[go: up one dir, main page]

CN107229741B - Information searching method, device, equipment and storage medium - Google Patents

Information searching method, device, equipment and storage medium Download PDF

Info

Publication number
CN107229741B
CN107229741B CN201710470126.9A CN201710470126A CN107229741B CN 107229741 B CN107229741 B CN 107229741B CN 201710470126 A CN201710470126 A CN 201710470126A CN 107229741 B CN107229741 B CN 107229741B
Authority
CN
China
Prior art keywords
search
user
entity
result
image
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
Application number
CN201710470126.9A
Other languages
Chinese (zh)
Other versions
CN107229741A (en
Inventor
吕居美
胡翔宇
黄丽洁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Original Assignee
Baidu Online Network Technology Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Baidu Online Network Technology Beijing Co Ltd filed Critical Baidu Online Network Technology Beijing Co Ltd
Priority to CN201710470126.9A priority Critical patent/CN107229741B/en
Publication of CN107229741A publication Critical patent/CN107229741A/en
Application granted granted Critical
Publication of CN107229741B publication Critical patent/CN107229741B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Landscapes

  • Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the invention discloses an information searching method, an information searching device, information searching equipment and a storage medium. The method comprises the following steps: acquiring a search image input by a user; carrying out entity identification on the search image, and providing at least two search dimensions corresponding to an entity identification result to the user, wherein different search dimensions correspond to different network query conditions; and performing network search according to the network query condition corresponding to the search dimension selected by the user, and providing a corresponding search result for the user. The scheme of the embodiment of the invention solves the problem that the prior art can only return the search result with a single search dimension in the search result page and cannot bear the multidimensional picture search requirement, well butt-joints the information search result of the system with the actual search requirement of the user, improves the hit rate of the search result and improves the use satisfaction of the user.

