CN111523007B - Method, device, equipment and storage medium for determining user interest information - Google Patents
Method, device, equipment and storage medium for determining user interest information Download PDFInfo
- Publication number
- CN111523007B CN111523007B CN202010345720.7A CN202010345720A CN111523007B CN 111523007 B CN111523007 B CN 111523007B CN 202010345720 A CN202010345720 A CN 202010345720A CN 111523007 B CN111523007 B CN 111523007B
- Authority
- CN
- China
- Prior art keywords
- scene
- user
- entity
- determining
- candidate
- 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 53
- 230000006399 behavior Effects 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 19
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method, a device, equipment and a storage medium for determining user interest information, which relate to the field of data processing, in particular to an artificial intelligence technology. The specific implementation scheme is as follows: acquiring scene characteristics from the knowledge graph according to scene information of a user; determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity; and determining target entities interested by the user from the candidate entities according to the interestingness. The embodiment of the application provides a method, a device, equipment and a storage medium for determining user interest information, which realize further mining of the user interest information, thereby improving the application value of the user interest information in intelligent information services such as intelligent search, intelligent question-answering, personalized recommendation and the like.
Description
Technical Field
Embodiments of the present application relate to the field of data processing, and in particular, to artificial intelligence techniques. Specifically, the embodiment of the application provides a method, a device, equipment and a storage medium for determining information of interest of a user.
Background
The information of interest to the user refers to information of interest to the user. The information of interest of the user is widely applied to intelligent information services such as intelligent search, intelligent question and answer, personalized recommendation and the like so as to improve the satisfaction degree of the user. How to further mine the information of interest to the user so that the information of interest to the user generates greater application value in the intelligent information service is a current problem.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a storage medium for determining user interest information.
In a first aspect, an embodiment of the present application provides a method for determining information of interest to a user, where the method includes:
acquiring scene characteristics from the knowledge graph according to scene information of a user;
determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity;
and determining target entities interested by the user from the candidate entities according to the interestingness.
In a second aspect, an embodiment of the present application further provides a device for determining information of interest to a user, where the device includes:
the feature acquisition module is used for acquiring scene features from the knowledge graph according to the scene information of the user;
the interest degree determining module is used for determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity;
and the entity determining module is used for determining target entities interested by the user from the candidate entities according to the interestingness.
In a third aspect, embodiments of the present application further provide an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the embodiments of the present application.
In a fourth aspect, embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of the embodiments of the present application.
According to the technical scheme, the information of interest of the user is further mined, so that the application value of the information of interest of the user in the intelligent information service is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for better understanding of the present solution and do not constitute a limitation of the present application. Wherein:
FIG. 1 is a flow chart of a method for determining information of interest to a user provided in an embodiment of the present application;
FIG. 2 is a partial flow chart of another method for determining information of interest to a user provided in an embodiment of the present application;
FIG. 3 is a flow chart of yet another method for determining information of interest to a user provided by an embodiment of the present application;
FIG. 4 is a schematic structural diagram of an interestingness prediction model according to an embodiment of the present application;
FIG. 5 is a flow chart of yet another method for determining information of interest to a user provided by an embodiment of the present application;
FIG. 6 is a flow chart of yet another method for determining information of interest to a user provided by an embodiment of the present application;
FIG. 7 is a schematic structural diagram of a device for determining information of interest to a user according to an embodiment of the present application;
FIG. 8 is a block diagram of an electronic device for implementing a method of determining information of interest to a user in accordance with an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flowchart of a method for determining information of interest to a user according to an embodiment of the present application. The method and the device are applicable to the situation that the user information of interest is further mined, so that the user information of interest generates greater application value in the intelligent information service. The method may be performed by a user information of interest determining means, which may be implemented in software and/or hardware. Referring to fig. 1, an embodiment of the present application provides a method for determining information of interest to a user, where the method includes:
s110, acquiring scene features from the knowledge graph according to scene information of the user.
The scene information refers to information of a scene where a user is located.
Scene features refer to features of the scene in which the user is located.
The knowledge graph comprises scene information.
Typically, the knowledge graph includes scene nodes, and attribute tags associated with the scene nodes.
Because the knowledge included in the knowledge graph is relatively rich, scene features acquired from the knowledge graph can comprehensively describe the scene in which the user is located. That is, scene features obtained from the knowledge graph are more abundant.
Specifically, according to the scene information of the user, acquiring scene features from the knowledge graph includes:
determining a target scene from the knowledge graph according to scene information of a user;
acquiring an attribute tag of the target scene;
and taking the acquired attribute tag as the scene feature.
The target scene refers to a scene where a user is located.
The attribute tag refers to a tag for describing the attribute of the target scene, and specifically can be a classification tag or a descriptive tag.
Specifically, acquiring the attribute tag of the target scene includes:
the attribute tags of the target scene are mined from the text.
In order to improve the obtaining efficiency and the obtaining comprehensiveness of the attribute tag, the obtaining the attribute tag of the target scene includes:
and acquiring the attribute label of the target scene from the knowledge graph by searching the edge between the target scene node and the attribute label node in the knowledge graph.
Specifically, determining the target scene from the knowledge graph according to the scene information of the user comprises the following steps:
matching the scene information of the user with the scene information in the knowledge graph;
and determining a target scene from the knowledge graph according to the matching result.
In order to improve the accuracy of the target scene, the determining the target scene from the knowledge graph according to the scene information of the user includes:
determining scene elements of a scene where the user is located according to scene information of the user;
matching scene elements of a scene where a user is located with scene elements in the knowledge graph;
and determining the target scene from the knowledge graph according to the matching result.
Wherein the scene element is an element that constructs the target scene.
In particular, the target scene may comprise one scene element, two scene elements or a plurality of scene elements.
Because the scene elements can describe the target scene more accurately than other scene information, the embodiment of the application can improve the accuracy of the target scene based on the technical characteristics, thereby improving the accuracy of the scene characteristics.
S120, determining the interest degree of the user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity.
Where the candidate entity refers to an entity that may be of interest to the user.
Entity characteristics are used to describe the nature of an entity.
The interestingness is used to describe the degree to which the candidate entity is of interest to the user.
Alternatively, the candidate entity may be a POI (Point of Interest ) or a person. The candidate entity can be preset or determined according to scene characteristics.
The embodiment of the present application is not limited in any way.
Specifically, determining candidate entities from scene features includes:
acquiring a related entity of a target scene from the knowledge graph, wherein the target scene is a scene to which the scene characteristics belong;
and taking the associated entity as the candidate entity.
The association entity refers to an entity having an association relationship with the target scene.
Based on the technical characteristics, the entity associated with the target scene is taken as the candidate entity, and because the entity associated with the target scene is more in line with the scene of the user, the likelihood that the user is interested in the entity is higher, so that the accuracy of the candidate entity can be improved.
Specifically, determining the interest degree of the user on the candidate entity according to the scene feature and the entity feature of the candidate entity comprises the following steps:
matching the scene characteristics with entity characteristics of the candidate entity;
and determining the interest degree of the user on the candidate entity according to the matching degree.
S130, determining a target entity which is interested by the user from the candidate entities according to the interestingness.
Optionally, determining, according to the interestingness, a target entity interested by the user from the candidate entities, including:
according to the set interestingness threshold, filtering out target entities interested by a user from the candidate entities according to the interestingness; or,
and sequencing the interestingness, and determining a target entity interested by the user from the candidate entities according to the sequencing result.
According to the technical scheme, the interest degree of the user on the candidate entity is determined according to the scene characteristics of the scene where the user is located; and determining a target entity which is interested by the user from the candidate entities according to the interestingness, so that the mining of the entity which is interested by the user based on the scene information of the user is realized, the information which is interested by the user is enriched, and the application value of the information which is interested by the user in the intelligent information service is improved.
In addition, by acquiring the scene characteristics from the knowledge graph, the comprehensiveness of the scene characteristics can be improved, so that the accuracy of the target entity is improved.
FIG. 2 is a partial flow chart of another method for determining information of interest to a user provided in an embodiment of the present application. On the basis of the above embodiment, the description of S120 is given for improving the accuracy of the interest level.
Specifically, the step S120 includes:
s121, matching the words in the scene characteristics and the high-frequency words of the candidate entity in the entity characteristics.
The high-frequency word of the candidate entity refers to a word with the co-occurrence frequency with the candidate entity being greater than a set frequency threshold.
The candidate entity can be accurately described by the high-frequency words of the candidate entity.
S122, determining the interest degree of the user to the candidate entity according to the matching result.
Specifically, the interest degree of the user to the candidate entity is determined according to the matching degree.
The higher the matching degree is, the higher the interest degree of the user to the candidate entity is.
According to the technical scheme, the candidate entity is accurately described by using the high-frequency words of the candidate entity, and the scene is accurately matched with the candidate entity by matching the words in the scene characteristics with the high-frequency words of the candidate entity, so that the accuracy of interest degree of the user on the candidate entity is improved.
FIG. 3 is a flow chart of yet another method for determining information of interest to a user provided in an embodiment of the present application. Based on the above embodiment, in order to improve depth mining on the relationship between the scene feature and the entity feature, so as to improve accuracy of interest, the technical solution of the embodiment of the present application may be further described as follows:
s210, acquiring scene features from the knowledge graph according to scene information of the user.
S220, matching the words in the scene characteristics with the high-frequency words of the candidate entities.
S230, encoding the scene features according to the matching result.
Alternatively, the encoding of the scene feature may be implemented by using any encoding manner, which is not limited in any way by the embodiments of the present application.
Specifically, encoding the scene features includes:
setting a first numerical value for the high-frequency words which are matched consistently, and setting a second numerical value for the high-frequency words which are not matched;
and sequencing the first numerical value and the second numerical value according to the arrangement sequence of the high-frequency words to obtain the coding result of the scene feature.
Wherein the first value is not equal to the second value.
Typically, the first value is 1 and the second value is 0, or the first value is 0 and the second value is 1.
S240, inputting the coding result of the scene feature into a pre-trained interestingness prediction model, and outputting the interestingness of the user to the candidate entity.
Specifically, the number of layers of the interestingness prediction model is determined according to the accuracy and the calculation efficiency of the target entity, so that the network structure is simplified to the greatest extent under the condition of meeting the requirement, and the calculation complexity of the model is reduced.
Typically, referring to FIG. 4, the interestingness prediction model includes 1 embedded layer, two cross net (cross network layer), two deep net (deep network layer), and 1 fully connected layer.
S250, determining a target entity which is interested by the user from the candidate entities according to the interestingness.
According to the technical scheme, the scene characteristics are encoded according to the matching result of the words in the scene characteristics and the high-frequency words of the candidate entity, so that the encoding result comprises distinguishing characteristics of the scene and the candidate entity; and then converting the features into different dimensional spaces based on the network model to realize deep mining of the association relationship between the scene and the candidate entity, thereby improving the accuracy of the interestingness.
Fig. 5 is a flowchart of yet another method for determining information of interest to a user provided in an embodiment of the present application. On the basis of the above embodiment, in order to further improve the accuracy of the interestingness, the technical solution of the embodiment of the present application may be further described as follows:
s310, acquiring scene characteristics from the knowledge graph according to scene information of the user.
S320, determining the interest degree of the user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity and at least one of the user personal information characteristics, the user history behavior characteristics and the user current behavior characteristics.
The personal information characteristic of the user is a characteristic for reflecting personal information of the user, and specifically comprises at least one of age of the user, driving condition, sex of the user, marital condition of the user, occupation of the user, position of the user, current time and current place.
The user history behavior characteristic is a characteristic reflecting the user history behavior, and specifically comprises at least one of price of a user history access entity, scoring of the history access entity, heat of the history access entity and information of high-frequency words of history access candidate entities.
The current behavior characteristic of the user is a characteristic reflecting the current behavior of the user, and specifically comprises at least one of the price of an entity, scoring of the entity, heat of the entity, high-frequency word information of candidate entities, time and place included in the current retrieval of the user.
Specifically, the entity characteristics of the candidate entity include: at least one of price, scoring, heat, high frequency words, and associated scenes of the candidate entity.
Specifically, the encoding mode for the above features may be: carrying out normalized coding by adopting logarithmic calculation logic aiming at floating point type characteristics; using one-hot (one-hot) coding for single-valued type features; multi-hot (multi-hot) encoding is used for multi-valued type features; and aiming at other characteristics, encoding according to the appearance information of the high-frequency words of the candidate entity in the other characteristics based on the encoding logic of the scene characteristics.
Optionally, determining the interest degree of the user on the candidate entity according to the scene feature and the entity feature of the candidate entity and at least one of the user personal information feature, the user history behavior feature and the user current behavior feature comprises:
determining the interest degree of a user on the candidate entity according to the scene characteristics, the entity characteristics of the candidate entity and the personal information characteristics of the user; or,
determining the interest degree of a user on the candidate entity according to the scene characteristics, the entity characteristics of the candidate entity and the historical behavior characteristics of the user; or,
determining the interest degree of the user on the candidate entity according to the scene characteristics, the entity characteristics of the candidate entity and the current behavior characteristics of the user; or,
determining the interest degree of a user on the candidate entity according to the scene characteristics, the entity characteristics of the candidate entity, the personal information characteristics of the user and the historical behavior characteristics of the user; or,
determining the interest degree of the user on the candidate entity according to the scene characteristics, the entity characteristics of the candidate entity, the historical behavior characteristics of the user and the current behavior characteristics of the user; or,
and determining the interest degree of the user on the candidate entity according to the scene characteristics, the entity characteristics of the candidate entity, the personal information characteristics of the user, the historical behavior characteristics of the user and the current behavior characteristics of the user.
S330, determining a target entity which is interested by the user from the candidate entities according to the interestingness.
According to the technical scheme, the interest degree of the user on the candidate entity is determined by increasing at least one information dimension among the personal information feature, the historical behavior feature and the current behavior feature of the user, so that the accuracy of the interest degree is improved.
Specifically, before the determining the interest level of the user in the candidate entity, the method further includes:
and acquiring the pre-stored personal information characteristics and the entity characteristics of the user.
Based on the technical characteristics, the embodiment of the application directly obtains the characteristics by pre-determining the personal information characteristics of the user and the entity characteristics of the candidate entity, so that the step of characteristic determination is saved, and the determination efficiency of the interestingness is improved.
Fig. 6 is a flowchart of yet another method for determining information of interest to a user provided in an embodiment of the present application. Based on the above embodiment, taking the entity as a POI and taking the application scene as an example of a scene for personalized recommendation of the user in the map application, an alternative scheme is provided. Referring to fig. 6, the method for determining the information of interest of the user provided in the embodiment of the application includes:
acquiring scene characteristics from the knowledge graph according to scene information of a user;
encoding the scene characteristics, POI characteristics of candidate POIs, user personal information characteristics, user historical behavior characteristics and user current behavior characteristics;
combining the coding results, inputting the combined coding results into a pre-trained interest degree prediction model, and outputting the interest degree of the user on the candidate POIs;
determining target POIs which are interested by the user from the candidate POIs according to the interest degree;
and presenting the determined target POI to a user.
Specifically, target POIs include restaurants, hotels, tourist attractions, and the like.
According to the technical scheme, by adding scene characteristics, accurate mining of the information of interest of the user is achieved, and accurate recommendation of the user based on the scene is further improved.
In addition, because complex processing is not carried out in the scheme, the scheme can meet the requirement of high performance on line.
Optionally, when the entity is a person, the method can realize the mining of the person interested by the user, so as to present news, dynamic and the like of the person to the user.
Fig. 7 is a schematic structural diagram of a device for determining information of interest to a user according to an embodiment of the present application. Referring to fig. 7, an apparatus 700 for determining information of interest of a user according to an embodiment of the present application includes: a feature acquisition module 701, an interestingness determination module 702, and an entity determination module 703.
The feature acquisition module 701 is configured to acquire a scene feature from the knowledge graph according to scene information of a user;
the interestingness determining module 702 is configured to determine an interestingness of a user to a candidate entity according to the scene feature and an entity feature of the candidate entity;
and the entity determining module 703 is configured to determine, according to the interestingness, a target entity that is interested by the user from the candidate entities.
According to the technical scheme, the interest degree of the user on the candidate entity is determined according to the scene characteristics of the scene where the user is located; and determining a target entity which is interested by the user from the candidate entities according to the interestingness, so that the mining of the entity which is interested by the user based on the scene information of the user is realized, the information which is interested by the user is enriched, and the application value of the information which is interested by the user in the intelligent information service is improved.
In addition, by acquiring the scene characteristics from the knowledge graph, the comprehensiveness of the scene characteristics can be improved, so that the accuracy of the target entity is improved.
Further, the feature acquisition module includes:
the scene determining unit is used for determining a target scene from the knowledge graph according to the scene information of the user;
the tag acquisition unit is used for acquiring attribute tags of the target scene;
and taking the acquired attribute tag as the scene feature.
Further, the scene determination unit includes:
an element determining subunit, configured to determine, according to the scene information of the user, a scene element of the scene where the user is located;
the element matching subunit is used for matching scene elements of the scene where the user is located with scene elements in the knowledge graph;
and the scene determining subunit is used for determining the target scene from the knowledge graph according to the matching result.
Further, the interestingness determining module includes:
the word matching unit is used for matching the words in the scene characteristics and the high-frequency words of the candidate entities in the entity characteristics;
and the interest degree determining unit is used for determining the interest degree of the user on the candidate entity according to the matching result.
Further, the interestingness determination unit includes:
the coding subunit is used for coding the scene features according to the matching result;
and the interest degree determining subunit is used for inputting the coding result of the scene characteristic into a pre-trained interest degree prediction model and outputting the interest degree of the user on the candidate entity.
Further, the coding subunit is specifically configured to:
setting a first numerical value for the high-frequency words which are matched consistently, and setting a second numerical value for the high-frequency words which are not matched;
and sequencing the first numerical value and the second numerical value according to the arrangement sequence of the high-frequency words to obtain the coding result of the scene feature.
Further, the interestingness determining module includes:
and the interest degree determining unit is used for determining the interest degree of the user on the candidate entity according to the scene characteristics, the entity characteristics and at least one of the user personal information characteristics, the user historical behavior characteristics and the user current behavior characteristics.
Further, the apparatus further comprises:
and the feature acquisition module is used for acquiring the pre-stored personal information features of the user and the entity features before the user interest degree of the candidate entity is determined.
Further, the apparatus further comprises:
the related entity acquisition module is used for acquiring a related entity of a target scene from the knowledge graph before determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity, wherein the target scene is the scene to which the scene characteristics belong;
and the candidate entity determining module is used for taking the associated entity as the candidate entity.
According to embodiments of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 8, a block diagram of an electronic device of a method for determining information of interest to a user according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.
As shown in fig. 8, the electronic device includes: one or more processors 801, memory 802, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 801 is illustrated in fig. 8.
Memory 802 is a non-transitory computer-readable storage medium provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the user information of interest determination methods provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the user information of interest determination method provided by the present application.
The memory 802 is used as a non-transitory computer readable storage medium, and may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules (e.g., the feature acquisition module 701, the interestingness determination module 702, and the entity determination module 703 shown in fig. 7) corresponding to the user interest information determination method in the embodiments of the present application. The processor 801 executes various functional applications of the server and data processing, i.e., implements the user-interest information determination method in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 802.
Memory 802 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created from determining the use of the electronic device based on the information of interest to the user, and the like. In addition, memory 802 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 802 may optionally include memory remotely located with respect to processor 801, which may be connected to the user information of interest determination electronics via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the user interest information determination method may further include: an input device 803 and an output device 804. The processor 801, memory 802, input devices 803, and output devices 804 may be connected by a bus or other means, for example in fig. 8.
The input device 803 may receive entered numeric or character information and generate key signal inputs related to the information of interest to the user to determine user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a joystick, one or more mouse buttons, a track ball, a joystick, or the like. The output device 804 may include a display apparatus, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme, the information of interest of the user is further mined, so that the application value of the information of interest of the user in the intelligent information service is improved.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.
Claims (18)
1. A method for determining information of interest to a user, comprising:
acquiring scene characteristics from the knowledge graph according to scene information of a user;
determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity;
determining a target entity which is interested by the user from the candidate entities according to the interestingness;
the step of obtaining scene features from the knowledge graph according to the scene information of the user comprises the following steps:
determining a target scene from the knowledge graph according to scene information of a user;
acquiring an attribute tag of the target scene;
and taking the acquired attribute tag as the scene feature.
2. The method according to claim 1, wherein determining the target scene from the knowledge-graph according to the scene information of the user comprises:
determining scene elements of a scene where the user is located according to scene information of the user;
matching scene elements of a scene where a user is located with scene elements in the knowledge graph;
and determining the target scene from the knowledge graph according to the matching result.
3. The method according to any one of claims 1-2, wherein determining the interest level of the user in the candidate entity according to the scene feature and the entity feature of the candidate entity comprises:
matching the words in the scene features with the high-frequency words of the candidate entities in the entity features;
and determining the interest degree of the user to the candidate entity according to the matching result.
4. A method according to claim 3, wherein determining the interest level of the user in the candidate entity according to the matching result comprises:
coding the scene features according to the matching result;
inputting the coding result of the scene characteristic into a pre-trained interestingness prediction model, and outputting the interestingness of the user to the candidate entity.
5. The method of claim 4, wherein encoding the scene feature based on the matching result comprises:
setting a first numerical value for the high-frequency words which are matched consistently, and setting a second numerical value for the high-frequency words which are not matched;
and sequencing the first numerical value and the second numerical value according to the arrangement sequence of the high-frequency words to obtain the coding result of the scene feature.
6. The method according to any one of claims 1-2, wherein determining the interest level of the user in the candidate entity according to the scene feature and the entity feature of the candidate entity comprises:
and determining the interest degree of the user on the candidate entity according to the scene characteristics and the entity characteristics and at least one of the user personal information characteristics, the user historical behavior characteristics and the user current behavior characteristics.
7. The method of claim 6, wherein prior to determining the user's interest level in the candidate entity, the method further comprises:
and acquiring the pre-stored personal information characteristics and the entity characteristics of the user.
8. The method according to any one of claims 1-2, wherein before determining the user's interest level in the candidate entity based on the scene characteristics and the entity characteristics of the candidate entity, the method comprises:
acquiring a related entity of a target scene from the knowledge graph, wherein the target scene is a scene to which the scene characteristics belong;
and taking the associated entity as the candidate entity.
9. A user information of interest determining apparatus, comprising:
the feature acquisition module is used for acquiring scene features from the knowledge graph according to the scene information of the user;
the interest degree determining module is used for determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity;
the entity determining module is used for determining a target entity which is interested by the user from the candidate entities according to the interestingness;
the feature acquisition module comprises:
the scene determining unit is used for determining a target scene from the knowledge graph according to the scene information of the user;
the tag acquisition unit is used for acquiring attribute tags of the target scene;
and taking the acquired attribute tag as the scene feature.
10. The apparatus according to claim 9, wherein the scene determination unit includes:
an element determining subunit, configured to determine, according to the scene information of the user, a scene element of the scene where the user is located;
the element matching subunit is used for matching scene elements of the scene where the user is located with scene elements in the knowledge graph;
and the scene determining subunit is used for determining the target scene from the knowledge graph according to the matching result.
11. The apparatus according to any one of claims 9-10, wherein the interestingness determination module comprises:
the word matching unit is used for matching the words in the scene characteristics and the high-frequency words of the candidate entities in the entity characteristics;
and the interest degree determining unit is used for determining the interest degree of the user on the candidate entity according to the matching result.
12. The apparatus according to claim 11, wherein the interestingness determination unit includes:
the coding subunit is used for coding the scene features according to the matching result;
and the interest degree determining subunit is used for inputting the coding result of the scene characteristic into a pre-trained interest degree prediction model and outputting the interest degree of the user on the candidate entity.
13. The apparatus of claim 12, wherein the encoding subunit is specifically configured to:
setting a first numerical value for the high-frequency words which are matched consistently, and setting a second numerical value for the high-frequency words which are not matched;
and sequencing the first numerical value and the second numerical value according to the arrangement sequence of the high-frequency words to obtain the coding result of the scene feature.
14. The apparatus according to any one of claims 9-10, wherein the interestingness determination module comprises:
and the interest degree determining unit is used for determining the interest degree of the user on the candidate entity according to the scene characteristics, the entity characteristics and at least one of the user personal information characteristics, the user historical behavior characteristics and the user current behavior characteristics.
15. The apparatus of claim 14, wherein the apparatus further comprises:
and the feature acquisition module is used for acquiring the pre-stored personal information features of the user and the entity features before the user interest degree of the candidate entity is determined.
