Resource search method, device and electronic device

Abstract

The present disclosure relates to a resource search method, device and electronic device, and in particular to the field of communication technology. It includes: receiving a user's search request through a first external interface, the first external interface is a data interface in a first version recommendation system, and the data format of the search request is a first format corresponding to the first version recommendation system; converting the data format of the search request from the first format to a second format corresponding to the second version recommendation system; according to the search request in the second format, adopting a multi-channel recommendation strategy corresponding to the second version recommendation system, and determining the recommended resource information in the second format; wherein the multi-channel recommendation strategy is obtained after updating the single-channel recommendation strategy of the first version recommendation system; converting the recommended resource information in the second format to the recommended resource information in the first format, and outputting the recommended resource information in the first format through the first external interface. The embodiment of the present disclosure is used to solve the problem of incompatibility between the formats of the search request and the search results.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a resource search method, device and electronic device. Background Art

[0002] Currently, users can use the search system in the APP or device to search for resources. The search system is usually updated to optimize the recommendation strategy of the recommendation system. However, if the external interface is updated together during this process, it may cause the external interface to receive search requests from outside the search system, or return search results to the outside. There may be incompatibility between the formats of the search request and the search results. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the technical solutions provided by the embodiments of the present disclosure are as follows:

[0004] In a first aspect, a resource search method is provided, comprising: receiving a user's search request through a first external interface, the first external interface being a data interface in a first version recommendation system, and the data format of the search request being a first format corresponding to the first version recommendation system;

[0005] Converting the data format of the search request from the first format to a second format corresponding to the second version of the recommendation system;

[0006] According to the search request in the second format, the recommended resource information in the second format is determined by adopting the multi-channel recommendation strategy corresponding to the second version recommendation system; wherein the multi-channel recommendation strategy is obtained after updating the single-channel recommendation strategy of the first version recommendation system;

[0007] The recommended resource information in the second format is converted into recommended resource information in a first format, and the recommended resource information in the first format is output through the first external interface.

[0008] As an optional implementation of the embodiment of the present disclosure, the search request includes a source identifier for representing a user terminal that issues the search request, and the source identifier includes a first source identifier and a second source identifier;

[0009] Receiving a user's search request through the first external interface includes:

[0010] When the search request includes the first source identifier, receiving the search request through the first external interface;

[0011] The resource search method further includes:

[0012] When the search request includes the second source identifier, the search request is received through the second external interface, and the data format of the search request is the second format corresponding to the second version recommendation system; based on the search request in the second format, the multi-channel recommendation strategy corresponding to the second version recommendation system is adopted to determine the recommended resource information in the second format, and the recommended resource information in the second format is output through the second external interface.

[0013] As an optional implementation of the embodiment of the present disclosure, the determining, according to the search request in the second format, the recommended resource information in the second format by using the target recommendation strategy corresponding to the second version recommendation system includes:

[0014] determining a search keyword according to the search request in the second format;

[0015] Determine from a database the first resource information in the second format corresponding to the search keyword;

[0016] Obtain a user portrait tag of the user corresponding to the search request;

[0017] Determine at least one first recommended resource matching the user portrait tag from the first resource information;

[0018] Determine at least one second recommended resource having a correlation parameter with the at least one first resource greater than a preset parameter;

[0019] The at least one first recommended resource and the at least one second recommended resource are determined as target recommended resources, and resource recommendation information in the second format is generated, where the resource recommendation information is used to indicate the target recommended resource.

[0020] As an optional implementation of the embodiment of the present disclosure, determining the at least one first recommended resource and the at least one second recommended resource as target recommended resources includes:

[0021] From the at least one first recommended resource and the at least one second recommended resource, determine a resource whose resource heat parameter is greater than a preset heat parameter as the target recommended resource;

[0022] The resource heat parameter includes at least one of the following:

[0023] Number of searches, number of plays, and resource evaluation parameters.

[0024] As an optional implementation of the embodiment of the present disclosure, the step of determining a resource whose resource heat parameter is greater than a preset heat parameter as the target recommended resource includes:

[0025] Determine the total number of resources whose resource heat parameter is greater than a preset heat parameter;

[0026] If the total number of resources whose resource heat parameter is greater than the preset heat parameter is greater than the preset number, then from the resources whose resource heat parameter is greater than the preset heat parameter, resources that meet the following screening conditions are determined as the target recommended resources;

[0027] The screening conditions include at least one of the following:

[0028] The video has been recommended to the user, but the user has not triggered the playback;

[0029] Not recommended to the user.

[0030] As an optional implementation of the embodiment of the present disclosure,

[0031] Before outputting the recommended resource information in the first format through the first external interface, the method includes:

[0032] Obtaining the corresponding relationship between multiple recommendation tags and multiple user terminals;

[0033] Determining that the recommended resource information in the first format matches a first recommended tag, where the first recommended tag is one of the multiple recommended tags;

[0034] Determining a target user terminal corresponding to the first recommendation tag according to the corresponding relationship; and outputting the recommended resource information in the first format through the first external interface includes:

[0035] The recommended resource information in the first format is sent to the target user terminal through the first external interface.

[0036] As an optional implementation of the embodiment of the present disclosure, determining the target user terminal corresponding to the first recommended tag according to the corresponding relationship includes:

[0037] Determining at least two user terminals corresponding to the first recommendation tag according to the corresponding relationship;

[0038] The user terminal with the highest output priority among the at least two user terminals is used as the target user terminal;

[0039] The output priority is a priority for displaying the content matched by the first recommendation tag.

[0040] In a second aspect, a resource search device is provided, comprising:

[0041] A first external interface, used to receive a user's search request, the first external interface is a data interface in the first version recommendation system, and the data format of the search request is a first format corresponding to the first version recommendation system;

[0042] a format conversion module, configured to convert the data format of the search request from the first format to a second format corresponding to the second version of the recommendation system;

[0043] A second version recommendation module, configured to determine the recommended resource information in the second format according to the search request in the second format by adopting a multi-channel recommendation strategy corresponding to the second version recommendation system; wherein the multi-channel recommendation strategy is obtained by updating the single-channel recommendation strategy of the first version recommendation system;

[0044] The format conversion module is further used to convert the recommended resource information in the second format into the recommended resource information in the first format;

[0045] The first external interface is also used to output the recommended resource information in the first format.

[0046] As an optional implementation of the embodiment of the present disclosure, the search request includes a source identifier for representing a user terminal that issues the search request, and the source identifier includes a first source identifier and a second source identifier;

[0047] The first external interface is specifically used for:

[0048] When the search request includes the first source identifier, receiving the search request through the first external interface;

[0049] The device also includes:

[0050] A second external interface, used for receiving the search request when the search request includes the second source identifier, wherein the data format of the search request is a second format corresponding to the second version recommendation system;

[0051] The second version recommendation module is used to determine the recommended resource information in the second format according to the search request in the second format by adopting a multi-channel recommendation strategy corresponding to the second version recommendation system;

[0052] The second external interface is further used to output the recommended resource information in the second format through the second external interface.

[0053] As an optional implementation of the embodiment of the present disclosure, the second version recommendation module is specifically used to:

[0054] determining a search keyword according to the search request in the second format;

[0055] Determine from a database the first resource information in the second format corresponding to the search keyword;

[0056] Obtain a user portrait tag of the user corresponding to the search request;

[0057] Determine at least one first recommended resource matching the user portrait tag from the first resource information;

[0058] Determine at least one second recommended resource having a correlation parameter with the at least one first resource greater than a preset parameter;

[0059] The at least one first recommended resource and the at least one second recommended resource are determined as target recommended resources, and resource recommendation information in the second format is generated, where the resource recommendation information is used to indicate the target recommended resource.

[0060] As an optional implementation of the embodiment of the present disclosure, the second version recommendation module is specifically used to:

[0061] From the at least one first recommended resource and the at least one second recommended resource, determine a resource whose resource heat parameter is greater than a preset heat parameter as the target recommended resource;

[0062] The resource heat parameter includes at least one of the following:

[0063] Number of searches, number of plays, and resource evaluation parameters.

[0064] As an optional implementation of the embodiment of the present disclosure, the second version recommendation module is specifically used to:

[0065] Determine the total number of resources whose resource heat parameter is greater than a preset heat parameter;

[0066] If the total number of resources whose resource heat parameter is greater than the preset heat parameter is greater than the preset number, then from the resources whose resource heat parameter is greater than the preset heat parameter, resources that meet the following screening conditions are determined as the target recommended resources;

[0067] The screening conditions include at least one of the following:

[0068] The video has been recommended to the user, but the user has not triggered the playback;

[0069] Not recommended to the user.

[0070] As an optional implementation of the embodiment of the present disclosure, the device further includes:

[0071] Get modules for:

[0072] Obtaining the corresponding relationship between multiple recommendation tags and multiple user terminals;

[0073] Determining that the recommended resource information in the first format matches a first recommended tag, where the first recommended tag is one of the multiple recommended tags;

[0074] According to the corresponding relationship, a target user terminal corresponding to the first recommendation tag is determined; and the first external interface is specifically used to:

[0075] The recommended resource information in the first format is sent to the target user terminal through the first external interface.

[0076] As an optional implementation of the embodiment of the present disclosure, the acquisition module is specifically used to:

[0077] Determining at least two user terminals corresponding to the first recommendation tag according to the corresponding relationship;

[0078] The user terminal with the highest output priority among the at least two user terminals is used as the target user terminal;

[0079] The output priority is a priority for displaying the content matched by the first recommendation tag.

[0080] Compared with the prior art, the technical solution provided by the disclosed embodiment has the following advantages: when a search request is received through the first external interface in the first version recommendation system, the data format of the search request will be converted from the first format to the second format, and after the conversion, the recommendation strategy in the second version recommendation system will be used to determine the recommended resource information in the second format corresponding to the search request, and before outputting the recommended resource information through the first external interface, the recommended resource information in the second format will be converted into the recommended resource information in the first format. In this way, through the format conversion, the first external interface in the original first version recommendation system can be used to receive the search request and output the search resource, and the recommendation strategy in the second version recommendation system can be used when searching. In this way, there is no need to set up a corresponding first external interface separately for the second version recommendation system, and the multi-channel recommendation strategy obtained after updating the single-channel recommendation strategy of the first version recommendation system can be used for resource search, so that the updated recommendation strategy can be used for resource search on the basis of reducing development costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0082] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0083] Figure 1 A schematic diagram of the architecture of a first version of a recommendation system provided by an embodiment of the present disclosure;

[0084] Figure 2 A schematic diagram of the architecture of a search server that applies the resource search method provided by an embodiment of the present disclosure;

[0085] Figure 3 A schematic diagram of a resource search method provided by an embodiment of the present disclosure;

[0086] Figure 4 A structural block diagram of a resource search device provided by an embodiment of the present disclosure;

[0087] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0088] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0089] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0090] In the related art, there is a first version recommendation system, which is mainly used on old versions of smart speakers and other voice interaction devices, such as Figure 1 As shown, the first version of the recommendation system includes the following five modules when applied:

[0091] (1) Speech recognition, which is used to recognize the received speech signal and obtain the corresponding speech content;

[0092] (2) Natural Language Processing (NLP): the user performs natural language processing on the voice content to obtain a processed search request. For example, performing natural language processing on the voice content may refer to adjusting the word order of the voice content and performing error correction processing on the voice content.

[0093] (3) Recommendation engine, which can receive search requests and generate corresponding recommended resource information by calling content indexing and resource search modules, and return it to the external caller;

[0094] (4) Content indexer: First, create an index and store data in the remote dictionary service (redis) in the content indexer. When the recommendation engine receives a search request, it calls the content indexer, determines the tag index through the search request, and determines the corresponding data in redis based on the tag index, retrieves the data, and returns it to the recommendation engine.

[0095] (5) Resource search: When the recommendation engine receives a search request, it calls resource-search, which retrieves the data from the search engine and returns it to the recommendation engine.

[0096] In the disclosed embodiment, the first version recommendation system mainly involves three modules: recommendation engine, content indexing and resource search. The data format of speech recognition, natural language processing and the first version recommendation system are all in the first format.

[0097] In the related technology, after updating the single-channel recommendation strategy of the first-version recommendation system, a second-version recommendation system with a multi-channel recommendation strategy is obtained. This recommendation system can be applied to new versions of applications or smart devices, and the data formats between the second-version recommendation systems are all in the second format; if you want to update the second-version recommendation system and apply it to the above-mentioned old version of voice interaction devices such as smart speakers, you need to change the data format of voice recognition, natural language processing and the first-version recommendation system as a whole, which will consume update resources.

[0098] The recommendation strategy used in the first version of the recommendation system was not rich enough, but in the second version of the recommendation system, the multi-channel recall and intelligent recommendation (Exploitation & Exploration, EE) algorithm was applied to implement the multi-channel recommendation strategy, making the recommended content richer, more diverse and more suitable for users. The EE algorithm will not only filter and recommend content based on the information exposed by users, but also explore the content that users may be interested in.

[0099] The resource search method provided by the embodiment of the present disclosure can make the recommendation engine of the first version recommendation system applicable to the content index and resource search of the second version recommendation system, so that the multi-channel recommendation strategy can be applied to the recommendation engine of the first version recommendation system. Since the recommendation engine of the first version recommendation system will be called by an external module, the format of the search request (request) and the returned resource information (response) transmitted by the first external interface cannot be changed, and the external request and response formats of the recommendation engine of the first version recommendation system and the recommendation engine of the second version recommendation system are different, so the external request and response formats of the recommendation engine of the first version recommendation system and the recommendation engine of the second version recommendation system need to be synchronized through format conversion.

[0100] The above-mentioned application of the multi-channel recommendation strategy to the recommendation engine of the first version recommendation system can be understood as: the multi-channel recommendation strategy is updated in the first version recommendation system, so that when the recommendation engine of the first version recommendation system calls the content index and resource search of the second version recommendation system, the multi-channel recommendation strategy can be used for resource recommendation; the above-mentioned application of the multi-channel recommendation strategy to the recommendation engine of the first version recommendation system can also be understood as: in the content index and resource search of the second version recommendation system, the multi-channel recommendation strategy is updated, so that when the recommendation engine of the first version recommendation system calls the content index and resource search of the second version recommendation system, the multi-channel recommendation strategy is applied for resource recommendation through content index and resource search.

[0101] like Figure 2 As shown, a search server that applies the resource search method provided by the embodiment of the present disclosure is a search server, wherein the search server includes a first version recommendation system and a second version recommendation system, wherein after a search request is input through the first external interface of the first version recommendation system, the search engine of the first version recommendation system receives the search request and sends the search request to a format conversion module, the format conversion module converts the search request from the first format to the second format, and obtains recommended resources according to the search request in the second format and the updated multi-channel recommendation strategy by calling the content index and resource search module in the recommendation system of the second version recommendation system, and returns the recommended resource information to the format conversion module, after the format conversion module converts the recommended resource information from the second format to the first format, it is finally output through the first external interface of the first version recommendation system.

[0102] The resource search method provided in the embodiments of the present disclosure can be applied to a resource search device or an electronic device, wherein the resource search device can be a functional module or a functional entity in an electronic device that implements the resource search method, wherein the electronic device can be a search server or other device with a search function.

[0103] like Figure 3 FIG. 1 is a flow chart of a resource search method provided by an embodiment of the present disclosure, the method comprising:

[0104] 301. Receive a user's search request through a first external interface.

[0105] Among them, the first external interface is the data interface in the first version recommendation system. Taking the application of the resource search method in the search server as an example, the external module can transmit data to the search server and receive data output by the search server by calling the first external interface.

[0106] Since the first external interface is a data interface in the first version recommendation system, the data format of the search request received through the first external interface is the first format corresponding to the first version recommendation system.

[0107] In the disclosed embodiment, different interfaces may be used to receive search requests from different user terminals, and different methods may be used to perform resource searches.

[0108] In some embodiments, the search request includes a source identifier for representing a user terminal that issues the search request, and the source identifier includes a first source identifier and a second source identifier;

[0109] When the search request includes the first source identifier, receiving the search request through the first external interface;

[0110] When the search request includes a second source identifier, the search request is received through the second external interface, and the data format of the search request is the second format corresponding to the second version recommendation system; based on the search request in the second format, the multi-channel recommendation strategy corresponding to the second version recommendation system is adopted to determine the recommended resource information in the second format, and the recommended resource information in the second format is output through the second external interface.

[0111] Among them, if the search request includes a first source identifier, it means that the user terminal indicated by the source of the search request is applicable to the first version recommendation system, and its data format is the first format; if the search request includes a second source identifier, it means that the user terminal indicated by the source of the search request is applicable to the second version recommendation system, and its data format is the second format.

[0112] In some embodiments, assuming that the first version recommendation system is applicable to a voice interaction device, when the data source of the search request is the voice interaction device, the search request can be received through the first external interface, and subsequent method steps are performed to implement the resource search method in the embodiment of the present disclosure.

[0113] In some embodiments, assuming that the second version recommendation system is applicable to an application, when the data source of the search request is the application, the search request can be received through the second external interface, and the multi-channel recommendation strategy corresponding to the second version recommendation system can be adopted to determine the recommended resource information in the second format, and the obtained resource recommendation information can be returned to the application through the second external interface.

[0114] In the above embodiment, since the user terminal carrying the second source identifier in the search request is suitable for the second version of the recommendation system, such search request can be directly received through the second external interface, and the recommended resource information can be determined through the multi-path recommendation strategy in the second recommendation system without the need for format conversion. In this way, since the user terminal source is distinguished, search requests from different sources can be classified and processed, ensuring that search requests from different types of user terminal sources can obtain recommended resource information through the resource search method provided in the embodiment of the present disclosure, which can better cover a variety of scenarios.

[0115] 302. Convert the data format of the search request from the first format to a second format corresponding to the second version recommendation system.

[0116] In order to subsequently use the multi-channel recommendation strategy corresponding to the second version recommendation system, for example, the format of the search request needs to be converted into a second format compatible with the second version recommendation system. Figure 2 The format conversion module shown in converts the data format of the search request from the first format to the second format.

[0117] 303. According to the search request in the second format, adopt a multi-channel recommendation strategy corresponding to the second version recommendation system to determine recommended resource information in the second format.

[0118] The multi-channel recommendation strategy is obtained by updating the single-channel recommendation strategy of the first version recommendation system.

[0119] In some embodiments, the above 303 can be implemented by the following steps:

[0120] 303a. Determine a search keyword according to the search request in the second format.

[0121] 303b. Determine first resource information in a second format corresponding to the search keyword from a database.

[0122] 303c. Obtain a user portrait tag of the user corresponding to the search request.

[0123] 303d. Determine at least one first recommended resource that matches the user portrait tag from the first resource information.

[0124] The user portrait tag may be a user interest tag determined according to resource information of the user history record. The user portrait tag may be a primary or multi-level user portrait tag, and the user portrait tag may reflect the user's preference and the user's preference.

[0125] In some embodiments, the user portrait tag may include two levels of portrait tags: interest topics and interest tags. For example, interest topics may include: videos, movies, TV series, documentaries, songs, etc. Interest tags may include: science fiction, romance, comedy, war, military, police and gangsters, etc.

[0126] 303e. Determine at least one second recommended resource whose correlation parameter with the at least one first resource is greater than a preset parameter.

[0127] Among them, the above preset parameters can be set according to actual conditions and are not limited in the embodiments of the present disclosure.

[0128] In the disclosed embodiment, the first recommended resource is determined based on the search keywords and user portrait tags, and the second recommended resource is determined based on the first recommended resource. This recommendation method not only considers the user's preferences to recommend resources, but also can explore the user's preferences to recommend related resources, thus making the recommended content richer.

[0129] 303f. Determine at least one first recommended resource and at least one second recommended resource as target recommended resources.

[0130] 304g. Generate resource recommendation information in a second format.

[0131] The resource recommendation information is used to indicate the target recommended resource.

[0132] In some embodiments, from at least one first-path recommended resource and at least one second-path recommended resource, a resource having a resource heat parameter greater than a preset heat parameter is determined as a target recommended resource.

[0133] Among them, the above-mentioned resource heat parameter can represent the popularity of the resource. The larger the resource heat parameter is, the higher the popularity is; the smaller the resource heat parameter is, the lower the popularity is.

[0134] The resource heat parameters include but are not limited to at least one of the following (1), (2) and (3):

[0135] (1) Number of resource searches;

[0136] The number of searches for each resource in at least one first-path recommended resource and at least one second-path recommended resource may be determined based on the big data.

[0137] (2) the number of times the resource is played;

[0138] The number of times each of the at least one first-path recommended resource and the at least one second-path recommended resource is played may be determined based on the big data.

[0139] (3) Resource evaluation parameters of resources.

[0140] For some film and television resources or song resources, there will be evaluation information and evaluation scores given by users, and resource evaluation parameters can be determined based on the evaluation information, evaluation scores, etc. The resource search method provided in the above embodiment screens out recommended resources with higher popularity.

[0141] In some embodiments, resources whose resource heat parameters are greater than preset heat parameters are determined as target recommended resources. This can be achieved in the following way: determine the total number of resources whose resource heat parameters are greater than the preset heat parameters; if the total number of resources whose resource heat parameters are greater than the preset heat parameters is greater than the preset number, then from the resources whose resource heat parameters are greater than the preset heat parameters, determine the resources that meet the following screening conditions and determine them as target recommended resources.

[0142] The above screening conditions include but are not limited to at least one of (a) and (b):

[0143] (a) The video has been recommended to the user, but the user has not triggered the playback;

[0144] (b) Not recommended to users.

[0145] In the above embodiment, when the number of recommended resources with higher popularity exceeds a preset number, it is possible to further determine recommended resources that have not been played and / or recommended resources that have not been recommended based on the previous recommendation records and playback records for the current search user. This can avoid repeatedly recommending resources to the user and achieve more accurate resource recommendations.

[0146] 304. Convert the recommended resource information in the second format into recommended resource information in the first format.

[0147] 305. Output the recommended resource information in the first format through the first external interface.

[0148] In order to facilitate the first external interface to return the recommended resource information to the external module, it is necessary to first convert the recommended resource information in the second format into the recommended resource information in the first format. Figure 2 The format conversion module shown in converts the format of the recommended resource information from the second format to the first format, and outputs the recommended resource information in the first format through the first external interface.

[0149] The resource search method provided by the embodiment of the present disclosure, when receiving a search request through the first external interface in the first version recommendation system, will convert the data format of the search request from the first format to the second format, and use the recommendation strategy in the second version recommendation system after the conversion to determine the recommended resource information in the second format corresponding to the search request, and before outputting the recommended resource information through the first external interface, first convert the recommended resource information in the second format into the recommended resource information in the first format. In this way, through the format conversion, the first external interface in the original first version recommendation system can be used to receive the search request and output the search resources, and the recommendation strategy in the second version recommendation system can be used when searching. In this way, there is no need to set up a corresponding first external interface separately for the second version recommendation system, and the multi-channel recommendation strategy obtained after updating the single-channel recommendation strategy of the first version recommendation system can be used for resource search, so that the updated recommendation strategy can be used for resource search on the basis of reducing development costs.

[0150] The resource search method provided in the embodiments of the present disclosure may be applied in a scenario including multiple smart devices, for example, a smart home scenario.

[0151] Exemplarily, assuming that among multiple smart devices, after a search request is issued by an application in a first device, after the search server performs a resource search according to the resource search method provided by an embodiment of the present disclosure, the obtained recommended resource information can be fed back to a target smart device associated with the application that matches the recommended resource information.

[0152] The target smart device may be a smart device that matches the recommendation tag to which the recommended resource information belongs. In a smart home scenario, the first device may be a mobile phone, and other smart devices may be a TV, a projector, a refrigerator, a smart bracelet, or a smart speaker. In the disclosed embodiment, a smart device may be equivalent to a user terminal, and may refer to a terminal device used by a user.

[0153] In some embodiments, before the above 305 outputs the recommended resource information in the first format through the first external interface, the correspondence between multiple recommendation tags and multiple user terminals can be obtained to determine whether the recommended resource information in the first format matches the first recommendation tag, and the target user terminal is determined based on the correspondence.

[0154] Furthermore, the above 305 may specifically be: sending the recommended resource information in the first format to the target user terminal through the first external interface.

[0155] It is understandable that before outputting the recommended resource information in the second format through the second external interface, the method in the above embodiment can also be executed to determine the target user terminal for outputting the recommended resource information in the second format, which will not be repeated here.

[0156] Exemplarily, it is assumed that the recommended tags corresponding to the smart speaker may include: music; the recommended tags corresponding to the television and projector may include: movies; the recommended tags corresponding to the refrigerator may be: food. For song resource information, it can be output to the smart speaker; for movie resource information, it can be output to the television, projector, etc.; for recipe, diet and health resource information, it can be output to the refrigerator. The above-mentioned target user terminals may be one or more. In some embodiments, the target user terminal corresponding to the first recommended tag is determined according to the corresponding relationship, including: determining at least two user terminals corresponding to the first recommended tag according to the corresponding relationship; taking the user terminal with the highest output priority among the at least two user terminals as the target user terminal; wherein the output priority is the priority for displaying the content corresponding to the first recommended tag.

[0157] When multiple matching user terminals are determined based on the recommendation tags, the user terminal with the highest priority can be further selected as the target user terminal according to the priority of displaying the content corresponding to the first recommendation tag to output the corresponding resource recommendation information.

[0158] The above-mentioned recommendation tags can represent the resource type of the recommended resource information. In the embodiment of the present disclosure, the correspondence between multiple recommendation tags and multiple user terminals is pre-set so that the recommended resource information of different resource types can be mapped to the corresponding devices for output. In this way, combined with the actual user use scenario of the user terminal, the accurate output of the recommended resource information can be further realized.

[0159] like Figure 4 As shown, an embodiment of the present disclosure provides a resource search device, the device comprising:

[0160] A first external interface 401 is used to receive a user's search request. The first external interface is a data interface in the first version recommendation system. The data format of the search request is a first format corresponding to the first version recommendation system.

[0161] A format conversion module 402, configured to convert the data format of the search request from the first format to a second format corresponding to the second version recommendation system;

[0162] The second version recommendation module 403 is used to determine the recommended resource information in the second format according to the search request in the second format by adopting the multi-channel recommendation strategy corresponding to the second version recommendation system; wherein the multi-channel recommendation strategy is obtained by updating the single-channel recommendation strategy of the first version recommendation system;

[0163] The format conversion module 402 is further used to convert the recommended resource information in the second format into the recommended resource information in the first format;

[0164] The first external interface 401 is also used to output the recommended resource information in the first format.

[0165] As an optional implementation of the embodiment of the present disclosure, the search request includes a source identifier for representing a user terminal that issues the search request, and the source identifier includes a first source identifier and a second source identifier;

[0166] The first external interface 401 is specifically used for:

[0167] When the search request includes the first source identifier, receiving the search request through the first external interface;

[0168] like Figure 4 As shown, the device also includes:

[0169] The second external interface 404 is used to receive the search request when the search request includes the second source identifier, and the data format of the search request is a second format corresponding to the second version recommendation system;

[0170] The second version recommendation module 403 is further configured to determine the recommended resource information in the second format by adopting a multi-channel recommendation strategy corresponding to the second version recommendation system according to the search request in the second format;

[0171] The second external interface 404 is further used to output the recommended resource information in the second format.

[0172] As an optional implementation of the embodiment of the present disclosure, the second version recommendation module 403 is specifically configured to:

[0173] determining a search keyword according to the search request in the second format;

[0174] Determine from a database the first resource information in the second format corresponding to the search keyword;

[0175] Obtain a user portrait tag of the user corresponding to the search request;

[0176] Determine at least one first recommended resource matching the user portrait tag from the first resource information;

[0177] Determine at least one second recommended resource having a correlation parameter with the at least one first resource greater than a preset parameter;

[0178] The at least one first recommended resource and the at least one second recommended resource are determined as target recommended resources, and resource recommendation information in the second format is generated, where the resource recommendation information is used to indicate the target recommended resource.

[0179] As an optional implementation of the embodiment of the present disclosure, the second version recommendation module 403 is specifically configured to:

[0180] From the at least one first recommended resource and the at least one second recommended resource, determine a resource whose resource heat parameter is greater than a preset heat parameter as the target recommended resource;

[0181] The resource heat parameter includes at least one of the following:

[0182] Number of searches, number of plays, and resource evaluation parameters.

[0183] As an optional implementation of the embodiment of the present disclosure, the second version recommendation module 403 is specifically configured to:

[0184] Determine the total number of resources whose resource heat parameter is greater than a preset heat parameter;

[0185] If the total number of resources whose resource heat parameter is greater than the preset heat parameter is greater than the preset number, then from the resources whose resource heat parameter is greater than the preset heat parameter, resources that meet the following screening conditions are determined as the target recommended resources;

[0186] The screening conditions include at least one of the following:

[0187] The video has been recommended to the user, but the user has not triggered the playback;

[0188] Not recommended to the user.

[0189] As an optional implementation of the embodiment of the present disclosure, Figure 4 As shown, the device also includes:

[0190] The acquisition module 405 is used to: acquire the corresponding relationship between multiple recommendation tags and multiple user terminals;

[0191] Determining that the recommended resource information in the first format matches a first recommended tag, where the first recommended tag is one of the multiple recommended tags;

[0192] Determining a target user terminal corresponding to the first recommendation tag according to the corresponding relationship;

[0193] The first external interface 401 is specifically used to send the recommended resource information in the first format to the target user terminal through the first external interface.

[0194] As an optional implementation of the embodiment of the present disclosure, the acquisition module 405 is specifically used to:

[0195] Determining at least two user terminals corresponding to the first recommendation tag according to the corresponding relationship;

[0196] The user terminal with the highest output priority among the at least two user terminals is used as the target user terminal;

[0197] The output priority is a priority for displaying the content matched by the first recommendation tag.

[0198] like Figure 5 As shown, the embodiment of the present disclosure provides an electronic device, which includes: a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501, and the computer program implements each process of the resource search method in the above method embodiment when executed by the processor 501. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.

[0199] An embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the various processes of the resource search method in the above method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0200] The computer readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0201] An embodiment of the present invention provides a computer program product, which stores a computer program. When the computer program is executed by a processor, the various processes of the resource search method in the above method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0202] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0203] In the present disclosure, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0204] In the present disclosure, memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0205] In the present disclosure, computer-readable media include permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0206] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0207] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A resource search method, characterized in that: include: When the search request includes a first source identifier, the search request is received through a first external interface, the first external interface is a data interface in a first version recommendation system, the data format of the search request is a first format corresponding to the first version recommendation system, and the first version recommendation system is applicable to a voice interaction device; wherein the search request includes a source identifier for representing a user terminal that issues the search request, and the source identifier includes a first source identifier and a second source identifier; converting the data format of the search request from the first format to a second format corresponding to a second version of the recommendation system, where the second version of the recommendation system is applicable to the application; According to the search request in the second format, the recommended resource information in the second format is determined by adopting the multi-channel recommendation strategy corresponding to the second version recommendation system; wherein the multi-channel recommendation strategy is obtained after updating the single-channel recommendation strategy of the first version recommendation system; converting the recommended resource information in the second format into recommended resource information in the first format, and outputting the recommended resource information in the first format through the first external interface; When the search request includes the second source identifier, the search request is received through the second external interface, and the data format of the search request is the second format corresponding to the second version recommendation system; based on the search request in the second format, the multi-channel recommendation strategy corresponding to the second version recommendation system is adopted to determine the recommended resource information in the second format, and the recommended resource information in the second format is output through the second external interface.

2. The method according to claim 1, characterized in that The step of determining the recommended resource information in the second format by adopting a target recommendation strategy corresponding to the second version recommendation system according to the search request in the second format includes: determining a search keyword according to the search request in the second format; Determine from a database the first resource information in the second format corresponding to the search keyword; Obtain a user portrait tag of the user corresponding to the search request; Determine at least one first recommended resource matching the user portrait tag from the first resource information; Determine at least one second recommended resource having a correlation parameter with the at least one first recommended resource greater than a preset parameter; The at least one first recommended resource and the at least one second recommended resource are determined as target recommended resources, and resource recommendation information in the second format is generated, where the resource recommendation information is used to indicate the target recommended resource.

3. The method according to claim 2, characterized in that The step of determining the at least one first recommended resource and the at least one second recommended resource as target recommended resources includes: From the at least one first recommended resource and the at least one second recommended resource, determine a resource whose resource heat parameter is greater than a preset heat parameter as the target recommended resource; The resource heat parameter includes at least one of the following: Number of searches, number of plays, and resource evaluation parameters.

4. The method according to claim 3, characterized in that The step of determining a resource whose resource heat parameter is greater than a preset heat parameter as the target recommended resource includes: Determine the total number of resources whose resource heat parameter is greater than a preset heat parameter; If the total number of resources whose resource heat parameter is greater than the preset heat parameter is greater than the preset number, then from the resources whose resource heat parameter is greater than the preset heat parameter, determine the resources that meet the following screening conditions and recommend them as the target resources; The screening conditions include at least one of the following: The video has been recommended to the user, but the user has not triggered the playback; Not recommended to the user.

5. The method according to claim 1, characterized in that: Before outputting the recommended resource information in the first format through the first external interface, the method includes: Obtaining the corresponding relationship between multiple recommendation tags and multiple user terminals; Determining that the recommended resource information in the first format matches a first recommended tag, where the first recommended tag is one of the multiple recommended tags; Determining a target user terminal corresponding to the first recommendation tag according to the corresponding relationship; The outputting the recommended resource information in the first format through the first external interface includes: The recommended resource information in the first format is sent to the target user terminal through the first external interface.

6. The method according to claim 5, characterized in that The determining, according to the corresponding relationship, a target user terminal corresponding to the first recommendation tag includes: Determining at least two user terminals corresponding to the first recommendation tag according to the corresponding relationship; The user terminal with the highest output priority among the at least two user terminals is used as the target user terminal; The output priority is a priority for displaying the content matched by the first recommendation tag.

7. A resource search device, characterized in that: include: A first external interface, used for passing the search request when the search request includes a first source identifier, the first external interface is a data interface in the first version recommendation system, the data format of the search request is a first format corresponding to the first version recommendation system, and the first version recommendation system is applicable to a voice interaction device; wherein the search request includes a source identifier for representing a user terminal that issues the search request, and the source identifier includes a first source identifier and a second source identifier; a format conversion module, configured to convert the data format of the search request from the first format to a second format corresponding to a second version recommendation system, wherein the second version recommendation system is applicable to an application program; A second version recommendation module, configured to determine the recommended resource information in the second format according to the search request in the second format by adopting a multi-channel recommendation strategy corresponding to the second version recommendation system; wherein the multi-channel recommendation strategy is obtained by updating the single-channel recommendation strategy of the first version recommendation system; The format conversion module is further used to convert the recommended resource information in the second format into the recommended resource information in the first format, and output the recommended resource information in the first format through the first external interface; A second external interface is used to receive the search request through the second external interface when the search request contains the second source identifier, and the data format of the search request is a second format corresponding to the second version recommendation system; according to the search request in the second format, adopt the multi-channel recommendation strategy corresponding to the second version recommendation system, determine the recommended resource information in the second format, and output the recommended resource information in the second format through the second external interface.

8. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the resource search method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that: include: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the resource search method according to any one of claims 1 to 6 is implemented.

Images