Description

Information searching method, device, equipment and storage medium
Technical Field
Embodiments of the present invention relate to information processing technologies, and in particular, to an information search method, an information search apparatus, an information search device, and a storage medium.
Background
The amount of information included in a picture search method is the most abundant among different search methods (e.g., text, voice, picture, etc.). Meanwhile, the retrieval requirements of the user on the pictures are also various and unpredictable.
The main expression is that when different users search for the same picture (photographed or network picture), the search requirements are often different, some users want to search for the same clothing in the picture, some users want to search for the price, the use method or the solution of the article in the picture, some users want to search for the original image, the high definition image or the similar image of the picture, some users want to search for the name of the person in the picture, and the like, and these user requirements (which may also be called as search dimension) cannot be known by the search system at the beginning of picture search.
The conventional image retrieval system can only return a search result with a single retrieval dimension in a search result page, cannot bear the requirement of multi-dimensional image retrieval, and a user often needs to acquire really required retrieval information by manual screening or a secondary retrieval mode, so that the retrieval efficiency is poor.
Disclosure of Invention
The embodiment of the invention provides an information searching method, an information searching device, information searching equipment and a storage medium, which are used for optimizing the existing image searching technology and meeting the increasing personalized and convenient image searching requirements of people.
In a first aspect, an embodiment of the present invention provides an information search method, including:
acquiring a search image input by a user;
carrying out entity identification on the search image, and providing at least two search dimensions corresponding to an entity identification result to the user, wherein different search dimensions correspond to different network query conditions;
and performing network search according to the network query condition corresponding to the search dimension selected by the user, and providing a corresponding search result for the user.
In a second aspect, an embodiment of the present invention further provides an information searching apparatus, including:
the search image acquisition module is used for acquiring a search image input by a user;
the search dimension providing module is used for carrying out entity identification on the search image and providing at least two search dimensions corresponding to the entity identification result to the user, wherein different search dimensions correspond to different network query conditions;
and the search result providing module is used for carrying out network search according to the network query condition corresponding to the search dimension selected by the user and providing the corresponding search result for the user.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the information search method according to any one of the embodiments of the present invention when executing the computer program.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the information search method according to any one of the embodiments of the present invention.
The embodiment of the invention provides an information searching method, a device, equipment and a storage medium, which can simultaneously provide multi-dimensional information included in a searching picture for a user to select by a technical means of carrying out entity identification on a searching image input by the user, providing at least two searching dimensions corresponding to an entity identification result for the user, carrying out network searching according to a network query condition corresponding to the searching dimension selected by the user and providing a corresponding searching result for the user, thereby helping the user to quickly clarify searching requirements, and further pertinently providing the searching result capable of meeting the actual requirements of the user for the user according to the searching dimension selected by the user independently, solving the problem that the prior art can only return the searching result with a single searching dimension in a searching result page and cannot bear the searching requirements of the multi-dimensional picture, the information search results of the system are well butted with the actual search requirements of the user, the hit rate of the search results is improved, and the use satisfaction of the user is improved.
Drawings
FIG. 1a is a flowchart of an information searching method according to a first embodiment of the present invention;
FIG. 1b is a schematic interface diagram of a search image presentation interface according to a first embodiment of the present invention;
FIG. 2a is a flowchart of an information searching method according to a second embodiment of the present invention;
fig. 2b is a schematic interface diagram illustrating visualized display of the identified entities in the search image display interface according to the second embodiment of the present invention;
fig. 2c is another interface schematic diagram for visually displaying the identified entities in the search image display interface according to the second embodiment of the present invention;
FIG. 2d is a schematic diagram of an interface for returning a corresponding search result according to a target entity selected by a user in a search image presentation interface according to a second embodiment of the present invention;
fig. 3a is a flowchart of an information searching method in the third embodiment of the present invention;
fig. 3b is a schematic interface diagram of a third embodiment of the present invention, in which a default display entity and a corresponding search result are displayed in a search image display interface in a differentiated manner;
FIG. 4a is a flowchart of an information searching method according to a fourth embodiment of the present invention;
fig. 4b is a schematic interface diagram of displaying a result page sub-cluster corresponding to each search dimension in a search result presentation page after a user selects a full-dimension search option in the fourth embodiment of the present invention;
FIG. 4c is a schematic interface diagram of a result page sub-cluster according to a fourth embodiment of the present invention;
FIG. 4d is a schematic diagram of an interface for displaying at least two single entity search dimensions in the search result presentation page according to the fourth embodiment of the present invention;
fig. 5a is a flowchart of an information searching method in the fifth embodiment of the present invention;
FIG. 5b is a schematic diagram of an interface for displaying at least two single entity search dimensions in the search result presentation page according to the fifth embodiment of the present invention;
fig. 6 is a structural diagram of an information search apparatus in a sixth embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computer device in a seventh embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1a is a flowchart of an information search method according to an embodiment of the present invention, where the present embodiment is applicable to a case where a user is provided with a search result corresponding to a search image, and the method may be performed by an information search apparatus according to an embodiment of the present invention, where the information search apparatus may be implemented in software and/or hardware, and may be generally integrated in a client providing an image search service (e.g., an image search engine). As shown in fig. 1a, the method of this embodiment specifically includes:
and S110, acquiring a search image input by a user.
Generally, when a user wants to search for an image through an image search engine, the user may first enter a set image input interface in a client of the image search engine, and then may provide the image to be searched for to a corresponding image search engine for network search through a photo upload or a local photo upload mode.
In addition, if the client of the image search engine comprises a function plug-in, the user can directly perform network search on the shot image in the camera application, or perform network search on the selected image in the folder application acquiring webpage browsing application.
Correspondingly, the search image may be obtained correspondingly based on the different image search modes described above by the user, where the search image is an image for which the user wishes to perform a network search for some unknown information amount included in the image.
In an optional implementation manner of this embodiment, acquiring the search image input by the user may include: the method comprises the steps of obtaining a search image input by a user through a search image display interface, wherein the search image display interface is a program interface which is provided for the user to browse the input search image by a client side of an image search engine. In the search image display interface, a user can directly take a picture and upload a search image, and can also search and upload a corresponding search image from a local photo folder.
Fig. 1b shows an interface schematic diagram of a search image presentation interface according to a first embodiment of the present invention. As shown in fig. 1b, after entering a search image display interface provided by a client of a search engine, a user may acquire an image captured by a camera in real time in the search image display interface, and may shoot a search image that needs to be subjected to web search by clicking a shooting control 1101 in the search image display interface, where the shot image may be simultaneously subjected to preview display in the search image display interface; in addition, the user can also find a search image to be subjected to network search in the locally stored photo folder by clicking the folder control 1102 in the search image display interface, and the found search image can be displayed in the search image display interface at the same time.
S120, entity recognition is carried out on the search image, and at least two search dimensions corresponding to the entity recognition result are provided for the user, wherein different search dimensions correspond to different network query conditions.
Feature point extraction can be performed in the search image through a local Scale-invariant feature transform (SIFT-invariant feature transform) technology, and one or more independent entities (for example, a human face, a badminton racket, a leather shoe and the like included in fig. 1 b) which can be distinguished from each other are identified; the search image may also be subjected to entity identification by the remote server in a manner of sending the search image to the remote image server, which is not limited in this embodiment.
It is understood that the number of entities that can be identified in a search image is different according to the content of the image in the search image, the sharpness of the image, and other factors, for example: 0, 1 or more, etc.
In the present embodiment, a corresponding image search method is mainly considered when the number of entities identified in searching for an image is 1 or more.
Correspondingly, if the number of the entities identified in the search image is greater than 1, the identified entities can be visually displayed in the search image display interface according to the identification positions of at least two entities identified in the search image; wherein different entities correspond to different search dimensions.
If the number of entities identified in the search image is 1, determining at least two single entity search dimensions corresponding to a single entity identified in the search image according to the entity type of the single entity; skipping the search image display interface to a search result display page; and displaying the at least two single entity search dimensions at a set position of the search image display interface so as to prompt the user to search for the single identified entity under the set single entity search dimension.
That is, in the present embodiment, if at least two entities are identified in one search image, it can be determined that the user may be interested in information of a certain entity in the search image. At this time, the search requirement of the user is ambiguous, and no matter which entity is identified to perform the web search, the actual requirement of the user may be missed. Therefore, the entities can be identified in the search image as a plurality of search dimensions (typically, frame selection is performed), so that the user can be helped to clarify the requirements, and after the user selects a specific entity, what the entity the user really wants to search can be determined very definitely, so that the accuracy of subsequent image search can be obviously improved. In addition, if only one entity can be identified in one search image, the scheme continues to excavate user requirements in multiple aspects corresponding to the entity (for example, a face identification requirement or a requirement for finding original images or similar images, and the like), constructs multiple corresponding search dimensions according to the user requirements in the multiple aspects, and provides the multiple search dimensions for the user, and the technical effect of rapidly helping the user to clarify the requirements can be achieved.
S130, network searching is carried out according to the network query conditions corresponding to the search dimensions selected by the user, and corresponding search results are provided for the user.
As mentioned above, a search dimension may correspond to a network query condition, and the query type of the network query condition may include at least one of the following: text query conditions, image query conditions, and video query conditions. For example: as shown in fig. 1b, if the recognition result of the search image includes: if the face is XX globoid, the network query condition corresponding to the search dimension of the face may be: the image query condition of the face image is added with the text query condition of XX ball star.
In this embodiment, when a user selects a search dimension, a network query condition corresponding to the search dimension may be determined, and then the network query condition is sent to the image search server, so that a corresponding network search result may be obtained and provided to the user.
The embodiment of the invention provides an information searching method, which can simultaneously provide multi-dimensional information included in a searching picture for a user to select by a technical means of carrying out entity identification on a searching image input by the user, providing at least two searching dimensions corresponding to an entity identification result for the user, carrying out network searching according to a network query condition corresponding to the searching dimension selected by the user and providing a corresponding searching result for the user, so as to help the user to quickly clarify searching requirements, and further provide the searching result which can meet the actual requirements of the user with pertinence according to the searching dimension selected by the user, thereby solving the problem that the prior art can only return the searching result with a single searching dimension in a searching result page, cannot bear the searching requirements of the multi-dimensional pictures, and well butt-joint the information searching result of the system with the actual searching requirements of the user, the hit rate of the search results is improved, and the use satisfaction of the user is improved.
Example two
Fig. 2a is a flowchart of an information search method according to a second embodiment of the present invention, which is embodied on the basis of the second embodiment, in this embodiment, entity recognition is performed on the search image, and at least two search dimensions corresponding to an entity recognition result are provided to the user, specifically: visually displaying the identified entities in the search image display interface according to the identification positions of the at least two entities identified in the search image;
meanwhile, network search is carried out according to the network query condition corresponding to the search dimension selected by the user, and a corresponding search result is provided for the user, specifically: acquiring a target entity selected by the user in the search image display interface; acquiring a target network query condition corresponding to the target entity; and performing network search according to the target network query condition, and displaying a corresponding search result at a first set position of the search image display interface. Correspondingly, the method of the embodiment specifically includes:
and S210, acquiring a search image input by a user through a search image display interface.
S220, visually displaying the identified entities in the search image display interface according to the identification positions of the at least two entities identified in the search image; wherein different entities correspond to different search dimensions.
As described above, by performing SIFT feature point identification on the search image, one or more independent entities can be obtained in the search image, and the scheme of the embodiment provides an information search method when the number of identified entities is greater than 1. Namely: before starting network search, firstly, visually displaying each identified entity in a search image display interface to help a user to determine the entity which actually needs to be searched. The visual display may be implemented by way of frame selection or highlighting, and the present embodiment does not limit this.
Fig. 2b is a schematic interface diagram illustrating a visualized presentation of the identified entities in the search image presentation interface according to a second embodiment of the present invention. As shown in fig. 2b, a total of three entities are identified in the search image, and the three entities are visually displayed by means of frame selection. Namely: a framed badminton racket 2101, a framed leather shoe 2102 and a framed human face 2103.
In another optional implementation manner of this embodiment, visually displaying, in the search image display interface, the identified entities according to the identified positions of the at least two entities identified in the search image, may further include:
determining entity labels respectively corresponding to the entities according to entity types of at least two entities identified in the search image; and according to the identification positions of at least two entities identified in the search image, visually displaying each identified entity and an entity label corresponding to the entity in the search image display interface.
Specifically, if the entity identification of the search image is realized by means of the big data of the image search engine server, more information of the identified entity can be further obtained, that is: and (4) entity labels. For example: if the face is recognized, the name of the person corresponding to the face can be further determined; if a badminton racket is recognized, the brand of the badminton racket can be further determined, for example: and carrying out logo search in the badminton racket.
Correspondingly, after the recognized entities are visually displayed in the search image display interface, the entity labels respectively corresponding to the entities can be visually displayed, so that more auxiliary decision information can be provided for the user, and the clarification requirement of the user can be further assisted.
Fig. 2c shows another interface schematic diagram for visually displaying the identified entities in the search image display interface according to the second embodiment of the present invention. As shown in fig. 2c, besides selecting the identified entity boxes and providing them to the user, further providing the entity labels of the entities to the user, and by the information of the entity labels, the user can more accurately determine the actual search requirement of the user.
And S230, acquiring a target entity selected by the user in the search image display interface.
Typically, when a user selects an entity prompt box, it may be determined that the user selected to search for a target entity corresponding to the entity prompt box.
S240, obtaining a target network query condition corresponding to the target entity.
And S250, performing network search according to the target network query condition, and displaying a corresponding search result at a first set position of the search image display interface.
Fig. 2d is a schematic interface diagram illustrating a second embodiment of the present invention, where a corresponding search result is returned according to a target entity selected by a user in a search image presentation interface. As shown in fig. 2d, when the user selects the entity prompt box corresponding to the face in the search image, the prompt box is displayed differently from the other entity prompt boxes. And based on the network query condition corresponding to the entity of the face, corresponding network search is performed, and the corresponding search result is displayed at the first setting position 2104 of the search image display interface.
The first setting position 2104 may be a lower half screen of the screen interface, and accordingly, the whole search image originally occupying the whole screen may be reduced to half screen display, or only the face portion selected by the user may be captured in the search image to perform half screen display.
According to the technical scheme of the embodiment of the invention, each identified entity is visually displayed in a search image display interface according to the identification positions of at least two entities identified in a search image; acquiring a target entity selected by the user in a search image display interface; acquiring a target network query condition corresponding to a target entity; the method for searching the network according to the target network query condition and displaying the corresponding search result at the first set position of the search image display interface can only provide the relevant network search result of the target entity selected by the user to the user in the search image display interface without bringing the bad experience of webpage skipping to the user, and returns the required search result to the user in the simplest and most convenient way, so that the user can meet the appeal at the highest speed, and the satisfaction degree of image search is greatly improved.
EXAMPLE III
Fig. 3 is a flowchart of an information searching method according to a third embodiment of the present invention, which is embodied based on the above embodiments. In this embodiment, after visually displaying, in the search image display interface, each of the identified entities according to the identification positions of at least two entities identified in the search image, the method further specifically includes: determining network query conditions respectively corresponding to the entities according to entity types respectively corresponding to the entities; modifying each network query condition according to the attribute description data of the user, and performing priority ranking on each entity; determining a default display entity and a default network query condition corresponding to the default display entity according to the priority ranking result; displaying the default display entity differently from other entities in the search image display interface; and performing network search according to the default network query condition, and displaying a corresponding search result at a second set position of the search image display interface. Correspondingly, the method of the embodiment specifically includes:
and S310, acquiring a search image input by a user through a search image display interface.
S320, visually displaying the identified entities in the search image display interface according to the identification positions of the at least two entities identified in the search image.
S330, determining network query conditions respectively corresponding to the entities according to entity types respectively corresponding to the entities.
In this embodiment, each identified entity corresponds to a fixed, or default, network query. Thus, in theory, search results obtained by different users are theoretically identical with respect to the same entity in the same search image. In practice, however, the search requirements for the same entity may vary among users based on their actual requirements. For example: for the same clothing entity in a search image, some users look like viewing a street photo or a match based on the clothing, and people want to view other people who wear the clothing. In order to make different users obtain the search results which are actually needed by the users as much as possible, in the embodiment of the present invention, an operation of correcting the network query condition is introduced.
S340, modifying each network query condition according to the attribute description data of the user, and performing priority ranking on each entity.
Wherein the attribute description data of the user may include: user profile data (e.g., "fashion darner" or "novice mom", etc.), and/or user history search records.
Wherein the user profile data may be determined based on a history search record of the user or personal information previously registered by the user. After the attribute description data of the user is obtained, each network query condition may be modified according to the attribute description data, for example, after a user is determined to be "fashion fellow", the network query condition of the text type of a clothing entity in the search image input by the user may be modified to "match with star science".
Further, in this embodiment, after the entities included in the search image input by the user are identified and selected, further, before the user selects a target entity, the search result corresponding to the entity that the user is most likely to search is provided to the user in the search image display interface, so that the optimal search result is displayed on the basis of the least user operations, and the picture search experience of the user is further improved.
Correspondingly, the priority ranking of the identified entities can be further performed according to the attribute description data of the user.
For example: if the entity recognition result includes: the "XX ball star", "AA badminton racket", and "BB leather shoe" are used as the user image of the user, and the "fashion darts" are used as the user image, the priority order of the entities can be determined as "BB leather shoe", "AA badminton racket", and "XX ball star".
And S350, determining a default display entity and a default network query condition corresponding to the default display entity according to the priority ranking result.
Typically, the highest priority one of the entities may be obtained as the default display entity. And correspondingly acquiring default network query conditions corresponding to the default display entities.
And S360, displaying the default display entity different from other entities in the search image display interface.
And S370, performing network search according to the default network query condition, and displaying a corresponding search result at a second set position of the search image display interface.
Fig. 3b is a schematic interface diagram illustrating a default display entity and a corresponding search result displayed differently in a search image presentation interface according to a third embodiment of the present invention. As shown in fig. 3b, after determining "BB shoes" as the highest priority entity, the entity can be distinguished from other entities for display, for example: the distinctive display is performed by means of color masking or a convex display. At the same time, the search result corresponding to "BB shoe" is displayed at the second set position 3101 on the search image display interface.
The second setting position may be the same as or different from the first setting position, which is not limited in this embodiment.
S380, network searching is carried out according to the network query conditions corresponding to the search dimensions selected by the user, and corresponding search results are provided for the user.
The technical scheme of the embodiment of the invention determines the network query conditions respectively corresponding to the entities according to the entity types respectively corresponding to the entities; modifying each network query condition according to the attribute description data of the user, and performing priority ranking on each entity; determining a default display entity and a default network query condition corresponding to the default display entity according to the priority ranking result; displaying the default display entity differently from other entities in the search image display interface; the technical means of performing network search according to the default network query condition and displaying the corresponding search result at the second set position of the search image display interface provides each entity that the user may select to the user and also provides the search result corresponding to the entity that the user is most likely to select to the user in the search image display interface.
Example four
Fig. 4a is a flowchart of an information searching method according to a fourth embodiment of the present invention, which is embodied based on the foregoing embodiments. In this embodiment, after visually displaying, in the search image display interface, each of the identified entities according to the identification positions of at least two entities identified in the search image, the method further specifically includes: providing a full-dimensional search option corresponding to the search image to the user;
correspondingly, network search is carried out according to the network query condition corresponding to the search dimension selected by the user, and a corresponding search result is provided for the user, specifically: skipping the search image display interface to a search result display page according to the full-dimension search option selected by the user; constructing result page sub-clusters corresponding to the search dimensions according to the set number of search results respectively corresponding to the search dimensions; and displaying each result page sub-cluster in the search result display page. Correspondingly, the method of the embodiment specifically includes:
and S410, acquiring a search image input by a user through a search image display interface.
S420, visually displaying the identified entities in the search image display interface according to the identification positions of the at least two entities identified in the search image.
And S430, providing the full-dimensional search option corresponding to the search image to the user.
In this embodiment, considering that when a user searches for a search image, not only one search dimension in the search image may be interested, but also information of all dimensions included in the search image may be interested, a full-dimensional search option may be provided to the user at the search image presentation interface, so that search results of the full-dimension are provided to the user according to user requirements.
S440, skipping the search image display interface to a search result display page according to the full-dimension search option selected by the user.
Considering that the number of search results to be returned is generally large when a full-dimensional search is performed, it is not appropriate to provide the search results in the search image presentation interface, and therefore, it is preferable that the search image presentation interface is jumped to a search result presentation page to complete presentation of the search results.
S450, constructing result page sub-clusters corresponding to the search dimensions according to the set number of search results corresponding to the search dimensions.
Different search dimensions correspond to different network query conditions, different network query conditions correspond to different types of search results, and different types of search results correspond to different result page sub-clusters.
And S460, displaying each result page sub-cluster in the search result display page.
Fig. 4b is a schematic interface diagram illustrating that, in the fourth embodiment of the present invention, after a user selects a full-dimensional search option, a result page sub-cluster corresponding to each search dimension is displayed in a search result presentation page. As shown in fig. 4b, when the user selects the full-dimension search option 4102 in the search image presentation interface 4101, the page will automatically jump to the search results presentation page 4103. Different entities correspond to different result page sub-clusters, and each result page sub-cluster comprises a set number of search results corresponding to the entities.
According to the technical scheme of the embodiment of the invention, the search image display interface is jumped to a search result display page according to the full-dimensional search option selected by the user; constructing result page sub-clusters corresponding to the search dimensions according to the set number of search results respectively corresponding to the search dimensions; the technical means of displaying each result page sub-cluster in the search result display page further enriches the service types provided by the image search tool, and more comprehensively meets different image search requirements of different users, so as to further improve the satisfaction degree of the users.
On the basis of the foregoing embodiments, the result page sub-cluster may include: entity mapping corresponding to the search dimension, result page sub-cluster title and a set number of search results corresponding to the search dimension.
In this embodiment, in order to further enable the user to distinguish the search results of different entities from the search results of the full search dimension, an entity matching map corresponding to the search dimension is added to the result page sub-cluster. Fig. 4c is a schematic interface diagram of a result page sub-cluster in the fourth embodiment of the present invention. As shown in fig. 4, the entity corresponding to the result cluster titled "XX globalstar related information" is a face in the search image, so that the face can be cut out from the search image and added to the result page sub-cluster 4104, so that the user can quickly and conveniently know that the search result included in the result page sub-cluster 4104 is a search result returned for the face entity.
On the basis of the foregoing embodiments, after displaying each result page sub-cluster in the search result presentation page, the method may further include:
when the user is detected to execute set interactive operation aiming at a target result page sub-cluster, determining at least two single entity search dimensions corresponding to a selected entity according to the entity type of the selected entity corresponding to the target result page sub-cluster, wherein different single entity search dimensions correspond to different network query conditions;
and displaying the at least two single entity search dimensions at a third set position of the search result display page to prompt the user to search under the set single entity search dimension for the selected entity.
As previously mentioned, after determining a single entity that the user actually wants to search, the search direction of the user based on that entity is also uncertain. Further, after the user selects an entity, at least two single entity search dimensions corresponding to the entity may be provided to the user. For example: if the entity selected by the user is a face, the user may wish to determine the personal information corresponding to the face, or may wish to obtain a similar image or a material image. Therefore, different single entity search dimensions can be determined and provided for the user based on different entity types (such as human faces or clothes or leather bags) of the single entity, so that the user can conduct more targeted network search, and the search satisfaction of the user is further improved.
The third setting position may be preset according to the visual experience of the user and the actual typesetting requirement, which is not limited in this embodiment.
Fig. 4d is a schematic interface diagram illustrating that at least two single entity search dimensions are displayed in the search result presentation page in the fourth embodiment of the present invention. As shown in fig. 4d, when the user performs a set interaction operation in a certain result page sub-cluster, for example, a fast downward sliding, at least two single entity search dimensions of the entity corresponding to the result page sub-cluster may be provided to the user, that is: "Picture identification", "Picture Source", and "similar Picture" in FIG. 4 d. Accordingly, for different single entity search dimensions, a next level search dimension may be further included, for example, a next level search dimension corresponding to "picture recognition" includes: "full image", "character", "brand", and "facial form".
EXAMPLE five
Fig. 5a is a flowchart of an information searching method according to a fifth embodiment of the present invention, which is embodied based on the foregoing embodiments. In this embodiment, the entity recognition is performed on the search image, and at least two search dimensions corresponding to the entity recognition result are provided to the user, specifically: determining at least two single entity search dimensions corresponding to a single entity according to the entity type of the single entity identified in the search image; skipping the search image display interface to a search result display page; and displaying the at least two single entity search dimensions at a fourth set position of the search image display interface to prompt the user to search for the single identified entity under the set single entity search dimension. Correspondingly, the method of the embodiment specifically includes:
and S510, acquiring a search image input by a user.
S520, determining at least two single entity searching dimensions corresponding to the single entity according to the entity type of the single entity identified in the searching image.
S530, jumping the search image display interface to a search result display page.
And S540, displaying the at least two single entity searching dimensions at a fourth set position of the searching image display interface so as to prompt the user to search under the set single entity searching dimensions for the single identified entity.
The fourth setting position may be the same as or different from the third setting position, which is not shown in this embodiment.
In an optional implementation manner of this embodiment, after displaying the at least two single entity search dimensions at a fourth set position of the search image display interface, the method may further include: determining a default display dimension according to the entity type of the single entity; and acquiring a search result corresponding to the default display dimension, and displaying the search result corresponding to the default display dimension in the search result display page.
Fig. 5b is a schematic interface diagram illustrating that at least two single-entity search dimensions are displayed in the search result presentation page in accordance with a fifth embodiment of the present invention.
S550, network searching is carried out according to the network query conditions corresponding to the search dimensions selected by the user, and corresponding search results are provided for the user.
The embodiment of the invention provides an information searching method, which can simultaneously provide multi-dimensional information included in a searching picture for a user to select by a technical means of carrying out entity identification on a searching image input by the user, providing at least two searching dimensions corresponding to an entity identification result for the user, carrying out network searching according to a network query condition corresponding to the searching dimension selected by the user and providing a corresponding searching result for the user, so as to help the user to quickly clarify searching requirements, and further provide the searching result which can meet the actual requirements of the user with pertinence according to the searching dimension selected by the user, thereby solving the problem that the prior art can only return the searching result with a single searching dimension in a searching result page, cannot bear the searching requirements of the multi-dimensional pictures, and well butt-joint the information searching result of the system with the actual searching requirements of the user, the hit rate of the search results is improved, and the use satisfaction of the user is improved.
EXAMPLE six
Fig. 6 is a schematic structural diagram of an information search apparatus according to a sixth embodiment of the present invention, and as shown in fig. 6, the apparatus includes: a search image acquisition module 610, a search dimension providing module 620, and a search result providing module 630, wherein:
a search image acquisition module 610 for acquiring a search image input by a user;
a search dimension providing module 620, configured to perform entity identification on the search image, and provide at least two search dimensions corresponding to an entity identification result to the user, where different search dimensions correspond to different network query conditions;
a search result providing module 630, configured to perform network search according to the network query condition corresponding to the search dimension selected by the user, and provide a corresponding search result to the user.
The embodiment of the invention provides an information searching device, which can simultaneously provide multi-dimensional information contained in a searching picture for a user to select by a technical means of carrying out entity identification on a searching image input by the user, providing at least two searching dimensions corresponding to an entity identification result for the user, carrying out network searching according to a network query condition corresponding to the searching dimension selected by the user and providing a corresponding searching result for the user, thereby helping the user to quickly clarify searching requirements, further providing searching results capable of meeting actual requirements of the user for the user in a targeted manner according to the searching dimension selected by the user independently, solving the problem that the prior art can only return searching results with a single searching dimension in a searching result page, cannot bear the searching requirements of the multi-dimensional pictures, and well butt-jointing the information searching results of a system with the actual searching requirements of the user, the hit rate of the search results is improved, and the use satisfaction of the user is improved.
On the basis of the foregoing embodiments, the search image acquisition module may be specifically configured to: and acquiring a search image input by a user through a search image display interface.
On the basis of the foregoing embodiments, the search dimension providing module may specifically include:
the multi-entity visual display sub-module is used for visually displaying the identified entities in the search image display interface according to the identification positions of at least two entities identified in the search image; wherein different entities correspond to different search dimensions.
On the basis of the foregoing embodiments, the search result providing module may be specifically configured to:
acquiring a target entity selected by the user in the search image display interface;
acquiring a target network query condition corresponding to the target entity;
and performing network search according to the target network query condition, and displaying a corresponding search result at a first set position of the search image display interface.
On the basis of the foregoing embodiments, the multi-entity visualization display sub-module may be further configured to:
determining entity labels respectively corresponding to the entities according to entity types of at least two entities identified in the search image;
and according to the identification positions of at least two entities identified in the search image, visually displaying each identified entity and an entity label corresponding to the entity in the search image display interface.
On the basis of the above embodiments, the method may further include: a default search result providing module to:
after visually displaying the identified entities in the search image display interface according to the identification positions of at least two entities identified in the search image, determining network query conditions respectively corresponding to the entities according to entity types respectively corresponding to the entities;
according to the attribute description data of the user, modifying each network query condition, and performing priority ranking on each entity, wherein the attribute description data of the user comprises: user representation data, and/or user historical search records;
determining a default display entity and a default network query condition corresponding to the default display entity according to the priority ranking result;
displaying the default display entity differently from other entities in the search image display interface;
and performing network search according to the default network query condition, and displaying a corresponding search result at a second set position of the search image display interface.
On the basis of the above embodiments, the method may further include: a full-dimensional option providing module, configured to provide a full-dimensional search option corresponding to the search image to the user after visually displaying, in the search image display interface, each of the identified entities according to the identification positions of the at least two entities identified in the search image;
correspondingly, the search result providing module may be specifically configured to: skipping the search image display interface to a search result display page according to the full-dimension search option selected by the user;
constructing result page sub-clusters corresponding to the search dimensions according to the set number of search results respectively corresponding to the search dimensions;
and displaying each result page sub-cluster in the search result display page.
On the basis of the foregoing embodiments, the result page sub-cluster may include: entity mapping corresponding to the search dimension, result page sub-cluster title and a set number of search results corresponding to the search dimension.
On the basis of the above embodiments, the method may further include: the single-entity multi-dimensional information providing module is used for determining at least two single-entity search dimensions corresponding to a selected entity according to the entity type of the selected entity corresponding to a target result page sub-cluster after each result page sub-cluster is displayed in the search result display page and when the user is detected to execute set interactive operation aiming at the target result page sub-cluster, wherein different single-entity search dimensions correspond to different network query conditions;
and displaying the at least two single entity search dimensions at a third set position of the search result display page to prompt the user to search under the set single entity search dimension for the selected entity.
On the basis of the foregoing embodiments, the search dimension providing module may specifically include:
determining at least two single entity search dimensions corresponding to a single entity according to the entity type of the single entity identified in the search image;
skipping the search image display interface to a search result display page;
and displaying the at least two single entity search dimensions at a fourth set position of the search image display interface to prompt the user to search for the single identified entity under the set single entity search dimension.
On the basis of the above embodiments, the method may further include: the default dimension search result providing module is used for determining a default display dimension according to the entity type of the single entity after the at least two single entity search dimensions are displayed at a fourth set position of the search image display interface;
and acquiring a search result corresponding to the default display dimension, and displaying the search result corresponding to the default display dimension in the search result display page.
The information search device can execute the information search method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executed information search method.
EXAMPLE seven
Fig. 7 is a schematic structural diagram of a computer device according to a seventh embodiment of the present invention. FIG. 7 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in fig. 7 is only an example and should not bring any limitations to the functionality or scope of use of the embodiments of the present invention.
As shown in FIG. 7, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, computer device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be appreciated that although not shown in FIG. 7, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing, such as implementing an information search method provided by an embodiment of the present invention, by executing programs stored in the system memory 28.
That is, the processing unit implements, when executing the program: acquiring a search image input by a user; carrying out entity identification on the search image, and providing at least two search dimensions corresponding to an entity identification result to the user, wherein different search dimensions correspond to different network query conditions; and performing network search according to the network query condition corresponding to the search dimension selected by the user, and providing a corresponding search result for the user.
Example eight
An eighth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the information search method provided in all the inventive embodiments of the present application:
that is, the program when executed by the processor implements: acquiring a search image input by a user; carrying out entity identification on the search image, and providing at least two search dimensions corresponding to an entity identification result to the user, wherein different search dimensions correspond to different network query conditions; and performing network search according to the network query condition corresponding to the search dimension selected by the user, and providing a corresponding search result for the user.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (12)

1. An information search method, comprising:
acquiring a search image input by a user through a search image display interface;
carrying out entity identification on the search image, and providing at least two search dimensions corresponding to an entity identification result to the user, wherein different search dimensions correspond to different network query conditions;
performing network search according to the network query condition corresponding to the search dimension selected by the user, and providing a corresponding search result to the user;
wherein the performing entity recognition on the search image and providing at least two search dimensions corresponding to the entity recognition result to the user comprises:
determining at least two single entity search dimensions corresponding to a single entity according to the entity type of the single entity identified in the search image;
skipping the search image display interface to a search result display page;
and displaying the at least two single entity search dimensions at a fourth set position of the search image display interface so as to prompt the user to search for the single entity under the set single entity search dimension.
2. The method of claim 1, wherein performing entity recognition on the search image and providing at least two search dimensions corresponding to entity recognition results to the user comprises:
visually displaying the identified entities in the search image display interface according to the identification positions of the at least two entities identified in the search image;
wherein different entities correspond to different search dimensions.
3. The method of claim 2, wherein performing a web search according to a web query condition corresponding to the search dimension selected by the user and providing corresponding search results to the user comprises:
acquiring a target entity selected by the user in the search image display interface;
acquiring a target network query condition corresponding to the target entity;
and performing network search according to the target network query condition, and displaying a corresponding search result at a first set position of the search image display interface.
4. The method of claim 2, wherein visually displaying the identified entities in the search image display interface according to the identified locations of the at least two entities identified in the search image, further comprises:
determining entity labels respectively corresponding to the entities according to entity types of at least two entities identified in the search image;
and according to the identification positions of at least two entities identified in the search image, visually displaying each identified entity and an entity label corresponding to the entity in the search image display interface.
5. The method according to any one of claims 2-4, further comprising, after visually presenting each of the identified entities in the search image presentation interface according to the identified locations of the at least two entities identified in the search image:
determining network query conditions respectively corresponding to the entities according to entity types respectively corresponding to the entities;
according to the attribute description data of the user, modifying each network query condition, and performing priority ranking on each entity, wherein the attribute description data of the user comprises: user representation data, and/or user historical search records;
determining a default display entity and a default network query condition corresponding to the default display entity according to the priority ranking result;
displaying the default display entity differently from other entities in the search image display interface;
and performing network search according to the default network query condition, and displaying a corresponding search result at a second set position of the search image display interface.
6. The method of claim 2, further comprising, after visually presenting the identified entities in the search image presentation interface according to the identified locations of the at least two entities identified in the search image:
providing a full-dimensional search option corresponding to the search image to the user;
performing network search according to the network query condition corresponding to the search dimension selected by the user, and providing a corresponding search result to the user, including:
skipping the search image display interface to a search result display page according to the full-dimension search option selected by the user;
constructing result page sub-clusters corresponding to the search dimensions according to the set number of search results respectively corresponding to the search dimensions;
and displaying each result page sub-cluster in the search result display page.
7. The method of claim 6, wherein the result page sub-cluster comprises: entity mapping corresponding to the search dimension, result page sub-cluster title and a set number of search results corresponding to the search dimension.
8. The method of claim 6, further comprising, after displaying each of the result page sub-clusters in the search result presentation page:
when the user is detected to execute set interactive operation aiming at a target result page sub-cluster, determining at least two single entity search dimensions corresponding to a selected entity according to the entity type of the selected entity corresponding to the target result page sub-cluster, wherein different single entity search dimensions correspond to different network query conditions;
and displaying the at least two single entity search dimensions at a third set position of the search result display page to prompt the user to search under the set single entity search dimension for the selected entity.
9. The method of claim 1, further comprising, after displaying the at least two single entity search dimensions at a fourth set position of the search image presentation interface:
determining a default display dimension according to the entity type of the single entity;
and acquiring a search result corresponding to the default display dimension, and displaying the search result corresponding to the default display dimension in the search result display page.
10. An information search apparatus, comprising:
the search image acquisition module is used for acquiring a search image input by a user through a search image display interface;
the search dimension providing module is used for carrying out entity identification on the search image and providing at least two search dimensions corresponding to the entity identification result to the user, wherein different search dimensions correspond to different network query conditions;
the search result providing module is used for carrying out network search according to the network query condition corresponding to the search dimension selected by the user and providing the corresponding search result for the user;
wherein the search dimension providing module is specifically configured to:
determining at least two single entity search dimensions corresponding to a single entity according to the entity type of the single entity identified in the search image; skipping the search image display interface to a search result display page; and displaying the at least two single entity search dimensions at a fourth set position of the search image display interface so as to prompt the user to search for the single entity under the set single entity search dimension.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-9 when executing the program.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-9.
CN201710470126.9A 2017-06-20 2017-06-20 Information searching method, device, equipment and storage medium Active CN107229741B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710470126.9A CN107229741B (en) 2017-06-20 2017-06-20 Information searching method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710470126.9A CN107229741B (en) 2017-06-20 2017-06-20 Information searching method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN107229741A CN107229741A (en) 2017-10-03
CN107229741B true CN107229741B (en) 2021-12-10

Family

ID=59935562

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710470126.9A Active CN107229741B (en) 2017-06-20 2017-06-20 Information searching method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN107229741B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110020086B (en) * 2017-12-22 2021-10-26 中国移动通信集团浙江有限公司 User portrait query method and device
CN108388397A (en) * 2018-02-13 2018-08-10 维沃移动通信有限公司 A kind of information processing method and terminal
CN108520029A (en) * 2018-03-27 2018-09-11 四川斐讯信息技术有限公司 A kind of method scanned for based on picture and location information, server and system
CN109040461A (en) * 2018-08-29 2018-12-18 优视科技新加坡有限公司 A kind of method and device for business processing based on Object identifying
CN111753181A (en) * 2019-03-28 2020-10-09 北京京东尚科信息技术有限公司 Image-based search method, apparatus, server, client and medium
CN110765296A (en) * 2019-10-23 2020-02-07 京东方科技集团股份有限公司 Image search method, terminal device and storage medium
CN111274431A (en) * 2020-02-04 2020-06-12 浙江大华技术股份有限公司 Image retrieval processing method and device
CN112035693B (en) * 2020-08-31 2024-10-29 维沃移动通信有限公司 Image display method, device, electronic device and readable storage medium
CN112957732B (en) * 2021-04-08 2023-03-31 腾讯科技(深圳)有限公司 Searching method, device, terminal and storage medium

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7739221B2 (en) * 2006-06-28 2010-06-15 Microsoft Corporation Visual and multi-dimensional search
US20100313274A1 (en) * 2008-10-07 2010-12-09 Apteryx, Inc. Image server with multiple image confidentiality ports
US20110128288A1 (en) * 2009-12-02 2011-06-02 David Petrou Region of Interest Selector for Visual Queries
EP2791780A4 (en) * 2011-12-15 2016-05-11 Yahoo Inc Systems and methods involving features of search and/or search integration
CN104679783B (en) * 2013-11-29 2019-08-02 北京搜狗信息服务有限公司 A kind of network search method and device
CN104111989B (en) * 2014-07-02 2017-12-22 百度在线网络技术(北京)有限公司 The offer method and apparatus of search result
CN106326288B (en) * 2015-06-30 2019-12-03 阿里巴巴集团控股有限公司 Image search method and device

Also Published As

Publication number Publication date
CN107229741A (en) 2017-10-03

Similar Documents

Publication Publication Date Title
CN107229741B (en) Information searching method, device, equipment and storage medium
US10642892B2 (en) Video search method and apparatus
US10032072B1 (en) Text recognition and localization with deep learning
US10133951B1 (en) Fusion of bounding regions
US10810252B2 (en) Searching using specific attributes found in images
CN112291609A (en) Video display and push method, device, storage medium and system thereof
CN111782977B (en) Point-of-interest processing method, device, equipment and computer readable storage medium
US9652534B1 (en) Video-based search engine
CN108776676B (en) Information recommendation method and device, computer readable medium and electronic device
WO2019144850A1 (en) Video content-based video search method and video search apparatus
CN111309200B (en) Method, device, equipment and storage medium for determining extended reading content
US11704357B2 (en) Shape-based graphics search
EP2587826A1 (en) Extraction and association method and system for objects of interest in video
US20150339348A1 (en) Search method and device
US10891019B2 (en) Dynamic thumbnail selection for search results
CN112052352B (en) Video ordering method, device, server and storage medium
CN112487242A (en) Method and device for identifying video, electronic equipment and readable storage medium
US11514231B2 (en) Web browser extension for linking images to webpages
EP3910496B1 (en) Search method and device
CN105095341A (en) Search methods and devices
US20180046631A1 (en) Display apparatus and method for controlling the same
US20200074218A1 (en) Information processing system, information processing apparatus, and non-transitory computer readable medium
CN111542817A (en) Information processing device, video retrieval method, generation method, and program
US10489460B2 (en) Method and apparatus for providing local search suggestion
CN103377270A (en) Image searching method and system

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