16. The apparatus according to any one of claims 9-10, wherein the apparatus further comprises:
the related entity acquisition module is used for acquiring a related entity of a target scene from the knowledge graph before determining the interest degree of a user on the candidate entity according to the scene characteristics and the entity characteristics of the candidate entity, wherein the target scene is the scene to which the scene characteristics belong;
and the candidate entity determining module is used for taking the associated entity as the candidate entity.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010345720.7A CN111523007B (en) | 2020-04-27 | 2020-04-27 | Method, device, equipment and storage medium for determining user interest information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010345720.7A CN111523007B (en) | 2020-04-27 | 2020-04-27 | Method, device, equipment and storage medium for determining user interest information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111523007A CN111523007A (en) | 2020-08-11 |
| CN111523007B true CN111523007B (en) | 2023-12-26 |
Family
ID=71905304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010345720.7A Active CN111523007B (en) | 2020-04-27 | 2020-04-27 | Method, device, equipment and storage medium for determining user interest information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523007B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112069275A (en) * | 2020-08-26 | 2020-12-11 | 北京百度网讯科技有限公司 | Destination prediction method and device, electronic equipment and storage medium |
| CN112015439B (en) * | 2020-09-21 | 2024-01-12 | 北京百度网讯科技有限公司 | Embedding method, device, equipment and storage medium of user APP interest |
| CN112115225B (en) * | 2020-09-25 | 2024-03-01 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for recommending region of interest |
| CN114911990B (en) * | 2022-05-27 | 2023-01-03 | 北京天域北斗文化科技集团有限公司 | Map browsing system based on virtual reality and intelligent interaction |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291888A (en) * | 2017-06-21 | 2017-10-24 | 苏州发飚智能科技有限公司 | Life commending system method near hotel is moved in based on machine learning statistical model |
| CN107465754A (en) * | 2017-08-23 | 2017-12-12 | 北京搜狐新媒体信息技术有限公司 | A kind of news recommends method and apparatus |
| CN108874957A (en) * | 2018-06-06 | 2018-11-23 | 华东师范大学 | The dialog mode music recommended method indicated based on Meta-graph knowledge mapping |
| CN109710935A (en) * | 2018-12-26 | 2019-05-03 | 北京航空航天大学 | A kind of museum guiding based on historical relic knowledge mapping and knowledge recommendation method |
| JP2019102033A (en) * | 2017-12-08 | 2019-06-24 | Kddi株式会社 | Topic presentation device, topic presentation method, and topic presentation program |
| CN109948068A (en) * | 2017-09-30 | 2019-06-28 | 阿里巴巴集团控股有限公司 | A kind of recommended method and device of interest point information |
| CN110020913A (en) * | 2019-02-20 | 2019-07-16 | 中国人民财产保险股份有限公司 | Products Show method, equipment and storage medium |
| CN110162690A (en) * | 2018-10-23 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Determine user to the method and apparatus of the interest-degree of article, equipment and storage medium |
| EP3554040A1 (en) * | 2018-04-10 | 2019-10-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for recommending entity |
| CN110427554A (en) * | 2019-07-26 | 2019-11-08 | 北京达佳互联信息技术有限公司 | Recommended method, device, intelligent terminal, server and the storage medium of point of interest |
| CN110674423A (en) * | 2019-09-23 | 2020-01-10 | 拉扎斯网络科技（上海）有限公司 | Address positioning method and device, readable storage medium and electronic equipment |
| CN110909170A (en) * | 2019-10-12 | 2020-03-24 | 百度在线网络技术（北京）有限公司 | Interest point knowledge graph construction method and device, electronic equipment and storage medium |
| CN110955820A (en) * | 2018-09-22 | 2020-04-03 | 北京微播视界科技有限公司 | Media information interest point recommendation method, device, server and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2568429A4 (en) * | 2010-11-29 | 2013-11-27 | Huawei Tech Co Ltd | Method and system for pushing individual advertisement based on user interest learning |
-
2020
- 2020-04-27 CN CN202010345720.7A patent/CN111523007B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291888A (en) * | 2017-06-21 | 2017-10-24 | 苏州发飚智能科技有限公司 | Life commending system method near hotel is moved in based on machine learning statistical model |
| CN107465754A (en) * | 2017-08-23 | 2017-12-12 | 北京搜狐新媒体信息技术有限公司 | A kind of news recommends method and apparatus |
| CN109948068A (en) * | 2017-09-30 | 2019-06-28 | 阿里巴巴集团控股有限公司 | A kind of recommended method and device of interest point information |
| JP2019102033A (en) * | 2017-12-08 | 2019-06-24 | Kddi株式会社 | Topic presentation device, topic presentation method, and topic presentation program |
| EP3554040A1 (en) * | 2018-04-10 | 2019-10-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for recommending entity |
| CN108874957A (en) * | 2018-06-06 | 2018-11-23 | 华东师范大学 | The dialog mode music recommended method indicated based on Meta-graph knowledge mapping |
| CN110955820A (en) * | 2018-09-22 | 2020-04-03 | 北京微播视界科技有限公司 | Media information interest point recommendation method, device, server and storage medium |
| CN110162690A (en) * | 2018-10-23 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Determine user to the method and apparatus of the interest-degree of article, equipment and storage medium |
| CN109710935A (en) * | 2018-12-26 | 2019-05-03 | 北京航空航天大学 | A kind of museum guiding based on historical relic knowledge mapping and knowledge recommendation method |
| CN110020913A (en) * | 2019-02-20 | 2019-07-16 | 中国人民财产保险股份有限公司 | Products Show method, equipment and storage medium |
| CN110427554A (en) * | 2019-07-26 | 2019-11-08 | 北京达佳互联信息技术有限公司 | Recommended method, device, intelligent terminal, server and the storage medium of point of interest |
| CN110674423A (en) * | 2019-09-23 | 2020-01-10 | 拉扎斯网络科技（上海）有限公司 | Address positioning method and device, readable storage medium and electronic equipment |
| CN110909170A (en) * | 2019-10-12 | 2020-03-24 | 百度在线网络技术（北京）有限公司 | Interest point knowledge graph construction method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| "教师—资源"互动视角下的教师教学设计能力研究;刘新阳;中国优秀博士学位论文全文数据库;全文 * |
| A POI-Sensitive Knowledge Graph Based Service Recommendation Method;Sihang Hu;2019 IEEE International Conference on Services Computing (SCC);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111523007A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111523007B (en) | Method, device, equipment and storage medium for determining user interest information | |
| CN113094550B (en) | Video retrieval method, device, equipment and medium | |
| CN110955764B (en) | Scene knowledge graph generation method, man-machine conversation method and related equipment | |
| CN111522967B (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN111488740B (en) | Causal relationship judging method and device, electronic equipment and storage medium | |
| CN111680517B (en) | Method, apparatus, device and storage medium for training model | |
| CN111860769A (en) | Method and device for pre-training neural network | |
| CN111797216B (en) | Search term rewriting method, apparatus, device and storage medium | |
| CN112466280B (en) | Voice interaction method and device, electronic equipment and readable storage medium | |
| CN110427436B (en) | Method and device for calculating entity similarity | |
| JP7242994B2 (en) | Video event identification method, apparatus, electronic device and storage medium | |
| CN111523001A (en) | Method, device, equipment and storage medium for storing data | |
| CN111274407A (en) | Triple confidence degree calculation method and device in knowledge graph | |
| CN111241838B (en) | Semantic relation processing method, device and equipment for text entity | |
| CN110532404B (en) | Source multimedia determining method, device, equipment and storage medium | |
| CN111666461A (en) | Method, apparatus, device and computer storage medium for retrieving geographical location | |
| CN111488972B (en) | Data migration method, device, electronic equipment and storage medium | |
| CN112115387B (en) | Training method and device for POI recommendation model and electronic equipment | |
| CN112597288B (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN112328896B (en) | Method, apparatus, electronic device, and medium for outputting information | |
| CN111666417B (en) | Method, device, electronic equipment and readable storage medium for generating synonyms | |
| CN111611364B (en) | Intelligent response method, device, equipment and storage medium | |
| CN111665955B (en) | Candidate character string processing method and device, electronic equipment and storage medium | |
| CN113111216B (en) | Advertisement recommendation method, device, equipment and storage medium | |
| CN111177479A (en) | Method and device for acquiring feature vectors of nodes in relational network graph |
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 |