CN110955823B - Information recommendation method and device - Google Patents
Information recommendation method and device Download PDFInfo
- Publication number
- CN110955823B CN110955823B CN201811124322.1A CN201811124322A CN110955823B CN 110955823 B CN110955823 B CN 110955823B CN 201811124322 A CN201811124322 A CN 201811124322A CN 110955823 B CN110955823 B CN 110955823B
- Authority
- CN
- China
- Prior art keywords
- service
- violation
- category
- topic
- service provider
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 20
- 230000002452 interceptive effect Effects 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000004138 cluster model Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 14
- 238000003860 storage Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000003672 processing method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011282 treatment Methods 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an information recommendation method and device. The method comprises the following steps: according to the acquired service data of the service provider, clustering the service provider by using a trained clustering model to determine a corresponding service information theme; further, according to the obtained service information subject of each service provider, the processed legal regulations and platform rule information are recommended to the corresponding service provider by using a recommendation model, so that the service provider can accurately acquire the required service information. The clustering model is obtained through training according to the service provider samples, and each service provider can be accurately classified, so that required service information is provided for each service provider, and the accuracy and timeliness of data are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to an information recommendation method and device.
Background
In order to ensure legal operation of merchants in the electronic commerce platforms, each electronic commerce platform can provide learning materials for learning legal regulations and platform operation rules for a plurality of merchants, so that the merchants in the electronic commerce platforms are effectively prevented from violating the legal regulations in the operation process.
In the prior art, since the types of commercial products of merchants are various, laws and regulations which are easily violated by each merchant are also different. In order to avoid illegal operations of merchants, a learning file containing all legal regulations and platform management rules is generally provided for each merchant to learn. However, due to the great content of laws and regulations, the merchant needs to invest a relatively large amount of time to study laws and regulations, platform management rules and the like related to the laws and regulations, and the merchant needs to pay a relatively high learning cost, but the harvesting effect is very small.
Based on the prior art, a technical scheme capable of accurately and timely recommending corresponding service information according to service statistics data of merchants is needed.
Disclosure of Invention
In order to solve the problems, the embodiments of the present invention provide an information recommendation method and apparatus, so as to implement a technical scheme of timely and accurately recommending corresponding service information to a service provider.
In a first aspect, an embodiment of the present invention provides an information recommendation method, where the method includes:
acquiring service statistics data of a service provider;
determining a category of the service provider according to the service statistics;
Determining a service information theme corresponding to the category according to the established corresponding relation between the service provider category and the service information theme;
and recommending the service information corresponding to the service information theme to the service provider.
In a second aspect, an embodiment of the present invention provides an information recommendation apparatus, including:
the acquisition module is used for acquiring service statistics data of the service provider;
a category determining module, configured to determine a category of the service provider according to the service statistics data;
the topic determination module is used for determining the service information topic corresponding to the class according to the established corresponding relation between the class of the service provider and the service information topic;
and the recommending module is used for recommending the service information corresponding to the service information theme to the service provider.
In a third aspect, an embodiment of the present invention provides an electronic device, including a first processor, a first memory, a first communication interface, and a first touch screen, where the first memory is configured to store one or more computer instructions, where the one or more computer instructions are implemented when executed by the first processor:
acquiring service statistics data of a service provider;
Determining a category of the service provider according to the service statistics;
determining a service information theme corresponding to the category according to the established corresponding relation between the service provider category and the service information theme;
and recommending the service information corresponding to the service information theme to the service provider.
An embodiment of the present invention provides a computer storage medium storing a computer program, where the computer program makes a computer execute the information recommendation method in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a data processing method, including:
acquiring service statistics data of an account, wherein the service statistics data comprise violation times;
determining a category corresponding to the account according to the service statistics data;
obtaining push information corresponding to the category, wherein the push information comprises configuration parameters which are suitable for changing an interactive interface of a client where the account is located;
and sending the push information to the client.
In a fifth aspect, an embodiment of the present invention provides a data processing method, including:
the client side where the account is located receives push information from a server, wherein the push information corresponds to the category of the account;
The client side where the account is located obtains configuration parameters based on the push information;
and the client where the account is located changes the interactive interface based on the configuration parameters.
