the historical associated information.
9. The apparatus according to claim 8, wherein the feature information of the entity indicated by the result keyword includes prediction information of future profitability of the entity indicated by the result keyword; and
the determination unit includes:
the acquisition module is configured to acquire asset market value data and historical profitability data of an entity indicated by each keyword in the keyword set;
and the determining module is configured to determine importance information related to the keyword set based on the acquired asset market value data, the acquired historical rate of return data and the acquired attribute information.
10. The apparatus of claim 9, wherein the determining module is further configured to:
obtaining a target yield;
and determining importance information related to the keyword set corresponding to the target profitability based on the acquired property market value data, the historical profitability data and the acquired attribute information.
11. A server, comprising:
one or more processors;
a storage device for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-5.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710152537.3A CN108628861B (en) | 2017-03-15 | 2017-03-15 | Method and device for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710152537.3A CN108628861B (en) | 2017-03-15 | 2017-03-15 | Method and device for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108628861A CN108628861A (en) | 2018-10-09 |
| CN108628861B true CN108628861B (en) | 2022-03-04 |
Family
ID=63686276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710152537.3A Active CN108628861B (en) | 2017-03-15 | 2017-03-15 | Method and device for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108628861B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133908A (en) * | 2014-08-07 | 2014-11-05 | 北京奇虎科技有限公司 | Method, server, client and system for displaying or generating discussion box on page |
| CN104537065A (en) * | 2014-12-29 | 2015-04-22 | 北京奇虎科技有限公司 | Search result pushing method and system |
| CN104598556A (en) * | 2015-01-04 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Search method and search device |
| CN104899285A (en) * | 2015-06-04 | 2015-09-09 | 百度在线网络技术（北京）有限公司 | Display method and apparatus for search result |
| CN105630876A (en) * | 2015-12-17 | 2016-06-01 | 百度在线网络技术（北京）有限公司 | Cross-application information obtaining method and device |
| CN106095895A (en) * | 2016-06-07 | 2016-11-09 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8086508B2 (en) * | 2000-07-24 | 2011-12-27 | Cashedge, Inc. | Method and apparatus for delegating authority |
| US7244230B2 (en) * | 2002-11-08 | 2007-07-17 | Siemens Medical Solutions Usa, Inc. | Computer aided diagnostic assistance for medical imaging |
| CN103473317A (en) * | 2013-09-12 | 2013-12-25 | 百度在线网络技术（北京）有限公司 | Method and equipment for extracting keywords |
| CN105488163B (en) * | 2015-11-30 | 2019-02-01 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| CN105488161A (en) * | 2015-11-30 | 2016-04-13 | 百度在线网络技术（北京）有限公司 | Information pushing method and apparatus |
-
2017
- 2017-03-15 CN CN201710152537.3A patent/CN108628861B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133908A (en) * | 2014-08-07 | 2014-11-05 | 北京奇虎科技有限公司 | Method, server, client and system for displaying or generating discussion box on page |
| CN104537065A (en) * | 2014-12-29 | 2015-04-22 | 北京奇虎科技有限公司 | Search result pushing method and system |
| CN104598556A (en) * | 2015-01-04 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Search method and search device |
| CN104899285A (en) * | 2015-06-04 | 2015-09-09 | 百度在线网络技术（北京）有限公司 | Display method and apparatus for search result |
| CN105630876A (en) * | 2015-12-17 | 2016-06-01 | 百度在线网络技术（北京）有限公司 | Cross-application information obtaining method and device |
| CN106095895A (en) * | 2016-06-07 | 2016-11-09 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108628861A (en) | 2018-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11443305B2 (en) | Context augmentation for processing data from multiple sources | |
| CN109522483B (en) | Method and device for pushing information | |
| CN107679217B (en) | Associated content extraction method and device based on data mining | |
| CN109492772B (en) | Method and device for generating information | |
| CN110390408B (en) | Transaction object prediction method and device | |
| CN110084658B (en) | Method and device for matching articles | |
| CN107944032B (en) | Method and apparatus for generating information | |
| CN111680165B (en) | Information matching method and device, readable storage medium and electronic equipment | |
| CN112204610A (en) | Neural network based electronic content | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| CN111612581A (en) | Method, device and equipment for recommending articles and storage medium | |
| CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN113190702A (en) | Method and apparatus for generating information | |
| CN111538909A (en) | Information recommendation method and device | |
| CN110197317B (en) | Target user determination method and device, electronic equipment and storage medium | |
| CN113392920A (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN110992127A (en) | Article recommendation method and device | |
| CN108959289B (en) | Website category acquisition method and device | |
| CN110889716A (en) | Method and device for identifying potential registered user | |
| CN111768218A (en) | Method and device for processing user interaction information | |
| CN108628861B (en) | Method and device for pushing information | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN110766488A (en) | Method and device for automatically determining theme scene | |
| CN115048487A (en) | Artificial intelligence-based public opinion analysis method, device, computer equipment and medium |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20181009 Assignee: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd. Assignor: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. Contract record no.: X2020990000192 Denomination of invention: Method and device for pushing information License type: Common License Record date: 20200417 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |