CN111143546A - Method and device for obtaining recommendation language and electronic equipment - Google Patents
Method and device for obtaining recommendation language and electronic equipment Download PDFInfo
- Publication number
- CN111143546A CN111143546A CN201911120544.0A CN201911120544A CN111143546A CN 111143546 A CN111143546 A CN 111143546A CN 201911120544 A CN201911120544 A CN 201911120544A CN 111143546 A CN111143546 A CN 111143546A
- Authority
- CN
- China
- Prior art keywords
- field
- attribute information
- recommended
- split
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 abstract description 15
- 238000010586 diagram Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 4
- 230000006798 recombination Effects 0.000 description 3
- 238000005215 recombination Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008521 reorganization Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Abstract
The embodiment of the application provides a method for obtaining a recommended word, which is applied to a server or a client, and comprises the following steps: obtaining original data, wherein the original data comprises at least one of user image data, target object characteristic data and entity object characteristic data, the entity object characteristic data is used for describing the characteristics of an entity object providing service for a user, and the target object characteristic data is used for describing the characteristics of a target object used by the user; splitting the original data according to the field attribute to obtain a split field; and recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object. By adopting the recommended language obtained by the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved by obtaining the recommended language for the target object or the entity object.
Description
Technical Field
The application relates to the technical field of computers, in particular to a method and a device for obtaining a recommendation and an electronic device.
Background
With the rapid development of science and technology, the living material level is continuously improved, and with the development, the user has more and more demands on object selection or service selection. Since there are more and more physical objects and various kinds of objects or services that can provide the objects or services at present, a user must select an object or a physical object when selecting the object or the service. Therefore, how to form a recommendation for a target object or an entity object among a plurality of objects or entity objects becomes a key for matching the target object or the entity object to the user.
In order to solve the above problems, a recommendation for a target object or an entity object is mainly formed and presented to a user in the following ways. For example, the recommended language is manually filled in or the recommended language of the entity object is imported in a manual import mode; or directly recommending the evaluation words of the user to the target object or the entity object to the user as recommendation words for the target object or the entity object. Some entity objects can also form a recommendation language by directly counting historical behavior data of a certain user, for example, a certain user directly recommends aiming at the historical behavior data of the entity object or the target object in a certain period of time according to the statistics. However, since the recommended language is directly recommended to the public user as the recommended language by using some collected user behavior data, the degree of association between the historical behavior data and the public user is not high, so that when the public user browses the recommended language, the accuracy of the recommended language is not high due to the single recommended sentence.
Disclosure of Invention
The embodiment of the application provides a method for obtaining a recommended word, and aims to solve the problem that the existing recommended word is not high in accuracy.
In a first aspect, an embodiment of the present application provides a method for obtaining a recommendation, which is applied to a server or a client, where the method includes:
obtaining raw data, wherein the raw data comprises at least one of user image data, target object feature data and entity object feature data, the entity object feature data is used for describing features of entity objects for providing services for users, and the target object feature data is used for describing features of target objects for users to use; splitting the original data according to the field attribute to obtain a split field; and recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object.
Optionally, the splitting the original data according to the field attribute to obtain a split field includes: splitting the original data to obtain an initial splitting field; and matching the attribute information of the initial splitting field with preset field attribute information to obtain an initial splitting field matched with the preset field attribute information, and determining the initial splitting field matched with the preset field attribute information as a split field.
Optionally, the obtaining the initial split field matched with the preset field attribute information includes: obtaining an initial splitting field with the same attribute information as the preset field attribute information, or obtaining an initial splitting field with attribute information similarity meeting a preset similarity condition; the attribute information similarity refers to the similarity between the attribute information of the initial split field and the attribute information of the preset field attribute information.
Optionally, the split field has an association relationship with at least one object of a user object, a target object, and an entity object in the original data.
Optionally, the method further includes: extracting at least one of a user object, a target object and an entity object from the original data; determining at least one object of the extracted user object, the target object and the entity object to which the split field belongs; and associating the split field with at least one object of the extracted user object, the target object and the entity object to which the split field belongs to generate the association relation.
Optionally, the recombining the split fields according to the attribute of the recommended language includes: extracting at least one object of a user object, a target object and an entity object to which the split field belongs from the split field; traversing the split field to obtain the split field having an incidence relation with the at least one object; and recombining the at least one object and the split fields with the incidence relation according to the matching degree of the preset attribute information of the recommended words and the attribute information of the at least one object.
Optionally, the recombining the split fields according to the attribute of the recommended language includes: traversing the split field to obtain the split field matched with preset attribute information of the recommended words; and recombining the initial splitting field matched with the preset attribute information of the recommended words.
Optionally, the recombining the split fields according to the attribute of the recommended language includes: acquiring preset attribute information of a recommended word; and obtaining an initial splitting field associated with the preset attribute information of the recommended language, and recombining the initial splitting field associated with the preset attribute information of the recommended language.
Optionally, the recombining the split fields according to the attribute of the recommended language to obtain the recommended language for the target object or the entity object includes: recombining the split fields to obtain an initial recommendation; and matching the attribute information of the initial recommended language with preset recommended language attribute information to obtain the initial recommended language matched with the preset recommended language attribute information, and determining the initial recommended language matched with the preset recommended language attribute information as the recommended language for the target object or the entity object.
Optionally, the obtaining of the initial recommended language matched with the preset recommended language attribute information includes: obtaining an initial recommended word with the same attribute information as the preset recommended word attribute information, or obtaining an initial recommended word with attribute information similarity meeting a preset similarity condition; the attribute information similarity refers to the attribute information similarity between the attribute information of the initial recommended language and the preset attribute information of the recommended language.
Optionally, the method further includes: and carrying out priority ordering on the recommenders aiming at the target object or the entity object according to the recommenders attributes.
Optionally, the prioritizing the recommendation for the target object or the entity object according to the recommendation attribute includes: acquiring the priority of the preset attribute of the recommended word; obtaining attribute information of the recommended language for the target object or the entity object; and matching the attribute information of the recommended words for the target object or the entity object with the preset recommended word attributes to obtain the priority sequence of the recommended words for the target object or the entity object.
Optionally, if the method is applied to a server, the method further includes: providing the recommended words for the target object or the entity object to a client.
Optionally, if the method is applied to a server, the method further includes: and providing the recommended words to the client according to the priority of the recommended words.
Optionally, the method further includes: judging whether a numerical field in the recommended language meets a preset threshold value or not; the providing the recommendation for the target object or the entity object to a client comprises: and if the preset threshold value is met, providing the recommended words to the client.
Optionally, the method further includes: and obtaining a request message sent by the client for requesting to obtain the recommendation language aiming at the target object or the entity object.
Optionally, if the method is applied to a client, the method further includes: and displaying the recommended words aiming at the target object or the entity object.
Optionally, the presenting the recommended language for the target object or the entity object includes: and displaying the recommended words aiming at the target object or the entity object according to the priority of the recommended words.
Optionally, the method further includes: judging whether a numerical field in the recommended language meets a preset threshold value or not; the presenting the recommendation for the target object or the entity object includes: and if the preset threshold value is met, displaying the recommended words aiming at the target object or the entity object.
Optionally, the user representation data is used to describe a user characteristic associated with the target object or the entity object.
Optionally, the field attribute includes at least one of the following attribute information: user object field attribute information; target object field attribute information; entity object field attribute information; verb field attribute information; numerical field attribute information; resource field attribute information.
Optionally, the attribute of the recommended word includes at least one of the following attribute information: recommendation language attribute information associated with the user; recommendation language attribute information associated with the target object or the entity object by the plurality of users; recommendation attribute information associated with the target object or the entity object; and recommending language attribute information associated with the resource provided by the entity object.
In a second aspect, an embodiment of the present application provides an apparatus for obtaining a recommended language, which is applied to a server or a client, where the apparatus includes:
the system comprises an original data acquisition unit, a data acquisition unit and a data acquisition unit, wherein the original data comprises at least one of user image data, target object characteristic data and entity object characteristic data, the entity object characteristic data is used for describing the characteristics of an entity object providing service for a user, and the target object characteristic data is used for describing the characteristics of a target object used by the user; the splitting unit is used for splitting the original data according to the field attribute to obtain a split field; and the recommended word obtaining unit is used for recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object.
In a third aspect, an embodiment of the present application provides an electronic device, which is applied to a server or a client, where the electronic device includes: a processor; the memory is used for storing a computer program, and the computer program is executed by the processor and executes the method for obtaining the recommended language provided by the embodiment of the application.
In a fourth aspect, an embodiment of the present application provides a computer storage medium, which is applied to a server or a client, where the computer storage medium stores a computer program, and the computer program is executed by a processor to execute the method for obtaining a recommended word provided in the embodiment of the present application.
Compared with the prior art, the embodiment of the application has the following advantages:
the embodiment of the application provides a method for obtaining a recommended word, which is applied to a server or a client, and comprises the following steps: obtaining raw data, wherein the raw data comprises at least one of user image data, target object feature data and entity object feature data, the entity object feature data is used for describing features of entity objects for providing services for users, and the target object feature data is used for describing features of target objects for users to use; splitting the original data according to the field attribute to obtain a split field; and recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object. By adopting the recommended language obtained by the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved for the obtained recommended language for the target object or the entity object.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart of a method for obtaining a recommended word according to an embodiment of the present application.
Fig. 1-a is a schematic view of an application scenario of the method for obtaining a recommended word provided by the present application.
Fig. 1-B is a schematic view of a second application scenario of the method for obtaining a recommended word provided by the present application.
Fig. 1-C is a schematic diagram of a third application scenario of the method for obtaining a recommended word provided by the present application.
Fig. 2 is a schematic diagram of an apparatus for obtaining a recommended word according to a second embodiment of the present application.
Fig. 3 is a schematic view of an electronic device for obtaining a recommendation according to a third embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
Some embodiments provided by the application can be applied to a server or a client. The description will be given by taking a scenario applied to interaction among the client, the server, and the user as an example. As shown in fig. 1-a, which is a schematic diagram of an embodiment of an application scenario provided in the present application.
The embodiment firstly provides original data at a server; the raw data includes at least one of user portrait data, target object feature data, and entity object feature data, that is, the raw data may be any one of the user portrait data, the target object feature data, and the entity object feature data, or may be a combination of any two or more of them. The entity object feature data is used for describing features of an entity object providing services for a user, the target object feature data is used for describing features of a target object used by the user, and the user portrait data is used for describing features of the user associated with the target object or the entity object.
In this scenario embodiment, the entity object may be a merchant that provides services to the user. Correspondingly, the entity object feature data may be merchant feature data, where the merchant feature data is used to describe features of merchants providing services for the user, and may be feature data of the merchants themselves, for example, the feature data may refer to a business circle where a certain merchant is located, or may refer to the number of times that a merchant is collected by the user or the number of times that the merchant is browsed. The target object may be a commodity provided by a merchant for a user, and correspondingly, the target object feature data is used to describe features of the target object for the user, and may be feature data of the commodity itself, for example, the number of times a certain commodity is purchased, or the number of new days on the commodity. The user representation data is used for describing user characteristics associated with the target object or the entity object, and specifically, the user representation data may refer to a history record related to a certain user for a certain merchant, or may also refer to a history record related to a certain user for a certain commodity. For example, user A browses merchant M, or user A purchases item N. Of course, the user image data may be a history of a plurality of users with respect to a certain merchant or a history of a plurality of users with respect to a certain product.
After receiving the original data, the server may obtain the recommended language for the target object or the entity object according to a request message sent by the client to request to obtain the recommended language for the target object or the entity object. Of course, the client may also send a request message for requesting to obtain the recommended language for the target object or the entity object to the server, and the server receives the request message and obtains the original data according to the request message. And then obtaining a recommended word aiming at the target object or the entity object according to the original data.
In this embodiment, obtaining a recommendation for the target object or the entity object may refer to obtaining a recommendation for a commodity or a merchant. The specific process of obtaining the recommendation is described by taking the example of obtaining the recommendation for the commodity: after the original data are obtained, the original data are split according to the field attributes, and split fields are obtained. Specifically, the original data may be original data of the user a for a plurality of commodities, and the original data of the user a for the plurality of commodities may be split into fields according to the field attributes, for example, the original data corresponding to "five times for a single commodity N under the user a" may be split into four fields of "four times for the user a", "five times for a single commodity N under the user a". In this embodiment, the field attribute includes at least one of the following attribute information: user object field attribute information; target object field attribute information; entity object field attribute information; verb field attribute information; numerical field attribute information; resource field attribute information. Obviously, the raw data "N times per commodity under user a" includes: the user object field "user a", the target object field "commodity N", the verb field "place a order", and the numerical field "five times". Therefore, the original data of 'user A places an order for commodity N five times' can be divided into 'user A', 'place an order', 'commodity N', 'five times' four fields.
And then, recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the commodity N. The attribute of the recommended word comprises at least one of the following attribute information: recommendation language attribute information associated with the user; recommendation language attribute information associated with the target object or the entity object by the plurality of users; recommendation attribute information associated with the target object or the entity object; and recommending language attribute information associated with the resource provided by the entity object. According to the above recommended word attribute associated with the user a, the split fields may be recombined to form a recommended word "order N five times" or a recommended word "order N five times" for the user a.
Of course, the above listed way of splitting the field is only to split the original data which can be used as the recommended language, and when the original data is actually split, the obtained original data may be a large amount of original data which is not suitable for being used as the recommended language. However, the recommendation "user a places an order for N items N five times" or "places an order for N items N five times" cannot be directly recommended to user B, mainly because the recommendation is unrelated to user B. Therefore, for the user B, the recommended word for the commodity N needs to be obtained again, and if the user B does not place the order of the commodity N but browses the commodity N, the recommended word can be obtained by using the data of the commodity N browsed by the user B as the original data.
For the way of obtaining the recommended language, please refer to the above-described way of splitting the field of the original data according to the field attribute, and then recombining the split field according to the recommended language attribute to obtain the recommended language for the target object or the entity object. By adopting the method for obtaining the recommended language in the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language, and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved for the obtained recommended language for the target object or the entity object. It should be noted that the application scenario is only one embodiment of the application scenario, and the embodiment of the application scenario is provided to facilitate understanding of the method for obtaining a recommendation of the present application, and is not used to limit the method for obtaining a recommendation of the present application.
The application provides a method, a device, electronic equipment and a computer storage medium for obtaining a recommendation.
The following are specific examples.
Fig. 1 is a flowchart illustrating a method for obtaining a recommended phrase according to a first embodiment of the present application. The method comprises the following steps.
Step S101: the method comprises the steps of obtaining raw data, wherein the raw data comprises at least one of user image data, target object feature data and entity object feature data, the entity object feature data is used for describing features of entity objects for providing services for users, and the target object feature data is used for describing features of target objects for users to use.
To obtain a recommendation for a target object or an entity object, raw data is first obtained. The raw data includes at least one of user portrait data, target object feature data, and entity object feature data, that is, the raw data may be any one of the user portrait data, the target object feature data, and the entity object feature data, or may be a combination of any two or more of them.
In this embodiment, the entity object may be a merchant that provides services to the user. Correspondingly, the entity object feature data may be merchant feature data, where the merchant feature data is used to describe features of merchants providing services for the user, and may be feature data of the merchants themselves, for example, the feature data may refer to a business circle where a certain merchant is located, or may refer to the number of times that a merchant is collected by the user or the number of times that the merchant is browsed. The target object may be a commodity provided by a merchant for a user, and correspondingly, the target object feature data is used to describe features of the target object for the user, and may be feature data of the commodity itself, for example, the number of times a certain commodity is purchased, or the number of new days on the commodity. The user representation data is used to describe a user characteristic associated with the target object or the physical object. Specifically, the user representation data may refer to a history of a user's relevance to a merchant, or may refer to a history of a user's relevance to a product. For example, user A browses merchant M, or user A purchases item N. Of course, the user image data may be a history of a plurality of users with respect to a certain merchant or a history of a plurality of users with respect to a certain product.
Step S102: and splitting the original data according to the field attribute to obtain a split field.
After the original data is obtained in step S101, the original data is split according to the field attribute, and a split field is obtained.
As one of the ways of splitting the original data according to the field attribute to obtain the split field, the following ways may be used.
Firstly, splitting original data to obtain an initial splitting field. And then, matching the attribute information of the initial split field with preset field attribute information to obtain the initial split field matched with the preset field attribute information, and determining the initial split field matched with the preset field attribute information as a split field.
Specifically, obtaining an initial split field matched with preset field attribute information may refer to obtaining an initial split field having the same attribute information as the preset field attribute information, or obtaining an initial split field whose attribute information similarity satisfies a preset similarity condition; the attribute information similarity refers to the similarity between the attribute information of the initial split field and the attribute information of the preset field attribute information.
After the obtained original data comprises at least one of user image data, target object characteristic data and entity object characteristic data, splitting the original data according to field attribute information to obtain split fields. In other words, the original data is essentially classified, that is, the original data is classified according to the preset field attribute information. More specifically, the preset field attribute includes at least one of user object field attribute information, target object field attribute information, entity object field attribute information, verb field attribute information, numerical value field attribute information, and resource field attribute information, and the original data is split into fields according to the preset field attribute, so as to obtain the split fields. For example, for the commodity N, the user a places an order for the commodity N five times, the user B browses the commodity N three times, and if the data of the user for the commodity N is used as the original data, the divided fields are "user a", "user B", "place an order", "browsed", "commodity N", "five times", and "three times". "user a" and "user B" belong to the user object field, "order placement" and "viewed" belong to the verb field, "commodity N" belongs to the target object, "five times" and "three times" belong to the numerical value field. For another example, the merchant M gives a five-membered red packet, and the divided fields are "merchant M", "give", "five-membered" and "red packet". "Merchant M" belongs to the entity object field, "gift" belongs to the verb field, "five-membered" belongs to the value field, and "Red envelope" belongs to the resource field.
In order to facilitate the recombination of the split fields in the subsequent process, the split fields and at least one of the user object, the target object and the entity object in the original data may be set to have an association relationship.
Specifically, setting the split field and at least one of the user object, the target object, and the entity object in the original data to have an association relationship may be performed in a manner as described below.
First, at least one of a user object, a target object, and an entity object is extracted from raw data. And then, determining at least one object of the extracted user object, the target object and the entity object to which the split field belongs. And finally, associating the split field with at least one object of the extracted user object, the target object and the entity object to which the split field belongs to generate an association relation.
For example, in the splitting process, the split fields "order", "commodity N", "five" are attributed to "user a", so that the association relationship between "order", "commodity N", "five" and "user a" is established. And attributing the split fields of browsed, commodity N and third time to a user B, so that the association relationship is established between the browsed, commodity N and third time and the user B. Or "user a", "user B", "placing an order", "browsing", "five times" and "three times" may also be attributed to "commodity N", so that "user a", "user B", "placing an order", "browsing", "five times" and "three times" establish an association with "commodity N". Similarly, for "merchant M", gifts "," quints ", and" red packets "may be attributed to" merchant M ", so that" gifts "," quints ", and" red packets "are associated with" merchant M ".
Step S103: and recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object.
After the split fields are obtained in step S102, the split fields are recombined according to the attribute of the recommended language, and the field combination after the split fields are recombined is used as the recommended language for the target object or the entity object.
As a way of recombining the split fields according to the recommender attribute, a way described below may be adopted.
Firstly, at least one object of a user object, a target object and an entity object to which the split field belongs is extracted from the split field. Since, in the splitting process of the original data in step S102, one of the ways of splitting may be to set the split field and at least one of the user object, the target object and the entity object in the original data to have an association relationship, the split field substantially belongs to at least one of the user object, the target object and the entity object. Therefore, when the split field is recombined, at least one of the user object, the target object and the entity object to which the split field belongs may be extracted first. And after at least one object to which the split field belongs is extracted, traversing the split field to obtain the split field which has an incidence relation with the at least one object. For example, all of the raw data described above includes: the user A puts a single commodity N times, the user B browses the commodity N times, and the merchant M gives a five-element red packet. Suppose the commodity of the merchant M is the commodity N; the user portrait data is that a user A puts a single commodity for N times, and a user B browses the commodity for N times; the merchant M gives a five-membered red envelope. In step S102, the fields obtained by splitting the original data are: "user a", "order placement", "commodity N", "five"; "user B", "viewed", "commodity N", "three times"; "Merchant M", "give away", "five-tuple", and "Red envelope". If the field of the user A is extracted, the fields of ordering, commodity N and quintic which have the association relation with the user A during splitting can be traversed in the traversing process. After the split field with the incidence relation with the at least one object is obtained, the at least one object and the split field with the incidence relation are recombined according to the preset matching degree of the attribute information of the recommendation language and the attribute information of the at least one object. Specifically, according to the matching degree of the preset attribute information of the recommendation language and the attribute information of the at least one object, the at least one object and the split field having the association relationship are recombined and described as follows.
In this embodiment, the attribute of the recommender includes at least one of the following attribute information: recommendation language attribute information associated with the user; recommendation language attribute information associated with the target object or the entity object by the plurality of users; recommendation attribute information associated with the target object or the entity object; and recommending language attribute information associated with the resource provided by the entity object.
Specifically, in the present embodiment, when generating the recommended word, the reorganized field combinations are actually classified. For example, the recommended word associated with the user may be a recommended word associated with "user a" or a recommended word associated with "user B". When the recommendation associated with the user A is obtained, the user A, the order placing, the commodity N and the fifth time are recombined to form the recommendation of the commodity N for placing the order five times. The recommended phrases of the plurality of users associated with the target object or the entity object may be recommended phrases associated with the "user a", "user B", and the "merchant M", or recommended phrases associated with the "user a", "user B", and the "commodity N". When obtaining the recommendation words associated with the user a, the user B and the merchant M, the user a, the order placing, the commodity N and the merchant M are processed; and recombining the user B, the browsed product N and the three times to form a recommendation language that the two users visit eight times.
More specifically, in forming the recommendation, the "user a", "user B" are combined with the "number of people" tab, the "viewed" tab is combined with the "visited" tab, and the "five times" tab is combined with the "three times" tab. In the reorganization, the finely divided fields in step S102 may be merged first, and reorganization may be performed on the basis of the merging. Correspondingly, in the process of splitting the field in step S102, splitting may also be performed initially, and then fine splitting is performed. The above recommendation associated with the resource provided by the entity object may refer to a recommendation associated with "red envelope". And when the recommendation associated with the merchant M is obtained, recombining the donation, the quintuple and the red packet to form the recommendation for placing the order and getting the quintuple red packet. In particular, "gifts" are for merchants, and correspondingly, for users, are essentially "earns". The recommended phrases associated with "red envelope" are, obviously, when directed to the user, the fields "place order" and "pick up". The above process is essentially to replace the semantics of the split fields during the recombination, so that the obtained recommendation is more associated with the user. Of course, the split field can also be directly recombined.
As another implementation for recombining the split field according to the attribute of the recommended phrase, the following may also be implemented: traversing the split fields to obtain split fields matched with preset attribute information of the recommended words; and recombining the initial splitting field matched with the preset attribute information of the recommended words.
For example, the aforementioned recommended language associated with the resource provided by the entity object may refer to a recommended language associated with "red envelope". Traversing all the split fields, obtaining split fields 'merchant M', 'gift', 'five-element' and 'red packet' matched with the recommended language associated with the 'red packet', and then recombining the obtained split fields to form the recommended language 'issuing order and getting five-element red packet'. In particular, "gifts" are for merchants, and correspondingly, for users, are essentially "earns". The recommended phrases associated with "red envelope" are, obviously, when directed to the user, the fields "place order" and "pick up". The above process is essentially to replace the semantics of the split fields during the recombination, so that the obtained recommendation is more associated with the user.
As a third implementation manner of recombining the split fields according to the attribute of the recommended phrase, the following may also be implemented: first, preset attribute information of a recommended word is obtained. And then, obtaining an initial splitting field associated with the preset attribute information of the recommended language, and recombining the initial splitting field associated with the preset attribute information of the recommended language. In the embodiment, a splitting field matched with preset attribute information of the recommended words is obtained from the traversed and split field; the embodiment of reorganizing the initial split field matched with the preset recommender attribute information is basically similar, except that the above embodiment obtains the split field matched with the preset recommender attribute information, and the embodiment obtains the initial split field associated with the preset recommender attribute information.
And recombining the split fields according to the attribute of the recommended language to obtain the recommended language for the target object or the entity object, wherein the method can be described as follows. Firstly, recombining the split fields to obtain an initial recommendation. And then, matching the attribute information of the initial recommended language with preset recommended language attribute information to obtain the initial recommended language matched with the preset recommended language attribute information, and determining the initial recommended language matched with the preset recommended language attribute information as the recommended language for the target object or the entity object.
Specifically, the split field may be recombined with at least one of the user object, the target object, and the entity object to which the field belongs, and the recombined field may be used as the initial recommendation. After the initial recommended language is obtained, matching degree calculation is carried out on the attribute information of the initial recommended language and the preset recommended language attribute information, the initial recommended language matched with the preset recommended language attribute information is obtained by comparing the set matching degree threshold value with the calculated matching degree, and the initial recommended language matched with the preset recommended language attribute information is determined as the recommended language for the target object or the entity object.
More specifically, the initial recommended language matched with the preset recommended language attribute information is obtained, which may be the initial recommended language having the same attribute information as the preset recommended language attribute information, or the initial recommended language having the attribute information similarity meeting the preset similarity condition; the attribute information similarity refers to the similarity between the attribute information of the initial recommended language and the attribute information of the preset recommended language attribute information.
After obtaining the recommenders for the target object or the entity object, in order to improve the accuracy of the recommenders in different scenes, the recommenders for the target object or the entity object are prioritized according to the recommenders attributes.
As an embodiment of prioritizing recommenders for a target object or an entity object according to a recommender attribute, first, a priority of a preset recommender attribute is obtained. After that, attribute information of the recommended word for the target object or the entity object is obtained. And finally, matching the attribute information of the recommended words aiming at the target object or the entity object with the preset attributes of the recommended words, thereby obtaining the priority sequence of the recommended words aiming at the target object or the entity object.
Among the above recommenders associated with users, recommenders associated with a plurality of users and a target object or an entity object, recommenders associated with a target object or an entity object, and recommenders associated with a resource provided by an entity object, the following recommenders may be arranged in order of priority: the recommendation language is associated with the resource provided by the entity object, the recommendation language is associated with the user, the recommendation languages of the plurality of users are associated with the target object or the entity object, and the recommendation language is associated with the target object or the entity object. For example, a recommendation "place order and receive five-membered red envelope" is arranged at the head, and the recommendation is related to all users. The recommendation language of "order placing N times" is arranged at the second position, the recommendation language of "two users visit eight times" is arranged at the third position, and the recommendation language related to the resource provided by the entity object is arranged at the fourth position.
It should be noted that, if the above method embodiment for obtaining a recommended language is applied to a server, after obtaining a recommended language for a target object or an entity object, a request message sent by a client for requesting to obtain the recommended language for the target object or the entity object is obtained. Thereafter, the recommendation for the target object or the entity object is provided to the client. Specifically, the recommendation may be provided to the client according to the priority of the recommendation described above.
More specifically, providing the recommendation to the client in accordance with the priority of the recommendation described above may be as follows. And judging whether the numerical field in the current recommended language meets a preset threshold value or not according to the priority of the recommended language, and if so, providing the recommended language to the client. For example, in the recommendation "get five-membered red envelope on order", the value field is five. And assuming that the preset threshold red packet value is more than three, if the value field of the current recommended word meets the preset threshold, providing the recommended word 'ordering and getting five-membered red packets' to the client. If the preset threshold red packet value is greater than six, the value field of the current recommendation language does not meet the preset threshold, and the recommendation language 'ordering and getting five-membered red packets' is not provided for the client. And continuously judging whether the numerical value field in the next recommended word meets a preset threshold value according to the priority of the recommended word. And if the preset threshold value is met, providing the recommendation language to the client. Otherwise, the recommendation language is not provided to the client.
If the method embodiment for obtaining the recommended language is applied to the client, the client can also display the recommended language for the target object or the entity object. Specifically, the recommendation for the target object or the entity object is presented according to the priority of the recommendation. Presenting the referral for the target object or the entity object according to the priority of the referral may be in the manner described below. And judging whether the numerical value field in the recommended language meets a preset threshold value, and if so, displaying the recommended language aiming at the target object or the entity object. For example, in the recommendation "get five-membered red envelope on order", the value field is five. And assuming that the preset threshold red packet value is more than three, the value field of the current recommended word meets the preset threshold, and showing that the recommended word is 'placed to receive the quinary red packet'. If the preset threshold red packet value is greater than six, the value field of the current recommended language does not meet the preset threshold, and the recommended language 'ordering and getting five-membered red packets' is not displayed. And judging whether the numerical value field in the next recommended word meets a preset threshold value according to the priority of the recommended word. And if the preset threshold value is met, displaying the recommended words. Otherwise, the recommendation language is not displayed.
As shown in fig. 1-B and fig. 1-C, a second application scenario diagram and a third application scenario diagram of the method for obtaining a recommended word provided by the present application are respectively shown. In FIG. 1-B, Merchant 1 is acting as the recommending store, and the referral is the "30-tuple Red envelope of the next available list" associated with the user; the merchant 2 is used as a new store, and the recommendation is a recommendation that a plurality of users are associated with target objects or entity objects, specifically a crowd endorsement recommendation "a red bar store collected by 35 people recently". In fig. 1-C, merchants 3-6 are the recommended stores, and the recommendations of merchant 3, merchant 4, and merchant 6 are the recommendations associated with the user, which are "consumed 3 times", "consumed the last 5 days", and "recently visited", respectively; the recommendation of the merchant 5 is a recommendation that a plurality of users are associated with target objects or entity objects, and is specifically a recommendation "eaten by 35 people recently" endorsed by a crowd.
According to the method and the device, the original data are obtained firstly, then the original data are split according to the field attributes, the split fields are obtained, finally the split fields are recombined according to the recommended language attributes, and the recommended language for the target object or the entity object is obtained. By adopting the recommended language obtained by the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved for the obtained recommended language for the target object or the entity object.
In the first embodiment described above, a method for obtaining a recommended word is provided, and correspondingly, the present application provides an apparatus for obtaining a recommended word. Fig. 2 is a schematic diagram of an apparatus for obtaining a recommended word according to a second embodiment of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
A second embodiment of the present application provides an apparatus for obtaining a recommended language, which is applied to a server or a client, and the apparatus includes:
a raw data obtaining unit 201, configured to obtain raw data, where the raw data includes at least one of user image data, target object feature data, and entity object feature data, where the entity object feature data is used to describe features of an entity object that provides a service for a user, and the target object feature data is used to describe features of a target object that is used by the user;
a splitting unit 202, configured to split the original data according to the field attribute, so as to obtain a split field;
and a recommended word obtaining unit 203, configured to recombine the split fields according to the attributes of the recommended words, and obtain recommended words for the target object or the entity object.
Optionally, the splitting unit is specifically configured to: splitting the original data to obtain an initial splitting field; and matching the attribute information of the initial splitting field with preset field attribute information to obtain an initial splitting field matched with the preset field attribute information, and determining the initial splitting field matched with the preset field attribute information as a split field.
Optionally, the splitting unit is specifically configured to: obtaining an initial splitting field with the same attribute information as the preset field attribute information, or obtaining an initial splitting field with attribute information similarity meeting a preset similarity condition; the attribute information similarity refers to the similarity between the attribute information of the initial split field and the attribute information of the preset field attribute information.
Optionally, the split field has an association relationship with at least one object of a user object, a target object, and an entity object in the original data.
Optionally, the method further includes: the extraction unit is used for determining the object and the incidence relation generation unit; the extraction unit is used for extracting at least one of a user object, a target object and an entity object from the original data; the object determining unit is configured to determine at least one object of the extracted user object, the target object, and the entity object to which the split field belongs; the association relationship generating unit is configured to associate the split field with at least one object of the extracted user object, the target object, and the entity object to which the split field belongs, and generate the association relationship.
Optionally, the recommendation obtaining unit is specifically configured to: extracting at least one object of a user object, a target object and an entity object to which the split field belongs from the split field; traversing the split field to obtain the split field having an incidence relation with the at least one object; and recombining the at least one object and the split fields with the incidence relation according to the matching degree of the preset attribute information of the recommended words and the attribute information of the at least one object.
Optionally, the recommendation obtaining unit is specifically configured to: traversing the split field to obtain the split field matched with preset attribute information of the recommended words; and recombining the initial splitting field matched with the preset attribute information of the recommended words.
Optionally, the recommendation obtaining unit is specifically configured to: acquiring preset attribute information of a recommended word; and obtaining an initial splitting field associated with the preset attribute information of the recommended language, and recombining the initial splitting field associated with the preset attribute information of the recommended language.
Optionally, the recommendation obtaining unit is specifically configured to: recombining the split fields to obtain an initial recommendation; and matching the attribute information of the initial recommended language with preset recommended language attribute information to obtain the initial recommended language matched with the preset recommended language attribute information, and determining the initial recommended language matched with the preset recommended language attribute information as the recommended language for the target object or the entity object.
Optionally, the recommendation obtaining unit is specifically configured to: obtaining an initial recommended word with the same attribute information as the preset recommended word attribute information, or obtaining an initial recommended word with attribute information similarity meeting a preset similarity condition; the attribute information similarity refers to the attribute information similarity between the attribute information of the initial recommended language and the preset attribute information of the recommended language.
Optionally, the method further includes a prioritization unit: and the priority ordering unit is used for carrying out priority ordering on the recommenders aiming at the target object or the entity object according to the recommenders attributes.
Optionally, the priority ranking unit is specifically configured to: acquiring the priority of the preset attribute of the recommended word; obtaining attribute information of the recommended language for the target object or the entity object; and matching the attribute information of the recommended words for the target object or the entity object with the preset recommended word attributes to obtain the priority sequence of the recommended words for the target object or the entity object.
Optionally, if the apparatus is applied to a server, the apparatus further includes: a first providing unit; the first providing unit is configured to provide the recommendation for the target object or the entity object to a client.
Optionally, if the apparatus is applied to a server, the apparatus further includes: a second providing unit; the second providing unit is used for providing the recommended words to the client according to the priority of the recommended words.
Optionally, the method further includes: a first judgment unit; the first judging unit is used for judging whether a numerical field in the recommended language meets a preset threshold value or not; the first providing unit is specifically configured to: and if the preset threshold value is met, providing the recommended words to the client.
Optionally, the method further includes: a request unit; the request unit is used for obtaining a request message sent by a client and used for requesting to obtain the recommendation language for the target object or the entity object.
Optionally, if the apparatus is applied to a client, the apparatus further includes: and the display unit is used for displaying the recommended words aiming at the target object or the entity object.
Optionally, the display unit is specifically configured to: and displaying the recommended words aiming at the target object or the entity object according to the priority of the recommended words.
Optionally, the method further includes: a second judgment unit; the second judging unit is configured to judge whether a numeric field in the recommended word meets a preset threshold; the display unit is specifically configured to: and if the preset threshold value is met, displaying the recommended words aiming at the target object or the entity object.
Optionally, the user representation data is used to describe a user characteristic associated with the target object or the entity object.
Optionally, the field attribute includes at least one of the following attribute information: user object field attribute information; target object field attribute information; entity object field attribute information; verb field attribute information; numerical field attribute information; resource field attribute information.
Optionally, the attribute of the recommended word includes at least one of the following attribute information: recommendation language attribute information associated with the user; recommendation language attribute information associated with the target object or the entity object by the plurality of users; recommendation attribute information associated with the target object or the entity object; and recommending language attribute information associated with the resource provided by the entity object.
According to the method and the device, the original data are obtained firstly, then the original data are split according to the field attributes, the split fields are obtained, finally the split fields are recombined according to the recommended language attributes, and the recommended language for the target object or the entity object is obtained. By adopting the recommended language obtained by the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved for the obtained recommended language for the target object or the entity object.
The first embodiment of the present application provides a method for obtaining a recommended word, and the third embodiment of the present application provides an electronic device corresponding to the method of the first embodiment.
As shown in fig. 3, it shows a schematic diagram of the electronic device for obtaining a recommended phrase provided by this embodiment.
The embodiment provides an electronic device, which is applied to a server or a client, and the electronic device includes:
a processor 301;
the memory 302 is used for storing a computer program, which is executed by the processor and executes the method for obtaining the recommended language provided in the first embodiment of the present application.
According to the method and the device, the original data are obtained firstly, then the original data are split according to the field attributes, the split fields are obtained, finally the split fields are recombined according to the recommended language attributes, and the recommended language for the target object or the entity object is obtained. By adopting the recommended language obtained by the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved for the obtained recommended language for the target object or the entity object.
A first embodiment of the present application provides a method for obtaining a recommended phrase, and a fourth embodiment of the present application provides a computer storage medium corresponding to the method of the first embodiment.
The present embodiment provides a computer storage medium, which is applied to a server or a client, where the computer storage medium stores a computer program, and the computer program is executed by a processor to execute the method for obtaining a recommended word provided in the first embodiment of the present application.
According to the method and the device, the original data are obtained firstly, then the original data are split according to the field attributes, the split fields are obtained, finally the split fields are recombined according to the recommended language attributes, and the recommended language for the target object or the entity object is obtained. By adopting the recommended language obtained by the embodiment, because the original data is split according to the field attribute in the process of obtaining the recommended language and the split field is recombined according to the attribute of the recommended language, the accuracy of the recommended language can be relatively improved for the obtained recommended language for the target object or the entity object.
Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
1. 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 computer storage media 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 that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include non-transitory computer-readable storage media (non-transitory computer readable storage media), such as modulated data signals and carrier waves.
2. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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, and the like) having computer-usable program code embodied therein.
Claims (10)
1. A method for obtaining a recommendation, which is applied to a server or a client, includes:
obtaining raw data, wherein the raw data comprises at least one of user image data, target object feature data and entity object feature data, the entity object feature data is used for describing features of entity objects for providing services for users, and the target object feature data is used for describing features of target objects for users to use;
splitting the original data according to the field attribute to obtain a split field;
and recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object.
2. The method according to claim 1, wherein the splitting the original data according to the field attribute to obtain a split field comprises:
splitting the original data to obtain an initial splitting field;
and matching the attribute information of the initial splitting field with preset field attribute information to obtain an initial splitting field matched with the preset field attribute information, and determining the initial splitting field matched with the preset field attribute information as a split field.
3. The method of claim 2, wherein the obtaining the initial split field matching the preset field attribute information comprises:
obtaining an initial splitting field with the same attribute information as the preset field attribute information, or obtaining an initial splitting field with attribute information similarity meeting a preset similarity condition; the attribute information similarity refers to the similarity between the attribute information of the initial split field and the attribute information of the preset field attribute information.
4. The method of claim 1, wherein the split field has an association relationship with at least one of a user object, a target object, and an entity object in the original data.
5. The method of claim 4, further comprising:
extracting at least one of a user object, a target object and an entity object from the original data;
determining at least one object of the extracted user object, the target object and the entity object to which the split field belongs;
and associating the split field with at least one object of the extracted user object, the target object and the entity object to which the split field belongs to generate the association relation.
6. The method of claim 1, wherein the reorganizing the split fields according to the recommender attributes comprises:
extracting at least one object of a user object, a target object and an entity object to which the split field belongs from the split field;
traversing the split field to obtain the split field having an incidence relation with the at least one object;
and recombining the at least one object and the split fields with the incidence relation according to the matching degree of the preset attribute information of the recommended words and the attribute information of the at least one object.
7. The method of claim 1, wherein the reorganizing the split fields according to the recommender attributes comprises:
traversing the split field to obtain the split field matched with preset attribute information of the recommended words;
and recombining the initial splitting field matched with the preset attribute information of the recommended words.
8. An apparatus for obtaining a recommended language, applied to a server or a client, the apparatus comprising:
the system comprises an original data acquisition unit, a data acquisition unit and a data acquisition unit, wherein the original data comprises at least one of user image data, target object characteristic data and entity object characteristic data, the entity object characteristic data is used for describing the characteristics of an entity object providing service for a user, and the target object characteristic data is used for describing the characteristics of a target object used by the user;
the splitting unit is used for splitting the original data according to the field attribute to obtain a split field;
and the recommended word obtaining unit is used for recombining the split fields according to the attributes of the recommended words to obtain the recommended words for the target object or the entity object.
9. An electronic device, applied to a server or a client, the electronic device comprising:
a processor;
a memory for storing a computer program for execution by the processor to perform the method of any one of claims 1 to 7.
10. A computer storage medium for a server or a client, the computer storage medium storing a computer program, the computer program being executed by a processor to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911120544.0A CN111143546A (en) | 2019-11-15 | 2019-11-15 | Method and device for obtaining recommendation language and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911120544.0A CN111143546A (en) | 2019-11-15 | 2019-11-15 | Method and device for obtaining recommendation language and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111143546A true CN111143546A (en) | 2020-05-12 |
Family
ID=70517173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911120544.0A Pending CN111143546A (en) | 2019-11-15 | 2019-11-15 | Method and device for obtaining recommendation language and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111143546A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113821514A (en) * | 2021-09-26 | 2021-12-21 | 维沃移动通信有限公司 | Data splitting method and device, electronic equipment and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150073931A1 (en) * | 2013-09-06 | 2015-03-12 | Microsoft Corporation | Feature selection for recommender systems |
| CN105677795A (en) * | 2015-12-31 | 2016-06-15 | 上海智臻智能网络科技股份有限公司 | Abstract semantics recommendation method, recommendation device and recommendation system |
| CN107958088A (en) * | 2017-12-15 | 2018-04-24 | 佛山市因诺威特科技有限公司 | A kind of WORDS AND PHRASES IN ADVERTISEMENT recommends method, storage medium and server |
| CN110060029A (en) * | 2019-04-18 | 2019-07-26 | 浩鲸云计算科技股份有限公司 | A kind of AI energizes creative design method |
| CN110110207A (en) * | 2018-01-18 | 2019-08-09 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and electronic equipment |
| CN110196972A (en) * | 2019-04-24 | 2019-09-03 | 北京奇艺世纪科技有限公司 | Official documents and correspondence generation method, device and computer readable storage medium |
| CN110264315A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Recommended information generation method and device |
-
2019
- 2019-11-15 CN CN201911120544.0A patent/CN111143546A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150073931A1 (en) * | 2013-09-06 | 2015-03-12 | Microsoft Corporation | Feature selection for recommender systems |
| CN105677795A (en) * | 2015-12-31 | 2016-06-15 | 上海智臻智能网络科技股份有限公司 | Abstract semantics recommendation method, recommendation device and recommendation system |
| CN107958088A (en) * | 2017-12-15 | 2018-04-24 | 佛山市因诺威特科技有限公司 | A kind of WORDS AND PHRASES IN ADVERTISEMENT recommends method, storage medium and server |
| CN110110207A (en) * | 2018-01-18 | 2019-08-09 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and electronic equipment |
| CN110060029A (en) * | 2019-04-18 | 2019-07-26 | 浩鲸云计算科技股份有限公司 | A kind of AI energizes creative design method |
| CN110196972A (en) * | 2019-04-24 | 2019-09-03 | 北京奇艺世纪科技有限公司 | Official documents and correspondence generation method, device and computer readable storage medium |
| CN110264315A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Recommended information generation method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113821514A (en) * | 2021-09-26 | 2021-12-21 | 维沃移动通信有限公司 | Data splitting method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10504120B2 (en) | Determining a temporary transaction limit | |
| JP5897019B2 (en) | Method and apparatus for determining linked list of candidate products | |
| US8983930B2 (en) | Facet group ranking for search results | |
| WO2019149145A1 (en) | Compliant report class sorting method and apparatus | |
| US20130297382A1 (en) | Network transaction platform and processing method thereof | |
| CN111160950B (en) | Resource information processing and outputting method and device | |
| US20180308152A1 (en) | Data Processing Method and Apparatus | |
| CN110413870A (en) | Method of Commodity Recommendation, device and server | |
| CN110392155B (en) | Notification message display and processing method, device and equipment | |
| CN108550046A (en) | A kind of resource and market recommendation method, apparatus and electronic equipment | |
| CN117271385A (en) | Garbage collection for data storage | |
| CN110175306A (en) | A kind of processing method and processing device of advertising information | |
| TW201828200A (en) | Data processing method and apparatus increasing the overall display efficiency of the object display environment and decreasing the waste of display resources of each object display environment | |
| CN110851712A (en) | Book information recommendation method and device and computer readable medium | |
| US10497039B1 (en) | Techniques for dynamic variations of a search query | |
| US20130304539A1 (en) | User recommendation method and device | |
| US9201967B1 (en) | Rule based product classification | |
| CN107515896A (en) | A kind of resource recommendation method, device and equipment | |
| CN110717788A (en) | Target user screening method and device | |
| CN111143546A (en) | Method and device for obtaining recommendation language and electronic equipment | |
| CN111177093A (en) | Method, device and medium for sharing scientific and technological resources | |
| CN110796505B (en) | Business object recommendation method and device | |
| US20180330419A1 (en) | Method and Apparatus of Providing Brand List Information | |
| CN108154377B (en) | Advertisement cheating prediction method and device | |
| CN106886546B (en) | Construction method and equipment of data website |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200512 |