CN112330455A - Method, device, equipment and storage medium for pushing information - Google Patents
Method, device, equipment and storage medium for pushing information Download PDFInfo
- Publication number
- CN112330455A CN112330455A CN202011329158.5A CN202011329158A CN112330455A CN 112330455 A CN112330455 A CN 112330455A CN 202011329158 A CN202011329158 A CN 202011329158A CN 112330455 A CN112330455 A CN 112330455A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- target
- determining
- text
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 40
- 230000015654 memory Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 10
- 238000013145 classification model Methods 0.000 claims description 9
- 230000010365 information processing Effects 0.000 claims description 9
- 230000008030 elimination Effects 0.000 claims 2
- 238000003379 elimination reaction Methods 0.000 claims 2
- 239000000047 product Substances 0.000 description 54
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 239000003795 chemical substances by application Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000002537 cosmetic Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 101100537629 Caenorhabditis elegans top-2 gene Proteins 0.000 description 1
- 241000393496 Electra Species 0.000 description 1
- 208000001613 Gambling Diseases 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 101150107801 Top2a gene Proteins 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for pushing information, and relates to the fields of data processing and knowledge graph. The specific implementation scheme is as follows: acquiring retrieval information of a target user; determining a user representation based on the search information; determining credit scores and target push information of target users based on the user figures; and pushing target push information to the target user based on the credit score. According to the implementation mode, the user portrait is determined according to daily retrieval information of the user, the user portrait serves as a reference feature when the product is recommended, and credit score of the user determined based on the user portrait is combined, so that accurate product recommendation for a target user can be achieved, learning cost and time cost of the user when the product is selected can be effectively reduced, and user experience is improved.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to the field of data processing and knowledge graph, and more particularly, to a method, an apparatus, a device, and a storage medium for pushing information.
Background
With the rapid development of the internet, the processing of massive information on the network has become an important direction of current research, and the internet has become the largest information supply station in the world, and the living, learning and working environments of human beings are continuously changed. How to dig out important information through the contents searched and browsed by the user also becomes a place of major concern of each large search company.
On the other hand, along with the economic development, the financial consciousness of people is greatly enhanced, and the quantity of financial products is also greatly increased in recent years. While excellent financial products are increased, defective products are also increased. The internet information amount is very large, and investors of financial products need to master certain financial knowledge and risk analysis capability to select financial products suitable for the investors. For this reason, investors of financial products have to spend a lot of time on investigation and research, increasing learning costs and time costs of the investors.
Disclosure of Invention
The present disclosure provides a method, apparatus, device and storage medium for pushing information.
According to an aspect of the present disclosure, there is provided a method for pushing information, including: acquiring retrieval information of a target user; determining a user representation based on the search information; determining credit scores and target push information of target users based on the user figures; and pushing target push information to the target user based on the credit score.
According to another aspect of the present disclosure, there is provided an apparatus for pushing information, comprising: an acquisition unit configured to acquire retrieval information of a target user; a user representation determining unit configured to determine a user representation based on the search information; an information processing unit configured to determine a credit score and target push information of a target user based on a user representation; and the pushing unit is configured to push target pushing information to the target user based on the credit score.
According to still another aspect of the present disclosure, there is provided an electronic device for pushing information, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for pushing information as described above.
According to yet another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for pushing information as described above.
According to the technology of the application, the technical problems that a large amount of time is consumed for investigation and research and the learning cost and the time cost are increased when an investor selects a financing product are solved, the user portrait is determined according to daily retrieval information of the user, the user portrait is used as a reference feature when the product is recommended, and the credit score of the user determined based on the user portrait is combined, so that accurate product recommendation aiming at a target user can be realized, the learning cost and the time cost of the user when the product is selected can be effectively reduced, and the user experience is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for pushing information, according to the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for pushing information according to the present application;
FIG. 4 is a flow diagram of 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 block diagram of an electronic device for implementing a method for pushing information according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
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. The terminal devices 101, 102, 103 may have installed thereon various applications APP or applets, such as financing APP/applet, housekeeping APP/applet, take-away APP/applet, shopping APP/applet, etc.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, car computers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules, or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background server that processes search information of target users acquired by the terminal apparatuses 101, 102, 103. The background server acquires retrieval information of a target user; determining a user representation based on the search information; determining credit scores and target push information of target users based on the user figures; and pushing target push information to the target user based on the credit score.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as a plurality of software or software modules, or as a single software or software module. And is not particularly limited herein.
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. Accordingly, means for pushing information is typically provided 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. 2, a flow 200 of one embodiment of a method for pushing information in accordance with the present application is shown. The method for pushing information of the embodiment comprises the following steps:
In this embodiment, an execution subject (for example, the server 105 in fig. 1) of the method for pushing information may acquire, by means of wired connection or wireless connection, the retrieval information input by the target user acquired by the terminal device. Specifically, the target user may be a user with a financing tendency, or a user with a requirement for a college entrance to find a recommendation after a college entrance is ended, or a user with a requirement for a month break. The retrieval information may be the historical daily retrieval content of the target user, or the current frequently retrieved content, for example, "fund", "shanghai and bathyscraper index", "356 recommended school", "gold medal month sao" and other information. The present application does not limit the type of the target user and the specific content of the search information. The present application does not specifically limit the retrieval time for retrieving information.
The execution body may determine the user representation based on the search information after obtaining the search information. Specifically, the executive may first classify the search information and then determine the user representation based on the classified search information. Specifically, the execution subject may determine, according to a preset correspondence between the information and the classification identifier, a classification identifier corresponding to each piece of information in the retrieval information; the executive may then determine a child user representation based on information belonging to the same category identifier; then, the execution subject may collect the sub-user images, and perform deduplication processing to obtain a final simplified user image.
The executive body, after determining the user representation, may determine a credit score and target push information for the target user based on the user representation. Specifically, the executing entity may determine a score according to a correspondence relationship with a preset score based on information for performing credit scoring preset in the user representation, for example, credit card overdue information, loan information, monthly consumption information, and the like, and may perform weighting calculation based on a preset weighting coefficient to obtain a final credit score.
The executing agent may determine tag information that appears most frequently in the user representation; and determining information of the related field based on the label information, and taking the information of the related field as target push information. The target push information may be information of a region related to the tag information of the user figure that matches the search information most and has the highest search frequency. For example, when the related information such as "fund", "Shanghai depth index", etc. appears most frequently in the history search information of the target user, the target push information may be information related to financing, for example, it may be a financing product such as "XX week engorgement".
And step 204, pushing target push information to the target user based on the credit score.
After determining the credit score of the target user, the executive body may push the target push information to the target user based on the credit score. Specifically, the executive body may perform ratio calculation on the credit score and the credit score threshold, and when the obtained ratio is greater than 1, the executive body may push a financial product such as "XX week filling" or target push information such as "XX month cash-in-law", "XX school", "XX mentor" to the target user.
With continued reference to fig. 3, a schematic illustration of one application scenario of the method for pushing information according to the present application is shown. In the application scenario of fig. 3, the server 304 acquires the retrieval information 301 of the target user acquired by the terminal device 302 through the network 303. The server 304 specifies the user image 305 based on the search information 301. The server 304 determines a credit score 306 and target push information 307 (which may be a target financial product, for example) for the target user based on the user imagery 305. The server 304 pushes targeted push information 307 (i.e., targeted financial products) to the targeted user 308 based on the credit score 306.
According to the embodiment, the user portrait is determined according to daily retrieval information of the user, the user portrait serves as a reference feature when the product is recommended, and the credit score of the user determined based on the user portrait is combined, so that accurate product recommendation for a target user can be achieved, the learning cost and the time cost of the user when the product is selected can be effectively reduced, and the user experience is improved.
With continued reference to fig. 4, a flow 400 of another embodiment of a method for pushing information in accordance with the present application is shown. As shown in fig. 4, the method for pushing information of this embodiment may include the following steps:
The principle of step 401 to step 402 is similar to that of step 201 to step 202, and is not described herein again.
In this embodiment, the search information includes image information and first text information.
For example, the image information may be a financial product screenshot entered by the target user in a search box of the terminal device. The first text information may be a text description of the financial product of interest input by the target user in the search box of the terminal device, and may be information such as "store alive", "store regularly", "interest rate 2% or more", for example.
Specifically, step 402 can be realized through steps 4021 to 4023:
In this embodiment, the pre-trained conversion model is used to represent the correspondence between the image information and the text information. After the execution main body obtains the retrieval information, the second text information corresponding to the image information can be determined according to the image information in the retrieval information and the pre-trained conversion model. Specifically, the executing subject may input the image information to a pre-trained conversion model, and output a text description corresponding to the image information as second text information corresponding to the image information. The second text message is used to describe the content of the image message, for example, if the user inputs a "XX week filling" picture into the pre-trained conversion model, the model outputs a word "XX week filling, interest rate 2.5%", and the word may be the second text message.
Specifically, the pre-trained conversion model may be a CGO (tasks with Guiding objects) model, which may change image contents into textual descriptions and maintain fluency of sentences, and generate a textual description starting from a target object in a captured picture and a description of other objects according to the target object based on an input picture. The CGO model mainly comprises an image encoder (CNN model), a target detection model and a sentence generation model (LSTM model). The image encoder is used for encoding an image, the target detection model is used for detecting a selected target object, and the sentence generation model (LSTM) is used for converting image characteristics into a sentence describing the image. The CGO model in the application is a pre-trained model, and can accurately convert the information of the picture into text information.
In this embodiment, after obtaining the first text information and the second text information, the execution subject may generate the text label based on the first text information, the second text information, the pre-trained text label extraction algorithm, and the pre-trained text label generation model. Specifically, the executing entity may perform extraction-type tag generation on the first text information and the second text information by using a pre-trained text tag extraction algorithm, such as an embedlank algorithm. Specifically, the EmbedRank algorithm may be divided into four parts, the first part is to extract candidate keywords by combining parts of speech of the text information, the second part is to represent the candidate keywords and the text information by using sentence embedding (content embedding), and the third part is to rank the candidate keywords by using similarity between the text information and the candidate keywords. And finally, screening the candidate keywords through a Maximum Marginal Relevance (MMR) model to form a text label set with relevance and diversity and outputting the text label set. The MMR algorithm has a leading effect in an extraction type text label generation algorithm.