In the embodiment of the invention, the service statistical data is obtained by weighting according to the accumulated service data of the service provider. The category of the service provider is determined based on the service statistics. Further, according to the pre-established corresponding relation between the service provider category and the service information theme, the service information theme corresponding to the service provider is determined. And recommending the service information content corresponding to the service information theme to the service provider. Through the technical scheme, according to the category of the service provider (such as an e-commerce), the service information (such as laws and regulations and e-commerce platform rule system) corresponding to the category is accurately recommended, and excessive irrelevant service information is prevented from being sent to the service provider.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of an information recommendation system according to an embodiment of the present invention;
fig. 2 is a flow chart of an information recommendation method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of recommending laws and regulations, platform rules and corresponding presentation tools to a merchant according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an information recommendation device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device corresponding to the information recommending apparatus provided in the embodiment shown in fig. 4;
fig. 6 is a schematic diagram of two kinds of interaction interfaces according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two, but does not exclude the case of at least one.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or system comprising such elements.
Fig. 1 is a schematic structural diagram of an information recommendation system according to an embodiment of the present invention, where, as shown in fig. 1, the information recommendation system includes:
in the system, service statistics of a plurality of service providers for training an information recommendation model are included as training samples, and the information recommendation model obtained through training, the service providers to be classified and service information for feeding back to the service providers are obtained through training. Specifically, the training samples are used for training to obtain an information recommendation model. The service information to be recommended is also classified, and the service information is sorted to obtain the simplified service information of each class. Further, the information recommendation model is utilized to classify the service provider to be classified, and the service provider is provided with the required service information according to the classification result.
For ease of understanding, the following description will take as an example a merchant whose service provider is an e-commerce platform when illustrated. The information recommendation model described above includes a cluster model for classifying service providers and a recommendation model for recommending service information to the user.
Fig. 2 is a schematic flow chart of an information recommendation method provided by an embodiment of the present invention, where the method includes the following steps:
201: service statistics of the service provider are obtained.
For example, the service provider referred to herein may be a merchant in an e-commerce platform.
The service statistics referred to herein may be transaction data between the consumer and the merchant, the number of violations by the merchant, the total length of service by the merchant (in other words, the length of time the merchant registers with the e-commerce platform), and so on. The service statistics data types are only used as an example, and do not limit the technical scheme of the invention, and in practical application, the user can increase or decrease the number of the service statistics data types according to practical situations.
The service statistics of the service providers are stored and updated in real time by the storage means so that the latest data of each service provider can be acquired in time. In practical applications, the frequency of acquiring the service statistics may be daily, so that the required service information can be timely and accurately provided according to the latest service data of the service provider.
202: and determining the category of the service provider according to the service statistical data.
It will be readily appreciated that the service provider is assumed to be a merchant in the e-commerce platform. In the same electronic commerce platform, the types of products operated by all merchants are various, and the registration time and the violation times of different merchants operating the same product are different. Based on service statistics of the service providers, the service providers may be classified into the same class, classifying service providers that have a specified commonality (e.g., meeting the same distance threshold when performing cluster analysis). When determining the category of the service provider according to the service statistics, a clustering or classifying method can be adopted for determination.
For example, the classification of the merchant is performed according to service statistics such as transaction data, violation number and the like of the merchant, and the class can be the violation class of the merchant. Specifically, the violation categories may be pirate picture violations, product infringement violations, and so forth.
203: and determining the service information theme corresponding to the category according to the established corresponding relation between the service provider category and the service information theme.
When classifying the service provider, adopting label-free classification (such as classification by using a clustering model); after the classification result is obtained, determining the service information theme corresponding to the service provider according to the corresponding relation between the preset service provider class and the service information theme. The correspondence relationship may be determined by a correspondence relationship between a service provider category and a service information topic determined when a model for classifying service providers is trained, and different service provider categories may be distinguished by a service information topic label.
For example, assuming that the service provider is a merchant of the e-commerce platform, after determining the type of violation of the merchant according to the foregoing, further, determining the topic of violation of the merchant is required.
204: and recommending the service information corresponding to the service information theme to the service provider.
After determining the category to which the service provider belongs and the corresponding service information topic, further recommending the service information corresponding to the service information topic to the service provider. It should be noted that, the service information is obtained after query and screening, and generally, the screened service information has a one-to-one correspondence with the service information subject. In practical application, the recommending mode can be, for example, recommending the legal regulations and/or platform rules corresponding to the offence subject obtained through query screening to a service provider (such as a merchant), so that the required legal regulations and/or platform rules can be provided for the merchant more accurately, the merchant can learn the required legal regulations and/or platform rules more accurately and timely, and the probability of unintentional offence of the merchant can be effectively reduced. The service information is herein understood to be the content of the specific service information (e.g., law and regulation, platform rule, etc.) that is screened corresponding to the service information topic (e.g., offending topic), and does not include the service information that does not have a corresponding relationship with the service information topic. The service information obtained by screening can be, for example, law and regulation obtained by screening, specifically, law and regulation text of advertising law; the platform rule can also be a platform rule obtained through screening, in particular to a business advertisement propaganda rule text formulated by an electronic business platform. Of course, it may be a picture or video containing the content of the legal rules of advertising.
As described above, for example, assuming that the service provider is a merchant, the service information topic is a merchant violation topic, and the service information to be recommended is legal regulations for the merchant to learn, e-commerce platform rules, and the like. And recommending texts or videos for learning laws and regulations for the merchant and rule learning of an electronic commerce platform to the merchant according to the merchant violation topics. In the existing laws and regulations recommended for merchants and electronic commerce platform rules, various topics are usually contained, and the merchants cannot find relevant legal and regulation contents from the rules and the regulations in time and quickly, so that the problems of high merchant learning cost, low merchant learning efficiency, poor learning effect and the like are caused. Therefore, the embodiment of the invention classifies the laws and regulations and the electronic commerce platform rules according to the offending topics, so that the laws and regulations information of different offending topics can be recommended to required merchants, and the accuracy and timeliness of data are improved.
FIG. 3 is a schematic diagram of recommending laws and regulations, platform rules, and corresponding presentation tools to a merchant. In practical application, in order to improve the learning effect of the legal regulations and platform rules of the merchants in a targeted manner, the learning habit of the merchants needs to be considered during recommendation, for example, some merchants like to learn through text files, and some merchants like to learn through videos or pictures. To promote merchant learning interest, previous examples of other merchant violations and treatments may be added to the recommended service information. Thus, there is a need to recommend suitable presentation tools for different merchants in order to assist the merchants in better learning legal regulations and e-commerce platform rules.
In recommending service information to a merchant, a recommendation model (e.g., a recommendation model based on a bandit algoritm algorithm) may be utilized. Specifically, the recommendation model calculates service information closest to the offending theme according to service statistics data and service information themes of merchants, so that the service information and a corresponding display tool can be accurately recommended. Therefore, the learning cost of the merchant for learning laws and regulations and platform rules can be effectively reduced.
In one or more embodiments of the invention, the service statistics are weighted results of service data of at least one dimension.
In order to eliminate the influence of data fluctuation on the clustering result, a weighted moving average processing method can be adopted. One dimension as referred to herein may be understood as the time dimension. Specifically, the weighted moving average method is adopted because the recent observed value of the observed period has a larger influence on the predicted value, and it can reflect the trend of the recent service provider's offending change. Therefore, the observed values close to the prediction period are given larger weighted values, and the observed values far from the prediction period are given smaller weighted values correspondingly, so that the effect of each observed value on the predicted value is regulated by different weighted values, and the predicted value can more approximately reflect the future trend of the possibly attributive violation categories of the service provider.
Of course, in practical applications, when the service data is weighted, multiple dimensions may be used simultaneously, for example, the service data may be weighted simultaneously by using dimensions such as a time dimension and a space dimension.
In one or more embodiments of the present invention, the service data of the at least one dimension includes: at least one of transaction data within at least one preset time period, the number of violations occurring within at least one preset time period, and the total duration of service.
For example, as previously described, the service provider may be a merchant, transaction data within a predetermined period of time, as referred to herein, and specifically, for example, the order log system may calculate a historical 30 day transaction amount, a historical 30 day to 90 day transaction amount, and a historical 90 day to 180 day transaction amount for each merchant. The behavior log system may record, for example, 30 days of the number of violations, 30 days to 90 days of the number of violations, and 90 days to 180 days of the number of violations. The total duration of the service referred to herein is the duration of the merchant registration time to the current time.
In one or more embodiments of the present invention, for the transaction data in the at least one preset time period, the weight corresponding to the transaction data in the first preset time period is greater than the weight corresponding to the transaction data in the second preset time period, wherein the first preset time period is closer to the current time than the second preset time period.
As described above, the service statistics are weighted results obtained by weighting based on a specified dimension (e.g., a time dimension).
For example, for the weighting of transaction data, the weighting may be based on a time dimension. And giving different weights to different time dimensions, and carrying out weighted moving average processing to obtain predicted transaction data and predicted behavior data with a certain predictability on future trends.
Using a weighted moving average method (moving weighted average method), the formula is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,
W 1 the representation is: weighting of historical 30-day transaction amounts; a is that t1 30 days of transaction amount was historical. W (W) 2 The representation is: a weight of transaction amount of 30 days to 90 days in history; a is that t2 Transaction amounts of 30 days to 90 days in history. W (W) n The representation is: historical X1 day to X2 day transaction amount weights; a is that tn Transaction amounts of day X1 to day X2 are historical. The weight value is 1, i.e., W 1 +W 2 +…+W n ＝1。
The weighted moving average can smooth the fluctuation of the index, give a relatively higher weight to the index closer to the calculation date, accord with the service characteristics, and have a certain predictability in the future.
In one or more embodiments of the present invention, for the number of times of the offending behavior occurring in the at least one preset time period, a weight corresponding to the number of times of the offending behavior occurring in a first preset time period is greater than a weight corresponding to the number of times of the offending behavior occurring in a second preset time period, where the first preset time period is closer to the current time than the second preset time period.
As can be seen from the foregoing, assuming that the service provider is a merchant of the e-commerce platform, the corresponding service information topic is an offending topic. In order to accurately divide the types of the violations of the merchants and predict the types of the violations which may occur in the subsequent merchants, the acquired historical violation data of the merchants needs to be processed. For example, different weights are given to different time dimensions, weighted moving average processing is carried out, and a certain predictive weighted result is obtained on the future possible illegal category trend of the merchant. In dealing with the number of violations, a weighted moving average process may be employed, for example. In order to obtain more accurate times of violations with a prediction effect, when weighting is performed, a greater weighting value may be given to the times of violations in a time period close to the current time than the times of violations in a time period earlier than the current time.
A specific algorithm may employ a weighted moving average method (moving weighted average method),
wherein W represents the weight, and At represents the number of violations. The calculation process is similar to that described above, and the description thereof will not be repeated here.
In one or more embodiments of the present invention, the weight coefficient of the total duration of the service is one.
As noted above, the total length of service referred to herein may be understood as the length of merchant registration time. In practical application, the processing of the merchant registration time length can adopt a processing mode that the weight coefficient is one, and the merchant registration time is not split and weighted according to the time dimension.
In one or more embodiments of the present invention, the determining the class of the service provider according to the service statistics may specifically include: inputting the service statistical data into a trained cluster model; and obtaining the category output by the clustering model.
In practical application, when classifying the categories, the service provider may be classified by using a clustering model obtained by training in advance. For example, the relevant data such as the number of times of the offence of the merchant, the registration time, the transaction data and the like can be weighted according to the appointed dimension and then used as the input of the clustering model obtained through training, so that the offence category of the merchant can be determined.
In one or more embodiments of the present invention, service statistics of a plurality of service providers are obtained as training samples; and training the clustering model according to the training samples to obtain the categories corresponding to the service providers.
In preparing training samples, it is necessary to obtain a variety of service statistics provided by a plurality of service providers. It is easy to understand that the clustering model is a label-free learning model, and each category needs to be labeled after the category determined based on the clustering model is acquired.
In one or more embodiments of the invention, the service statistics include violation data.
Determining a set of service providers consisting of service providers corresponding to the same category; and determining each violation topic corresponding to the same category and the violation probability of each violation topic according to the violation data of each service provider in the service provider set.
As can be seen from the foregoing, the clustering model may be trained without labels, so that after the classification results of the classes of the plurality of service providers are obtained, the number of various service information topics of different service providers in each class is counted.
For example, suppose two violation categories are obtained, a first violation category and a second violation category, respectively; assume that there are merchant a and merchant b in the first violation category and merchant c and merchant d in the second violation category. Wherein, the illegal subject of merchant a has a pirate map which violates 10 times and violates the advertising method 7 times; the illegal subject of merchant b has a map stolen violation 6 times and an advertising law is violated 3 times; the illegal subject of merchant c has 7 illegal patterns and 12 violations of advertising laws; the offending topic of merchant d has a pirate drawing offending 3 times and an advertising law is violated 6 times. Further, counting the number of each violation subject in each violation category, wherein in the first violation category, the number of the illegal map violations is 16 times and the number of the illegal map violations is 10 times; in the second violation category, the piracy pattern violations are accumulated 10 times and the violation of the advertising laws is accumulated 18 times. After the number is obtained, further, the occupation ratio of each offending topic in each category is counted; in the first violation category, the rule-stealing graph violation probability=16/26, the rule-stealing graph violation probability is 61.5%, the rule-violating advertisement probability=10/26, and the rule-violating advertisement probability is 38.5%; in the second violation category, the probability of the illegal map violation=10/28, the probability of the illegal map violation is 35.7%, the probability of the violation of the advertising method is 18/28, and the probability of the violation of the advertising method is 64.3%. Therefore, it can be seen that the probability of the map theft violation in the first violation category is greater than the probability of the advertisement violation, and the main violation subject of the first violation category is the map theft violation; the probability of violating the advertising method in the second violation category is larger than the probability of violating the map, and the main violation subject of the second violation category is violating the advertising method.
In one or more embodiments of the present invention, the determining, according to the established correspondence between the service provider category and the service information topic, the service information topic corresponding to the category may specifically include: according to the violation probability of each violation topic corresponding to the category, determining the violation topic with the violation probability meeting the preset requirement from each violation topic corresponding to the category as the service information topic
In practical application, the violation subject corresponding to each category can be determined according to the violation probability. The preset requirement for determining the offence theme may refer to selecting the offence theme with the largest probability value of the offence probability in the offence themes, or the offence theme with the probability value larger than the preset threshold. For example, the probabilities of 3 offending topics in the same category can be counted, the offending probabilities are respectively 50%, 30% and 20%, and the offending topic with the maximum probability value of 50% is taken as the offending topic of the category. Of course, a certain threshold may be set, and when a probability value greater than a specified threshold exists in the category, a violation topic corresponding to the probability value greater than the threshold is defined as the topic of the category.
Based on the same idea, the embodiment of the present invention further provides an information recommendation device, as shown in fig. 4, including:
an acquisition module 41 that acquires service statistics of a service provider;
a category determination module 42 that determines a category of the service provider based on the service statistics;
the topic determination module 43 determines a service information topic corresponding to an established service provider class according to the corresponding relation between the class and the service information topic;
and the recommending module 44 recommends the service information corresponding to the service information theme to the service provider.
Further, the service statistics acquired by the acquisition module 41 are weighted results of the service data of at least one dimension.
Further, the service data of the at least one dimension includes: at least one of transaction data within at least one preset time period, the number of violations occurring within at least one preset time period, and the total duration of service.
Further, for the transaction data in the at least one preset time period, the weight corresponding to the transaction data in the first preset time period is larger than the weight corresponding to the transaction data in the second preset time period, wherein the first preset time period is closer to the current time relative to the second preset time period.
Further, for the number of times of the offence occurring in the at least one preset time period, a weight corresponding to the number of times of the offence occurring in a first preset time period is larger than a weight corresponding to the number of times of the offence occurring in a second preset time period, wherein, with respect to the second preset time period, the first preset time period is closer to the current time.
Further, the weight coefficient of the total service duration is one.
Further, the category determining module is used for inputting the service statistical data into a trained cluster model;
and obtaining the category output by the clustering model.
Further, the training module 45 acquires service statistics data of a plurality of service providers as training samples; and training the clustering model according to the training samples to obtain the categories corresponding to the service providers.
Further, the service statistics data comprise illegal behavior data;
the topic determination module 43 is configured to determine a set of service providers that are configured of service providers corresponding to a same category;
and determining each violation topic corresponding to the same category and the violation probability of each violation topic according to the violation data of each service provider in the service provider set.
Further, the topic determination module is configured to determine, according to the violation probability of each violation topic corresponding to the category, from each violation topic corresponding to the category, a violation topic whose violation probability meets a preset requirement as the service information topic.
Further, the service information includes: at least one of laws and regulations and platform rules.
And further recommending laws and regulations and/or platform rules which are obtained through query screening and correspond to the offence theme to the service provider.
The apparatus shown in fig. 4 may perform the method of the embodiment shown in fig. 2, and reference is made to the relevant description of the embodiment shown in fig. 2 for parts of this embodiment not described in detail. The implementation process and the technical effect of this technical solution are described in the embodiment shown in fig. 2, and are not described herein.
In one possible design, the structure of the information recommendation apparatus shown in fig. 4 may be implemented as an electronic device, as shown in fig. 5, which may include: a first processor 51, a first memory 52, a first communication interface 53. The first memory 52 is used for storing a program for supporting the electronic device to execute the information presenting method provided in the embodiment shown in fig. 2, and the first processor 41 is configured to execute the program stored in the first memory 52.
The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the first processor 51, are capable of performing the steps of:
acquiring, by the first processor 51, service statistics of the service provider;
determining, by the first processor 51, a category of the service provider from the service statistics;
determining, by the first processor 51, a service information topic corresponding to an established service provider category according to the correspondence between the category and the service information topic;
the first communication interface 53 recommends service information corresponding to the service information theme to the service provider.