In particular, the executive may utilize a pre-trained text label generation model, such as the TA-NKG (Topic-AwareNuyphraseGenerationModel) model, for generative label generation. The Model consists of two small models, the first being a topic Model (NTM) and the second being a generative Model (NKG). The topic model comprises an encoder and a decoder, data is mainly reconstructed, and the topic information of the first text information and the topic information of the second text information can be respectively obtained through the model. And respectively converting the theme information of the first text information and the second text information into vector forms, respectively inputting the vector forms into the generating models, and respectively outputting the generated label with the strongest relevance corresponding to the first text information and the generated label with the strongest relevance corresponding to the second text information. The basic model adopted by the generation model is a Seq2Seq model added with an attention mechanism, the basic model is input into topic information of the NTM model and key phrases directly extracted from the first text information and the second text information, and the generated text labels are the text labels with the strongest relevance with the first text information and the second text information respectively. It is understood that the executing entity may also mix the first text message and the second text message, input the TA-NKG model, and generate a common text label.
After the execution main body obtains the text label, the user image can be constructed according to the text label.
In the process of extracting the text label, the user label contained in the text information and the user label contained in the image information are considered, and the value of the retrieval information is fully mined, so that the user image determined according to the text label is more accurate.
In some optional implementations of this embodiment, step 4023 may also be implemented by the following steps 40231 to 40235 which are not shown in fig. 4:
step 40231, performing duplicate removal processing on the text labels to obtain target text labels.
After the execution main body obtains the text label obtained through the first text information and the second text information, redundant repeated labels can be removed, and a target text label is obtained. The defects of the text label extraction algorithm in label extraction can be weakened: only the keywords (labels) appearing in the text can be extracted, and many labels do not appear in the text and cannot be extracted; and the defects of the text label generation model during label generation can be weakened: it is easy to return the generated unrelated label.
Step 40232, clustering the target text labels to obtain a text label cluster.
And after the execution main body obtains the target text label, clustering the target text label to obtain the cluster with the text label. Specifically, label clustering is to perform cluster division on target text labels by using a clustering algorithm according to the idea of clustering the objects. Some labels are gathered together according to certain attribute information to form a set containing many similar labels. In this embodiment, a Clustering algorithm (DPCA algorithm) based on density peak values is used to cluster the user tags, first, the local density of the tags and the distance between the high-density tag points are calculated, and the tag points with a larger size between the local density and the high-density tag points are selected as a Clustering center, that is, a tag cluster; and after the label class clusters are determined, distributing the rest labels to the points closest to the label class clusters, and finally generating a plurality of text label class clusters.
Step 40233, determining a primary text label according to the text label cluster.
Step 40234, determining a secondary text label according to the target text label.
In this embodiment, vectors corresponding to several clustered text label clusters are defined as { C1, C2, C3,.. cndot., Cn }, where C1 to Cn represent different cluster categories. And determining the label cluster generated by clustering as a primary text label, and determining the original label before clustering as a secondary text label.
Step 40235, determining the user image according to the primary text label and the secondary text label.
After the execution main body obtains the first-level text label and the second-level text label, the user image can be constructed according to the first-level text label and the second-level text label. The user portrait is also called a user role, and is an effective tool for outlining target users and connecting user appeal, and the user portrait is widely applied to various fields. In the actual operation process, the most superficial and life-close labels are often used, for example, the obtained primary text label and secondary text label are used for connecting the attributes and behaviors of the user with expected data conversion to form the user portrait.
According to the embodiment, the artificial intelligence algorithms such as tag generation and tag clustering are applied to information pushing, so that the accuracy of information pushing is improved; meanwhile, the obtained text labels are subjected to de-duplication, the most simplified and effective text labels can be obtained, clustering is carried out on the simplified and effective text labels, and the user portrait is constructed according to the clustered label clusters and the original labels which are not clustered, so that the constructed user portrait is more perfect and accurate.
The principle of step 403 is similar to that of step 203, and is not described in detail here.
Specifically, step 403 can be implemented by steps 4031 to 4034:
In this embodiment, the execution subject may obtain attribute information of the target user after obtaining the user representation. Specifically, the executing entity may obtain attribute information of a user, which is sent by the terminal device and is filled in by the user when the user performs retrieval. The user attribute information generally refers to personal information filled by the user during registration, and includes data such as age, gender, region, education, professional information, hobbies and the like, and the information explicitly expresses the preference characteristics of the user and belongs to the user explicit characteristics. Two methods are usually adopted to process the attribute information of the user to obtain the preference characteristics of the user, wherein the two methods are used for directly extracting and processing the attribute information of the user and supplementing and speculating the attribute information of the user. The direct extraction of the user attribute information refers to mining user preference characteristics after the user registers the identity. When a user uses a search engine for searching for the first time, the executive body can remind the user of registering identity in a pop-up window mode, and the user needs to fill in date of birth, gender, province and the like. The user attribute information is supplemented and inferred, that is, when the user attribute information is missing and incomplete, an executive body can supplement and infer the user attribute information by using other characteristics of the user, for example, a work city is not filled in, but the work city of the user can be inferred and supplemented through a user address. By combining the attribute information of the user, the information is pushed to the user, and the success rate of the user for receiving the pushed information is improved. For example, if the push information is a financial product, the purchase rate of the financial product by the user may be increased.
In this embodiment, the pre-trained vector generation model is used to represent the corresponding relationship between each piece of information and the score vector. In this embodiment, after acquiring the user image, the search information, and the attribute information, the execution main body may further analyze the usage of the search information, and the usage of the search information may reflect the user's requirements. From the classification of the retrieved information, it can be determined whether the user frequently inquires about illegal information, such as illegal uses of gambling, drugs, loan overdue, and the like. Specifically, the executing agent may apply the ELECTRA model to classify the purpose of the retrieved information of the target user. The model is the latest pre-training text model, and the performance and the effect of the model are superior to those of similar language models. The input of the model is historical search text information of a target user or characters converted from pictures searched by the target user, and the output is whether the search information of the target user is in compliance or not and the content proportion of non-compliance.
In this embodiment, after obtaining the user image, the search information, the attribute information, and the usage of the target user search information, the execution subject may generate a model by using the usage of the user image, the search information, the attribute information, and the target user search information and a pre-trained vector, and determine a score vector. Specifically, the executing agent may input the user image, the search information, the attribute information, and the purpose of the target user search information into the pre-trained vector generation model, and output a corresponding score vector. Of course, the execution body may also convert the user image, the search information, the attribute information, and the purpose of the target user search information into corresponding score vectors based on a method of word embedding. The method of generating the score vector using the user image, the search information, the attribute information, and the use of the target user search information is not particularly limited.
In this embodiment, the credit score model is used to represent a corresponding relationship between the score vector and the credit score. The executive body can input the obtained scoring vector into a credit scoring model and output the credit scoring of the corresponding target user. The credit score may be a score or a probability, and the application is not limited to this. The executive body can judge whether the target user has the condition of pushed target information (for example, whether the target user has the condition of investment and financing) according to the credit score.
4034, target push information is determined based on the attribute information and the user profile.
In this embodiment, after obtaining the attribute information and the user profile, the execution subject may determine the target push information based on the attribute information and the user profile. Specifically, the executive body can determine the gender and income condition of the user according to the attribute information of the user; determining the type and price gear of a product suitable for being pushed to a target user according to the gender and income condition of the user; based on the user representation, products, such as cosmetics, electronic products, etc., that the user frequently browses are determined. For example, if it is determined that the target user is a girl based on the user attribute information, the monthly income is more than 3 ten thousand; and determining that the target user frequently browses cosmetics and clothes according to the user figure, and then the executive subject can select a handbag with the price of 5000-.
According to the embodiment, based on combination of attribute information of the user, the user portrait and retrieval information of the user, credit scores of the user can be obtained, the obtained credit scores can be used for assisting in judging whether the user meets the information pushing condition, a target user meeting the information pushing condition can be accurately determined, and waste of pushing resources is reduced; by the aid of the method and the device, the target pushing information pushed for the target user can be accurately determined based on the attribute information and the user portrait, the target user acceptance rate of the target pushing information is improved, and user experience is improved.
In some optional implementations of this embodiment, the method for pushing information further includes: historical user representations and historical user attribute information are obtained.
Specifically, the execution main body can acquire the historical user portrait and the historical user attribute information from a local database or a cloud end in a wired or wireless connection mode. The principles of the historical user representation and the historical user attribute information are similar to those of the target user representation and the target user attribute information, and are not described in detail herein.
Specifically, step 4034 may also be implemented by steps 40341 to 40345 as follows:
The executive agent, after obtaining the attribute information of the user and the user portrait, may determine a first probability that the target user accepts each piece of push information based on the attribute information, the user portrait, and the multi-label classification model. Specifically, the executive agent may input the attribute information and the user profile into a multi-label classification model, and output a first probability that the target user accepts each piece of push information. Specifically, the multi-label classification model is composed of a feature processing module, a sigmoid activation function and a cross entry loss function 3. The characteristic processing module is mainly used for vectorizing and digitizing the attribute information of the user and the characteristics corresponding to the user image. The sigmoid function is used as an activation function, so that a first probability that the target user accepts different push information can be obtained, for example, the probability that the target user purchases different financial products can be obtained. For example, if a user has purchased a product, the probability of purchasing the product is 1.
In this embodiment, the executive is obtaining historical user representations. After the historical user attribute information, the user representation and attribute information of the target user, the similarity between the target user and each historical user can be determined based on the historical user representation, the historical user attribute information, the user representation and attribute information of the target user. Specifically, the execution subject may convert the historical user representation, the historical user attribute information, the user representation of the target user, and the attribute information into vectors in a word embedding manner, and then calculate the similarity between the user representation vector and the attribute information vector of the target user and the historical user representation vector and the historical user attribute information vector, where the similarity may be a cosine similarity between the vectors.
After the execution subject obtains the similarity, the target historical user can be determined based on the similarity. Specifically, the execution subject may determine the target historical user according to the similarity and a preset similarity threshold. Specifically, the execution subject may determine all the history users or a preset number of history users corresponding to a similarity greater than a preset similarity threshold as the target history user. For example, k users corresponding to a similarity greater than a preset similarity threshold may be determined as target history users. The number of target history users is not particularly limited in the present application.
At step 40344, a second probability of the target historical user accepting each push is determined.
The executive agent may determine a second probability that the target historical user accepts each piece of push information based on the obtained target historical user attribute information, the target historical user profile, and the multi-label classification model based on the same principles as in step 40341. And will not be described in detail herein.
40345, target push information is determined based on the first probability, the second probability and each piece of push information.
After obtaining the first probability, the second probability, and each piece of push information, the execution subject may determine the target push information based on the first probability, the second probability, and each piece of push information. Specifically, the execution main body may add the first probability and the second probability to obtain user acceptance probabilities corresponding to the added push information, and then sort the user acceptance probabilities corresponding to the push information, and select the push information corresponding to the probability of the TOP-N as the target push information. Illustratively, the probability of the target user accepting product 1 is 0.01; the probability of accepting product 2 is 0.03; the probability of accepting product 3 is 0.5; the probability that the target historical user 1 accepts the product 1 is 0.2; the probability of the target historical user 1 accepting the product 2 is 0.1; the probability that the target historical user 1 accepts the product 3 is 0.4; the probability that the target historical user 2 accepts the product 1 is 0.1; the probability that the target historical user 2 accepts the product 2 is 0.1; the probability of the target history user 2 accepting the product 3 is 0.4. The execution subject may add the accepted probabilities of the same product and then perform descending sorting, and the sorting of each piece of push information (product) corresponding to the added probabilities is product 3: 1.3, product 1: 0.31, product 2: 0.2, it can be seen that the acceptance probability of product 3 and product 2 is greater than that of product 1. If the product ranked in the TOP-2 is selected for pushing, the product 3 and the product 2 are selected as target push information, and the first push is performed with the product 3 as the target push information.
According to the method and the device, the probability of receiving each piece of push information by the target user and the target historical user is respectively determined through the classification model based on the attribute information, the user portrait and the multiple labels, and then the probabilities corresponding to the same piece of push information are added to determine the target push information most popular with the user, so that the accuracy of the push information of the target user can be improved, and the receiving rate of the target user on the target push information can be improved.
In this embodiment, the method for pushing information further includes step 404:
Specifically, after obtaining the retrieval information, the execution subject may determine the target push time based on the retrieval information. Specifically, the execution subject may determine, based on the search information, a change of a user search content tag (or called a keyword/word) with time, and may obtain a change of user interest information and a change of user demand through statistics of the change of the user search content tag, for example, a time of recommendation of the financial product may be determined through statistics of the change of the search tag with time. For example, if the user frequently searches for keywords such as "fund" and "Shanghai depth index" within the latest period of time, the user may have a financial investment requirement recently, the execution subject may obtain the time when the user searches for the keywords such as "fund" and "Shanghai depth index", and may push the relevant financial products to the target user within the same or similar period of time of the obtained time in the next few days. The method and the device avoid the user's reaction caused by pushing related products to the target user in the working time of the target user or the time inconvenient for the target user, so that the target pushing information can be accurately pushed, the user's reaction cannot be caused, and the user experience can be improved.
The principle of step 405 is similar to that of step 204, and is not described here again.
Specifically, step 405 may be implemented by performing the following iterative steps 4051-4053 multiple times:
In this embodiment, after obtaining the credit score, the execution main body may determine a size relationship between the credit score and the preset threshold, and if the credit score is greater than the preset threshold, the execution main body may push, in response to determining that the credit score is greater than the preset threshold, related target push information to the target user at a target push time determined by statistics of changes over time of the retrieval tag. Specifically, the target push information may be more than one, and may be multiple.
After the execution main body pushes the target push information to the target user, the execution main body can respond to the fact that the user accepts the target push information and stop information pushing; of course, the executing entity may also select new target push information from the determined target push information of the TOP-N and update the target push information in response to determining that the user does not accept the target push information, and push the updated target push information to the target user at the target push time until the user accepts the target push information. Of course, it can be understood that, when the execution main body responds that the user does not accept the target push information and the target push information of the previous TOP-N has already been pushed, the execution main body may also randomly select the push information from the push information of the non-TOP-N as the updated target push information to push again to the target user, so as to improve the success rate of accepting the push information by the target user.
According to the embodiment, the information is pushed to the user with the credit score larger than the preset threshold value, the pushing resources can be saved, unnecessary pushing for increasing the memory pressure is avoided, meanwhile, the selected target pushing information of the front TOP-N is circularly pushed to the target user, the success rate of the user for receiving the pushing information can be improved, and the user experience is improved.
With further reference to fig. 5, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for pushing information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied 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 user portrait determination unit 502, an information processing unit 503, and a push unit 504.
An obtaining unit 501 configured to obtain retrieval information of a target user.
A user representation determination unit 502 configured to determine a user representation based on the retrieved information.
An information processing unit 503 configured to determine a credit score and target push information of the target user based on the user profile.
A pushing unit 504 configured to push the target push information to the target user based on the credit score.
In some optional implementations of this embodiment, the retrieval information includes image information and first text information; and user representation determination unit 502 is further configured to: determining second text information corresponding to the image information according to the image information and a pre-trained conversion model, wherein the pre-trained conversion model is used for representing the corresponding relation between the image information and the text information; generating a text label based on the first text information, the second text information, the pre-trained text label extraction algorithm and the pre-trained text label generation model; and determining the user image according to the text label.
In some optional implementations of this embodiment, the user representation determination unit 502 is further configured to: performing duplicate removal processing on the text label to obtain a target text label; clustering target text labels to obtain a text label cluster; determining a primary text label according to the text label cluster; determining a secondary text label according to the target text label; and determining the user image according to the primary text label and the secondary text label.
In some optional implementations of this embodiment, the information processing unit 503 is further configured to: acquiring attribute information of a target user; determining a score vector according to the user portrait, the retrieval information, the attribute information and a pre-trained vector generation model, wherein the pre-trained vector generation model is used for representing the corresponding relation between each piece of information and the score vector; determining the credit score of the target user according to the score vector and a credit score model, wherein the credit score model is used for representing the corresponding relation between the score vector and the credit score; based on the attribute information and the user profile, targeted push information is determined.
In some optional implementations of this embodiment, the obtaining unit 501 is further configured to: acquiring a historical user portrait and historical user attribute information; and the information processing unit 503 is further configured to: determining a first probability of receiving each piece of push information by a target user based on the attribute information, the user portrait and a multi-label classification model; determining the similarity between the target user and each historical user based on the historical user portrait, the historical user attribute information, and the user portrait and attribute information of the target user; determining a target historical user based on the similarity; determining a second probability that the target historical user receives each piece of push information; and determining target push information based on the first probability, the second probability and each piece of push information.
In some optional implementations of this embodiment, the apparatus further includes a target push time determining unit, not shown in fig. 5, configured to determine the target push time based on the retrieval information; and the pushing unit 504 is further configured to: the following iterative steps are performed a plurality of times: in response to determining that the credit score is greater than a preset threshold, pushing target push information to a target user at a target push time; stopping information pushing in response to determining that the user accepts the target pushing information; and in response to determining that the user does not accept the target push information, adjusting and updating the target push information, and pushing the updated target push information to the target user at the target push time.
It should be understood that units 501 to 504, which are described in the apparatus 500 for pushing information, correspond to respective steps in the method described with reference to fig. 2, respectively. Thus, the operations and features described above for the method for pushing information are also applicable to the apparatus 500 and the units included therein, and are not described in detail here.
According to an embodiment of the present application, an electronic device and a readable storage medium for pushing information are also provided.
As shown in fig. 6, the electronic device is a block diagram of an electronic device for pushing information according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses 605 and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses 605 may be used, along with multiple memories and multiple memories, if desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method for pushing information provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method for pushing information provided by the present application.
The memory 602, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and units, such as program instructions/units corresponding to the method for pushing information in the embodiment of the present application (for example, the acquiring unit 501, the user portrait determining unit 502, the information processing unit 503, and the pushing unit 504 shown in fig. 5). The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 602, that is, implements the method for pushing information in the above method embodiments.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device for pushing information, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 optionally includes memory located remotely from the processor 601, which may be connected to an electronic device for pushing information over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the method for pushing information may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603, and the output device 604 may be connected by a bus 605 or other means, and are exemplified by the bus 605 in fig. 6.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic apparatus for pushing information, such as an input device like a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, etc. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, the user portrait is determined according to daily retrieval information of the user, the user portrait is used as a reference feature when the product is recommended, and the credit score of the user determined based on the user portrait is combined, so that accurate product recommendation for a target user can be realized, the learning cost and the time cost of the user when the product is selected can be effectively reduced, and the user experience is improved.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (14)
1. A method for pushing information, comprising:
acquiring retrieval information of a target user;
determining a user representation based on the search information;
determining credit scores and target push information of target users based on the user portrait;
and pushing the target pushing information to the target user based on the credit score.
2. The method of claim 1, wherein the retrieval information includes image information and first text information; and
determining a user representation based on the search information, comprising:
determining second text information corresponding to the image information according to the image information and a pre-trained conversion model, wherein the pre-trained conversion model is used for representing the corresponding relation between the image information and the text information;
generating a text label based on the first text information, the second text information, a pre-trained text label extraction algorithm and a pre-trained text label generation model;
and determining the user image according to the text label.
3. The method of claim 2, wherein said determining a user portrait from the text label comprises:
carrying out duplication elimination processing on the text label to obtain a target text label;
clustering the target text labels to obtain a text label cluster;
determining a primary text label according to the text label cluster;
determining a secondary text label according to the target text label;
and determining the user image according to the primary text label and the secondary text label.
4. The method of claim 3, wherein determining a credit score and target push information for a target user based on the user representation comprises:
acquiring attribute information of a target user;
determining a score vector according to the user image, the retrieval information, the attribute information and a pre-trained vector generation model, wherein the pre-trained vector generation model is used for representing the corresponding relation between each piece of information and the score vector;
determining the credit score of the target user according to the score vector and a credit score model, wherein the credit score model is used for representing the corresponding relation between the score vector and the credit score;
and determining target push information based on the attribute information and the user portrait.
5. The method of claim 4, wherein the method further comprises: acquiring a historical user portrait and historical user attribute information; and
the determining target push information based on the attribute information and the user representation comprises:
determining a first probability of the target user accepting each piece of push information based on the attribute information, the user portrait and a multi-label classification model;
determining similarity between the target user and each historical user based on the historical user representation, the historical user attribute information, and the user representation and attribute information of the target user;
determining a target historical user based on the similarity;
determining a second probability that the target historical user accepts each piece of push information;
and determining target push information based on the first probability, the second probability and the push information.