In addition, an embodiment of the present invention provides a computer storage medium, which is used for computer software instructions used by the first user terminal, and includes a program for executing the information recommendation method in the embodiment of the method shown in fig. 2.
Based on the same thought, the embodiment of the invention also provides a data processing method, which comprises the following steps: acquiring service statistics data of an account, wherein the service statistics data comprise violation times;
determining a category corresponding to the account according to the service statistics data;
obtaining push information corresponding to the category, wherein the push information comprises configuration parameters which are suitable for changing an interactive interface of a client where the account is located;
And sending the push information to the client.
The configuration parameters herein include: interactive interface presentation (e.g., animation presentation, text presentation), interactive interface presentation picture style (e.g., ink-wash style), and so forth. The configuration parameters can be determined according to the corresponding category of the account, or can be set by the user according to the user demand. Therefore, the obtained interaction interfaces can be in one-to-one correspondence with the accounts and can also be in one-to-one correspondence with the categories of the accounts.
For example, assuming that the most frequent violation topic of merchant a is a pirate graph violation, it may be determined that the type of violation of merchant a is a pirate graph violation, and the corresponding legal rules and platform rules pushed for merchant a are topics related to the pirate graph. Because of different offence subjects of various merchants, the clicking frequencies of various merchants in the same category aiming at different types of learning content are different, and the clicking frequencies of the interactive interfaces in different styles are different; therefore, in order to more accurately recommend corresponding legal learning data according to the category of the merchant and improve the learning efficiency of the merchant, relevant configuration parameters need to be recommended according to relevant information such as the category of the merchant, clicking frequency and the like, so that a corresponding interaction interface is displayed for the merchant.
Based on the same thought, the embodiment of the invention also provides a data processing method, which comprises the following steps:
the client side where the account is located receives push information from a server, wherein the push information corresponds to the category of the account;
the client side where the account is located obtains configuration parameters based on the push information;
and the client where the account is located changes the interactive interface based on the configuration parameters.
For example, as shown in fig. 6, two kinds of interaction interface schematic diagrams provided in the embodiment of the present invention include: the first account corresponds to the violation subject of the A category, and the second account corresponds to the violation subject of the B category; as can be seen from the figure, the content of the displayed interactive interface and the display style are different. The obtained configuration parameters are different according to different categories of accounts; further, based on different configuration parameters, different interactive interfaces can be obtained; it is easy to understand that different interactive interfaces described herein include different display contents and different display styles.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by adding necessary general purpose hardware platforms, or may be implemented by a combination of hardware and software. Based on such understanding, the foregoing aspects, in essence and portions contributing to the art, may be embodied in the form of a computer program product, which may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable resource updating apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable resource updating apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable resource updating device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable resource updating apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (14)
1. An information recommendation method, the method comprising:
acquiring service statistics data of a service provider;
determining a category of the service provider according to the service statistics;
determining a service information theme corresponding to the category according to the established corresponding relation between the service provider category and the service information theme;
recommending the service information corresponding to the service information theme to the service provider;
wherein, the determining the service information theme corresponding to the category according to the established correspondence between the service provider category and the service information theme comprises: according to the violation probability of each violation topic corresponding to the category, determining the violation topic with the violation probability meeting the preset requirement from each violation topic corresponding to the category as the service information topic;
the violation probability of each violation topic corresponding to the same category is determined by adopting the following mode: and determining a service provider set formed by service providers corresponding to the same category, and determining each offence theme corresponding to the same category and the offence probability of each offence theme according to offence behavior data of each service provider in the service provider set.
2. The method of claim 1, wherein the service statistics are weighted results of service data of at least one dimension.
3. The method of claim 2, wherein the service data of the at least one dimension comprises: at least one of transaction data within at least one preset time period, the number of violations occurring within at least one preset time period, and the total duration of service.
4. A method according to claim 3, wherein for transaction data within the at least one predetermined time period, the transaction data within a first predetermined time period corresponds to a greater weight than the transaction data within a second predetermined time period, wherein the first predetermined time period is closer to the current time than the second predetermined time period.
5. The method of claim 3, wherein for the number of violations occurring within the at least one preset time period, the number of violations occurring within a first preset time period corresponds to a greater weight than the number of violations occurring within a second preset time period, wherein the first preset time period is closer to a current time than the second preset time period.
6. A method according to claim 3, wherein the weight coefficient of the total duration of service is one.
7. The method according to any one of claims 1 to 6, wherein said determining a category of the service provider from the service statistics comprises:
inputting the service statistical data into a trained cluster model;
and obtaining the category output by the clustering model.
8. The method of claim 7, wherein the method further comprises:
acquiring service statistical data of a plurality of service providers as training samples;
and training the clustering model according to the training samples to obtain the categories corresponding to the service providers.
9. The method of claim 8, wherein the method further comprises:
determining a set of service providers consisting of service providers corresponding to the same category;
and determining each violation topic corresponding to the same category and the violation probability of each violation topic according to the violation data of each service provider in the service provider set.
10. The method of claim 9, wherein the service information comprises: at least one of laws and regulations and platform rules.
11. The method of claim 10, wherein recommending the service information corresponding to the service information topic to the service provider comprises:
and recommending laws and regulations and/or platform rules which are obtained through query screening and correspond to the offence theme to the service provider.
12. An information recommendation device, characterized in that the device comprises:
the acquisition module is used for acquiring service statistics data of the service provider;
a category determining module, configured to determine a category of the service provider according to the service statistics data;
the topic determination module is used for determining the service information topic corresponding to the class according to the established corresponding relation between the class of the service provider and the service information topic;
the recommending module is used for recommending the service information corresponding to the service information theme to the service provider;
the topic determination module is specifically configured to determine, according to the violation probability of each violation topic corresponding to the category, from each violation topic corresponding to the category, a violation topic whose violation probability meets a preset requirement as the service information topic;
the violation probability of each violation topic corresponding to the same category is determined by adopting the following mode: and determining a service provider set formed by service providers corresponding to the same category, and determining each offence theme corresponding to the same category and the offence probability of each offence theme according to offence behavior data of each service provider in the service provider set.
13. A method of data processing, comprising:
acquiring service statistics data of an account, wherein the service statistics data comprise violation times;
determining a category corresponding to the account according to the service statistics data;
obtaining push information corresponding to the category, wherein the push information comprises configuration parameters and service information corresponding to a violation topic corresponding to the category, and the configuration parameters are suitable for changing an interactive interface of a client where the account is located;
sending the push information to the client;
the information service subject corresponding to the category is determined by adopting the following mode: according to the violation probability of each violation topic corresponding to the category, determining the violation topic with the violation probability meeting the preset requirement from each violation topic corresponding to the category as the service information topic;
the violation probability of each violation topic corresponding to the same category is determined by adopting the following mode: and determining a service provider set formed by service providers corresponding to the same category, and determining each offence theme corresponding to the same category and the offence probability of each offence theme according to offence behavior data of each service provider in the service provider set.
14. A method of data processing, comprising:
the client where the account is located receives push information from a server, wherein the push information corresponds to the category of the account, the push information comprises configuration parameters and service information corresponding to a violation subject corresponding to the category, and the configuration parameters are suitable for changing an interactive interface of the client where the account is located;
the client side where the account is located obtains the configuration parameters and the service information based on the push information;
the client where the account is located changes an interactive interface based on the configuration parameters and the service information;
the information service subject corresponding to the category is determined by adopting the following mode: according to the violation probability of each violation topic corresponding to the category, determining the violation topic with the violation probability meeting the preset requirement from each violation topic corresponding to the category as the service information topic;
the violation probability of each violation topic corresponding to the same category is determined by adopting the following mode: and determining a service provider set formed by service providers corresponding to the same category, and determining each offence theme corresponding to the same category and the offence probability of each offence theme according to offence behavior data of each service provider in the service provider set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811124322.1A CN110955823B (en) | 2018-09-26 | 2018-09-26 | Information recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811124322.1A CN110955823B (en) | 2018-09-26 | 2018-09-26 | Information recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110955823A CN110955823A (en) | 2020-04-03 |
| CN110955823B true CN110955823B (en) | 2023-04-25 |
Family
ID=69964453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811124322.1A Active CN110955823B (en) | 2018-09-26 | 2018-09-26 | Information recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110955823B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102282593A (en) * | 2008-10-24 | 2011-12-14 | Uc集团有限公司 | Systems and methods for processing transactions with online merchants |
| CN106296205A (en) * | 2015-05-14 | 2017-01-04 | 大连智慧岛知识产权有限公司 | Patent and the e-commerce system of legal services is provided based on the Internet |
| CN106708858A (en) * | 2015-11-13 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| CN107742430A (en) * | 2017-11-08 | 2018-02-27 | 广东翼卡车联网服务有限公司 | A kind of driving behavior monitoring method, storage medium and car-mounted terminal |
| CN107742217A (en) * | 2017-09-07 | 2018-02-27 | 阿里巴巴集团控股有限公司 | Service control method and device based on businessman |
| WO2018036272A1 (en) * | 2016-08-22 | 2018-03-01 | 上海壹账通金融科技有限公司 | News content pushing method, electronic device, and computer readable storage medium |
| CN107818336A (en) * | 2017-10-09 | 2018-03-20 | 中国电子科技集团公司第二十八研究所 | Method and system are recommended in a kind of matching based on city specific crowd and the policy that associates |
| CN107885796A (en) * | 2017-10-27 | 2018-04-06 | 阿里巴巴集团控股有限公司 | Information recommendation method and device, equipment |
| CN108198051A (en) * | 2018-03-01 | 2018-06-22 | 口碑(上海)信息技术有限公司 | Across the Method of Commodity Recommendation and device of merchandise classification |
| CN108268655A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | A kind of government subsidy service push method and system based on big data |
-
2018
- 2018-09-26 CN CN201811124322.1A patent/CN110955823B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102282593A (en) * | 2008-10-24 | 2011-12-14 | Uc集团有限公司 | Systems and methods for processing transactions with online merchants |
| CN106296205A (en) * | 2015-05-14 | 2017-01-04 | 大连智慧岛知识产权有限公司 | Patent and the e-commerce system of legal services is provided based on the Internet |
| CN106708858A (en) * | 2015-11-13 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| WO2018036272A1 (en) * | 2016-08-22 | 2018-03-01 | 上海壹账通金融科技有限公司 | News content pushing method, electronic device, and computer readable storage medium |
| CN107742217A (en) * | 2017-09-07 | 2018-02-27 | 阿里巴巴集团控股有限公司 | Service control method and device based on businessman |
| CN107818336A (en) * | 2017-10-09 | 2018-03-20 | 中国电子科技集团公司第二十八研究所 | Method and system are recommended in a kind of matching based on city specific crowd and the policy that associates |
| CN107885796A (en) * | 2017-10-27 | 2018-04-06 | 阿里巴巴集团控股有限公司 | Information recommendation method and device, equipment |
| CN107742430A (en) * | 2017-11-08 | 2018-02-27 | 广东翼卡车联网服务有限公司 | A kind of driving behavior monitoring method, storage medium and car-mounted terminal |
| CN108268655A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | A kind of government subsidy service push method and system based on big data |
| CN108198051A (en) * | 2018-03-01 | 2018-06-22 | 口碑(上海)信息技术有限公司 | Across the Method of Commodity Recommendation and device of merchandise classification |
Non-Patent Citations (1)
| Title |
|---|
| 孙雨生 ; 张晨 ; 任洁 ; 朱礼军 ; .国内电子商务个性化推荐研究进展:架构与实践.现代情报.2017,(05),153-158. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110955823A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657138B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| CN108521439B (en) | Message pushing method and device | |
| CN107908740B (en) | Information output method and device | |
| US8374983B1 (en) | Distributed object classification | |
| CN110503206A (en) | A kind of prediction model update method, device, equipment and readable medium | |
| CN106940705A (en) | A kind of method and apparatus for being used to build user's portrait | |
| US20160285672A1 (en) | Method and system for processing network media information | |
| CN107153656B (en) | Information searching method and device | |
| CN108885624A (en) | Information recommendation system and method | |
| CN108777701A (en) | A kind of method and device of determining receiver | |
| CN110880127B (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN107247728B (en) | Text processing method and device and computer storage medium | |
| CN113424207B (en) | System and method for efficiently training understandable models | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN112328889A (en) | Method and device for determining recommended search terms, readable medium and electronic equipment | |
| CN110717788A (en) | Target user screening method and device | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| US20230316106A1 (en) | Method and apparatus for training content recommendation model, device, and storage medium | |
| de Lima et al. | Temporal dynamics of requirements engineering from mobile app reviews | |
| CN116843376A (en) | Marketing effect prejudging method, marketing effect prejudging device, storage medium and marketing effect prejudging equipment | |
| CN114595323B (en) | Portrait construction, recommendation, model training method, apparatus, device and storage medium | |
| CN110955823B (en) | Information recommendation method and device | |
| CN108154377B (en) | Advertisement cheating prediction method and device | |
| WO2015179717A1 (en) | Determination of initial value for automated delivery of news items | |
| US11379929B2 (en) | Advice engine |
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 |