6. The method of any of claims 1-5, wherein the method further comprises: determining target pushing time based on the retrieval information; and
the pushing the target push information to the target user based on the credit score includes:
the following iterative steps are performed a plurality of times:
in response to determining that the credit score is greater than a preset threshold, pushing the target push information to the target user at the target push time;
stopping information pushing in response to determining that the user accepts the target pushing information;
and in response to determining that the user does not accept the target push information, adjusting and updating the target push information, and pushing the updated target push information to the target user at the target push time.
7. An apparatus for pushing information, comprising:
an acquisition unit configured to acquire retrieval information of a target user;
a user representation determining unit configured to determine a user representation based on the search information;
an information processing unit configured to determine a credit score and target push information for a target user based on the user representation;
a pushing unit configured to push the target push information to the target user based on the credit score.
8. The apparatus of claim 7, wherein the retrieval information includes image information and first text information; and
the user representation determination unit is further configured to:
determining second text information corresponding to the image information according to the image information and a pre-trained conversion model, wherein the pre-trained conversion model is used for representing the corresponding relation between the image information and the text information;
generating a text label based on the first text information, the second text information, a pre-trained text label extraction algorithm and a pre-trained text label generation model;
and determining the user image according to the text label.
9. The apparatus of claim 8, wherein the user representation determination unit is further configured to:
carrying out duplication elimination processing on the text label to obtain a target text label;
clustering the target text labels to obtain a text label cluster;
determining a primary text label according to the text label cluster;
determining a secondary text label according to the target text label;
and determining the user image according to the primary text label and the secondary text label.
10. The apparatus of claim 9, wherein the information processing unit is further configured to:
acquiring attribute information of a target user;
determining a score vector according to the user image, the retrieval information, the attribute information and a pre-trained vector generation model, wherein the pre-trained vector generation model is used for representing the corresponding relation between each piece of information and the score vector;
determining the credit score of the target user according to the score vector and a credit score model, wherein the credit score model is used for representing the corresponding relation between the score vector and the credit score;
and determining target push information based on the attribute information and the user portrait.
11. The apparatus of claim 10, wherein the obtaining unit is further configured to: acquiring a historical user portrait and historical user attribute information; and
the information processing unit is further configured to:
determining a first probability of the target user accepting each piece of push information based on the attribute information, the user portrait and a multi-label classification model;
determining similarity between the target user and each historical user based on the historical user representation, the historical user attribute information, and the user representation and attribute information of the target user;
determining a target historical user based on the similarity;
determining a second probability that the target historical user accepts each piece of push information;
and determining target push information based on the first probability, the second probability and the push information.
12. The apparatus according to any one of claims 7 to 11, wherein the apparatus further comprises a target push time determining unit configured to determine a target push time based on the retrieval information; and
the pushing unit is further configured to:
the following iterative steps are performed a plurality of times:
in response to determining that the credit score is greater than a preset threshold, pushing the target push information to the target user at the target push time;
stopping information pushing in response to determining that the user accepts the target pushing information;
and in response to determining that the user does not accept the target push information, adjusting and updating the target push information, and pushing the updated target push information to the target user at the target push time.
13. An electronic device for pushing information, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329158.5A CN112330455B (en) | 2020-11-24 | 2020-11-24 | Method, device, equipment and storage medium for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329158.5A CN112330455B (en) | 2020-11-24 | 2020-11-24 | Method, device, equipment and storage medium for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112330455A true CN112330455A (en) | 2021-02-05 |
| CN112330455B CN112330455B (en) | 2024-04-12 |
Family
ID=74322254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011329158.5A Active CN112330455B (en) | 2020-11-24 | 2020-11-24 | Method, device, equipment and storage medium for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112330455B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010777A (en) * | 2021-03-05 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Data pushing method, device, equipment and storage medium |
| CN113344620A (en) * | 2021-05-31 | 2021-09-03 | 北京百度网讯科技有限公司 | Method, device and storage medium for issuing welfare information |
| CN113362162A (en) * | 2021-06-29 | 2021-09-07 | 深圳壹账通智能科技有限公司 | Wind control identification method and device based on network behavior data, electronic equipment and medium |
| CN113962567A (en) * | 2021-10-26 | 2022-01-21 | 北京百度网讯科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN114117755A (en) * | 2021-11-11 | 2022-03-01 | 泰康保险集团股份有限公司 | Simulation drilling method and device, computing equipment and storage medium |
| CN114238767A (en) * | 2021-12-20 | 2022-03-25 | 中国平安财产保险股份有限公司 | Service recommendation method and device, computer equipment and storage medium |
| CN115955452A (en) * | 2023-03-15 | 2023-04-11 | 上海帜讯信息技术股份有限公司 | 5G message pushing method and device based on multi-turn conversation intention recognition |
| CN117749880A (en) * | 2023-12-21 | 2024-03-22 | 北京易丰嘉诚科技有限公司 | Webpage data pushing method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665355A (en) * | 2018-05-18 | 2018-10-16 | 深圳壹账通智能科技有限公司 | Financial product recommends method, apparatus, equipment and computer storage media |
| CN108984555A (en) * | 2017-06-01 | 2018-12-11 | 腾讯科技（深圳）有限公司 | User Status is excavated and information recommendation method, device and equipment |
| CN109104471A (en) * | 2018-07-26 | 2018-12-28 | 新疆玖富万卡信息技术有限公司 | A kind of method of recommendation service, management server and recommendation server |
| CN110245160A (en) * | 2019-06-03 | 2019-09-17 | 贝壳技术有限公司 | A kind of method and system of determining house decoration scheme |
| WO2020108150A1 (en) * | 2018-11-30 | 2020-06-04 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN111861174A (en) * | 2020-07-09 | 2020-10-30 | 北京睿知图远科技有限公司 | Credit assessment method for user portrait |
-
2020
- 2020-11-24 CN CN202011329158.5A patent/CN112330455B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984555A (en) * | 2017-06-01 | 2018-12-11 | 腾讯科技（深圳）有限公司 | User Status is excavated and information recommendation method, device and equipment |
| CN108665355A (en) * | 2018-05-18 | 2018-10-16 | 深圳壹账通智能科技有限公司 | Financial product recommends method, apparatus, equipment and computer storage media |
| CN109104471A (en) * | 2018-07-26 | 2018-12-28 | 新疆玖富万卡信息技术有限公司 | A kind of method of recommendation service, management server and recommendation server |
| WO2020108150A1 (en) * | 2018-11-30 | 2020-06-04 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN110245160A (en) * | 2019-06-03 | 2019-09-17 | 贝壳技术有限公司 | A kind of method and system of determining house decoration scheme |
| CN111861174A (en) * | 2020-07-09 | 2020-10-30 | 北京睿知图远科技有限公司 | Credit assessment method for user portrait |
Non-Patent Citations (1)
| Title |
|---|
| 吕超;朱郑州: "一个基于用户画像的商品推荐算法的设计与应用", 中国科技论文在线精品论文, vol. 11, no. 004, 31 December 2018 (2018-12-31) * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010777A (en) * | 2021-03-05 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Data pushing method, device, equipment and storage medium |
| CN113344620A (en) * | 2021-05-31 | 2021-09-03 | 北京百度网讯科技有限公司 | Method, device and storage medium for issuing welfare information |
| CN113362162A (en) * | 2021-06-29 | 2021-09-07 | 深圳壹账通智能科技有限公司 | Wind control identification method and device based on network behavior data, electronic equipment and medium |
| CN113962567A (en) * | 2021-10-26 | 2022-01-21 | 北京百度网讯科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN114117755A (en) * | 2021-11-11 | 2022-03-01 | 泰康保险集团股份有限公司 | Simulation drilling method and device, computing equipment and storage medium |
| CN114238767A (en) * | 2021-12-20 | 2022-03-25 | 中国平安财产保险股份有限公司 | Service recommendation method and device, computer equipment and storage medium |
| CN115955452A (en) * | 2023-03-15 | 2023-04-11 | 上海帜讯信息技术股份有限公司 | 5G message pushing method and device based on multi-turn conversation intention recognition |
| CN115955452B (en) * | 2023-03-15 | 2023-06-06 | 上海帜讯信息技术股份有限公司 | 5G message pushing method and device based on multi-round conversation intention recognition |
| CN117749880A (en) * | 2023-12-21 | 2024-03-22 | 北京易丰嘉诚科技有限公司 | Webpage data pushing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112330455B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112330455B (en) | Method, device, equipment and storage medium for pushing information | |
| CN111767403B (en) | Text classification method and device | |
| CN111191428B (en) | Comment information processing method and device, computer equipment and medium | |
| CN111625635A (en) | Question-answer processing method, language model training method, device, equipment and storage medium | |
| Fu et al. | CRNN: a joint neural network for redundancy detection | |
| WO2023108993A1 (en) | Product recommendation method, apparatus and device based on deep clustering algorithm, and medium | |
| CN111104514A (en) | Method and device for training document label model | |
| Mukalov et al. | Development of System for Auto-Tagging Articles, Based on Neural Network. | |
| CN111309910A (en) | Text information mining method and device | |
| CN112733042A (en) | Recommendation information generation method, related device and computer program product | |
| JP7498129B2 (en) | METHOD AND APPARATUS FOR PUSHING INFORMATION, ELECTRONIC DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM - Patent application | |
| CN112989208B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| EP3732592A1 (en) | Intelligent routing services and systems | |
| CN112148881A (en) | Method and apparatus for outputting information | |
| CN113051380B (en) | Information generation method, device, electronic equipment and storage medium | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text | |
| CN111782793A (en) | Intelligent customer service processing method, system and equipment | |
| CN113742592A (en) | Public opinion information pushing method, device, equipment and storage medium | |
| CN112560461A (en) | News clue generation method and device, electronic equipment and storage medium | |
| CN113516491A (en) | Promotion information display method and device, electronic equipment and storage medium | |
| CN114357951A (en) | Method, device, equipment and storage medium for generating standard report | |
| CN111988668B (en) | Video recommendation method and device, computer equipment and storage medium | |
| CN114255067A (en) | Data pricing method and device, electronic equipment and storage medium | |
| CN113486184A (en) | Keyword determination method, device, equipment and storage medium | |
| CN111832313B (en) | Method, device, equipment and medium for generating emotion matching set in text |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |