Recommended methods, apparatus, electronic devices and storage media

Abstract

The present disclosure proposes a recommendation method, device, electronic device and storage medium, which relate to the field of artificial intelligence technology, and specifically to the field of intelligent recommendation and natural language processing technology. The scheme is: obtain a target document and at least one description object in the target document; determine a sequence of candidate mount promotion objects that match the description object according to the description object; for each candidate mount promotion object in the candidate mount promotion object sequence, determine the target mount promotion object from the candidate mount promotion object sequence according to the promotion feature information of each candidate mount promotion object, and perform mount recommendation. In this way, automatic recommendation of mount promotion objects can be achieved, which reduces the mounting threshold of promotion objects and greatly improves the mounting ratio and efficiency of promotion objects in documents.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of intelligent recommendation and natural language processing technology, and in particular to a recommendation method, device, electronic device and storage medium. Background Art

[0002] Currently, when users (eg, authors) share articles on sharing platforms, they can actively attach promotional objects related to the articles to help other users browse or purchase related promotional objects as needed when browsing the articles. Summary of the invention

[0003] The present disclosure provides a recommendation method, device, electronic device and storage medium.

[0004] According to one aspect of the present disclosure, a recommendation method is provided, comprising: obtaining a target document and at least one description object in the target document; determining a sequence of candidate mount promotion objects matching the description object based on the description object; for each candidate mount promotion object in the sequence of candidate mount promotion objects, determining a target mount promotion object from the sequence of candidate mount promotion objects based on promotion feature information of each candidate mount promotion object, and performing a mount recommendation.

[0005] According to another aspect of the present disclosure, a recommendation device is provided, including: a first acquisition module, used to acquire a target document and at least one description object in the target document; a first determination module, used to determine, based on the description object, a sequence of candidate mount promotion objects that match the description object; a recommendation module, used to determine, for each candidate mount promotion object in the sequence of candidate mount promotion objects, a target mount promotion object from the sequence of candidate mount promotion objects according to promotion feature information of each candidate mount promotion object, and perform mount recommendation.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the embodiment of the first aspect of the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the embodiment of the first aspect of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method described in the embodiment of the first aspect of the present disclosure is implemented.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0012] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0014] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0016] Figure 6 is a schematic diagram according to a sixth embodiment of the present disclosure;

[0017] Figure 7 is a schematic diagram showing a target mount promotion object according to an embodiment of the present disclosure;

[0018] Figure 8 is a schematic diagram according to a seventh embodiment of the present disclosure;

[0019] Fig. 9 is a block diagram of an electronic device for implementing the recommended method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] However, since it is difficult to select promotion objects that are suitable for articles on sharing platforms, the proportion of users actively attaching promotion objects is low. Therefore, how to increase the attachment ratio of promotion objects has become an urgent problem to be solved.

[0022] In view of the above problems, the present disclosure proposes a recommendation method, device, electronic device and storage medium.

[0023] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure. It should be noted that the recommendation method of the embodiment of the present disclosure can be applied to the recommendation device of the embodiment of the present disclosure, and the device can be configured in an electronic device. The electronic device can be a mobile terminal, for example, a mobile phone, a tablet computer, a personal digital assistant, and other hardware devices with various operating systems.

[0024] like Figure 1 As shown, the recommended method may include the following steps:

[0025] Step 101: Obtain a target document and at least one description object in the target document.

[0026] In the embodiments of the present disclosure, the target document may be a document suitable for mounting a promotion object, and the documents to be processed may be screened to obtain the target document, wherein the document to be processed may be a document that the user needs to share, which may be a document edited by the user, or a document downloaded from the network, and the present disclosure does not make any specific limitations.

[0027] The description object may be the target object described by the content in the target document, for example, the target object may be a commodity, a commodity brand, a commodity brand type, etc. In the embodiment of the present disclosure, the description object in the target document may be determined according to the type of the target document, for example, when the target document contains text information, the corresponding description object may be determined according to the keywords in the target document; for another example, when the target document contains image information, the corresponding description object may be determined according to the image information in the target document.

[0028] Step 102: Determine, according to the description object, a sequence of candidate mount promotion objects matching the description object.

[0029] Furthermore, based on the description object, a sequence of candidate mounting promotion objects matching the description object can be searched in the set promotion object library. For example, if the description object is a commodity word in the text information in the target document, the set promotion object library can be searched based on the commodity word to obtain at least one candidate mounting promotion object matching the commodity word, and a sequence of candidate mounting promotion objects can be determined based on the at least one candidate mounting promotion object. For another example, if the description object is a target object described by image information in the target document, the set promotion object library can be searched for at least one candidate mounting promotion object that is identical or similar to the target object in the image information, and a sequence of candidate mounting promotion objects can be determined based on the at least one candidate mounting promotion object. For another example, the description object includes a product word in the text information in the target document, and a target object described in the picture information in the target document. The product word can be searched in the set promotion object library to obtain at least one candidate mounting promotion object matching the product word, and the set promotion object library can be searched for at least one candidate mounting promotion object that is identical or similar to the target object in the picture information. Furthermore, a candidate mounting promotion object sequence can be determined based on at least one candidate mounting promotion object matching the product word and at least one candidate mounting promotion object that is identical or similar to the target object in the picture information.

[0030] Step 103 , for each candidate mount promotion object in the candidate mount promotion object sequence, according to the promotion feature information of each candidate mount promotion object, determine the target mount promotion object from the candidate mount promotion object sequence, and make a mount recommendation.

[0031] In the embodiment of the present disclosure, for each candidate mount promotion object in the candidate mount promotion object sequence, the target mount promotion object can be determined from the candidate mount promotion object sequence according to the promotion feature information of each candidate mount promotion object, and mount recommendation can be performed. The promotion feature information may include at least one of the following information: the relevance between the candidate mount promotion object and the corresponding description object, the weight of the candidate promotion object, and the resource allocation information of the candidate promotion object.

[0032] In summary, by obtaining the description object from the content of the target document suitable for mounting the promotion object, and determining the target mounting promotion object from the sequence of candidate promotion objects matching the description object according to the promotion feature information, automatic recommendation of mounting promotion objects can be achieved, which lowers the mounting threshold of promotion objects and thereby improves the mounting ratio and efficiency of the document's promotion objects.

[0033] In order to accurately determine the target mount promotion object from the candidate mount promotion object sequence, such as Figure 2 As shown, Figure 2It is a schematic diagram according to the second embodiment of the present disclosure. In the embodiment of the present disclosure, the promotion feature information includes: the correlation between the candidate mount promotion object and the corresponding description object. The candidate mount promotion object sequence can be sorted according to the correlation to determine the first candidate mount promotion object sequence from the candidate mount promotion object sequence, and then determine the target mount promotion object from the first candidate mount promotion object sequence. Figure 2 The illustrated embodiment may include the following steps:

[0034] Step 201: Acquire a target document and at least one description object in the target document.

[0035] Step 202: Determine, according to the description object, a sequence of candidate mount promotion objects that match the description object.

[0036] Step 203, for each candidate mount promotion object in the candidate mount promotion object sequence, sort the candidate mount promotion object sequence according to the correlation between the candidate mount promotion object and the corresponding description object, so as to determine a first candidate mount promotion object sequence from the candidate mount promotion object sequence.

[0037] In the disclosed embodiment, for each candidate mount promotion object in the candidate mount promotion object sequence, a correlation analysis may be performed between the candidate mount promotion object and the corresponding description object to determine the correlation between the candidate mount promotion object and the corresponding description object, and the candidate mount promotion object sequence is sorted according to the correlation, and the first candidate mount promotion object sequence is determined according to the sorting result. For example, the candidate mount promotion object sequence is sorted from high to low according to the correlation of the candidate mount promotion object, and the sorting result is used as the first candidate mount promotion object sequence.

[0038] Step 204: According to the sorting result of the first candidate mount promotion object sequence, determine the target mount promotion object from the first candidate mount promotion object sequence, and make a mount recommendation.

[0039] Furthermore, a set number of candidate mount promotion objects may be selected from the first candidate mount promotion object sequence as target mount promotion objects for mount recommendation.

[0040] In summary, by sorting the candidate mount promotion object sequence according to the correlation between the candidate mount promotion object and the corresponding description object for each candidate mount promotion object in the candidate mount promotion object sequence, a first candidate mount promotion object sequence is determined from the candidate mount promotion object sequence; according to the sorting result of the first candidate mount promotion object sequence, a target mount promotion object is determined from the first candidate mount promotion object sequence, and mount recommendation is performed. Thus, according to the correlation between the candidate mount promotion object and the corresponding description object, the target mount promotion object can be accurately determined from the candidate mount promotion object sequence for mount recommendation.

[0041] In order to accurately determine the target mount promotion object from the candidate mount promotion object sequence, such as Figure 3 As shown, Figure 3 It is a schematic diagram according to the third embodiment of the present disclosure. In the embodiment of the present disclosure, the promotion feature information includes: the weight of the candidate promotion object, and the candidate mount promotion object sequence can be sorted according to the weight to determine the second candidate mount promotion object sequence, and the target mount promotion object is determined from the second candidate mount promotion object sequence for mount recommendation. Figure 3 The illustrated embodiment may include the following steps:

[0042] Step 301: Obtain a target document and at least one description object in the target document.

[0043] Step 302: Determine, according to the description object, a sequence of candidate mount promotion objects that match the description object.

[0044] Step 303: sort the candidate mount promotion object sequence according to the weight of each candidate mount promotion object in the candidate mount promotion object sequence to determine a second candidate mount promotion object sequence from the candidate mount promotion object sequence. The weight of each candidate mount promotion object is determined according to the promotion influencing factor corresponding to each candidate promotion object.

[0045] Optionally, the promotion influencing factors corresponding to each candidate mount promotion object in the candidate mount promotion object sequence are obtained, and each candidate mount promotion object is scored according to the promotion influencing factors to determine the weight of each candidate mount promotion object.

[0046] That is to say, in the embodiment of the present disclosure, the quality influencing factors corresponding to each candidate mounting promotion object in the candidate mounting promotion object sequence may include: the authority of the promotion object platform, the cost-effectiveness of each candidate mounting promotion object, the service guarantee of each candidate mounting promotion object, the evaluation information of each candidate mounting promotion object and the sales information of each candidate mounting promotion object, etc. Taking the candidate mounting promotion object as commodity A as an example, the quality influencing factors corresponding to the commodity may be: the authority of the e-commerce platform corresponding to commodity A, the cost-effectiveness of commodity A, the service guarantee of commodity A, the evaluation of commodity A and the sales volume of commodity A, etc.

[0047] Furthermore, each candidate mount promotion object may be scored according to the promotion influencing factor and the set weight corresponding to the promotion influencing factor to obtain the score of each candidate mount promotion object, and the score is used as the weight of each candidate mount promotion object. According to the weight, the candidate mount promotion object sequence is sorted to determine the second candidate mount promotion object sequence from the candidate mount promotion object sequence. For example, the candidate mount promotion object sequence is sorted from high to low according to the score of each candidate mount promotion object, and the sorting result is used as the second candidate mount promotion object sequence.

[0048] Step 304: According to the sorting result of the second candidate mount promotion object sequence, determine the target mount promotion object from the second candidate mount promotion object sequence, and make a mount recommendation.

[0049] Furthermore, a set number of candidate mount promotion objects may be selected from the second candidate mount promotion object sequence as target mount promotion objects for mount recommendation.

[0050] In summary, by sorting the candidate mount promotion object sequence according to the weights of the candidate mount promotion object for each candidate mount promotion object in the candidate mount promotion object sequence, a second candidate mount promotion object sequence is determined from the candidate mount promotion object sequence; according to the sorting result of the second candidate mount promotion object sequence, the target mount promotion object is determined from the second candidate mount promotion object sequence, and mount recommendation is performed. Thus, according to the weights of the candidate promotion objects, the target mount promotion object can be accurately determined from the candidate mount promotion object sequence for mount recommendation.

[0051] In order to accurately determine the target mount promotion object from the candidate mount promotion object sequence, such as Figure 4 As shown, Figure 4is a schematic diagram according to a fourth embodiment of the present disclosure. In the embodiment of the present disclosure, the promotion feature information includes: resource allocation information of the candidate promotion object, and the candidate mount promotion object sequence is sorted according to the resource allocation information of the candidate promotion object to determine a third candidate mount promotion object sequence from the candidate mount promotion object sequence, and then the target mount promotion object is determined from the third candidate mount promotion object sequence. Figure 4 The illustrated embodiment may include the following steps:

[0052] Step 401: Acquire a target document and at least one description object in the target document.

[0053] Step 402: Determine, according to the description object, a sequence of candidate mount promotion objects that match the description object.

[0054] Step 403: sort the candidate mount promotion object sequence according to the resource allocation information of each candidate mount promotion object in the candidate mount promotion object sequence, so as to determine a third candidate mount promotion object sequence from the candidate mount promotion object sequence.

[0055] In the disclosed embodiment, the resource may be the promotion price of the candidate mount promotion object, the resource allocation information may be the proportion of the promotion price, different candidate mount promotion objects may correspond to different set resource allocation information, and for each candidate mount promotion object in the candidate mount promotion object sequence, the candidate mount promotion object sequence may be sorted according to the set resource allocation information corresponding to each candidate mount promotion object, and the sorting result is used as the third candidate mount promotion object sequence. For example, the candidate mount promotion object sequence may be sorted from high to low according to the set resource allocation information of the candidate mount promotion object, and the sorting result is used as the third candidate mount promotion object sequence.

[0056] Step 404: According to the ranking result of the third candidate mount promotion object sequence, determine the target mount promotion object from the third candidate mount promotion object sequence, and make a mount recommendation.

[0057] Furthermore, a set number of candidate mount promotion objects may be selected from the third candidate mount promotion object sequence as target mount promotion objects for mount recommendation.

[0058] In summary, by sorting the candidate mount promotion object sequence according to the resource allocation information of each candidate mount promotion object in the candidate mount promotion object sequence, a third candidate mount promotion object sequence is determined from the candidate mount promotion object sequence; according to the sorting result of the third candidate mount promotion object sequence, the target mount promotion object is determined from the third candidate mount promotion object sequence, and mount recommendation is performed. Thus, according to the resource allocation information of the candidate promotion object, the target mount promotion object can be accurately determined from the candidate mount promotion object sequence for mount recommendation.

[0059] In order to accurately determine the target mount promotion object from the candidate mount promotion object sequence, such as Figure 5 As shown, Figure 5 is a schematic diagram according to the fifth embodiment of the present disclosure. In the embodiment of the present disclosure, the promotion feature information includes: the correlation between the candidate mount promotion object and the corresponding description object, the weight of the candidate promotion object and the resource allocation information of the candidate promotion object. According to the correlation between the candidate mount promotion object and the corresponding description object, the weight of the candidate promotion object and the resource allocation information of the candidate promotion object of each candidate mount promotion object, the target mount promotion object is determined from the candidate mount promotion object sequence, and mount recommendation is performed. Figure 5 The illustrated embodiment may include the following steps:

[0060] Step 501: Acquire a target document and at least one description object in the target document.

[0061] Step 502: Determine, according to the description object, a sequence of candidate mount promotion objects that match the description object.

[0062] Step 503, for each candidate mount promotion object in the candidate mount promotion object sequence, sort the candidate mount promotion object sequence according to the correlation between the candidate mount promotion object and the corresponding description object, so as to determine a first candidate mount promotion object sequence from the candidate mount promotion object sequence.

[0063] In the disclosed embodiment, for each candidate mount promotion object in the candidate mount promotion object sequence, a correlation analysis may be performed between the candidate mount promotion object and the corresponding description object to determine the correlation between the candidate mount promotion object and the corresponding description object, and the candidate mount promotion object sequence is sorted according to the correlation, and the first candidate mount promotion object sequence is determined according to the sorting result. For example, the candidate mount promotion object sequence is sorted from high to low according to the correlation of the candidate mount promotion object, and the candidate mount promotion objects whose correlation with the corresponding description object is lower than the set correlation threshold are discarded, and the candidate mount promotion objects whose correlation with the corresponding description object is greater than or equal to the set correlation threshold are retained, and the candidate mount promotion objects whose correlation with the corresponding description object is greater than or equal to the set correlation threshold are used as the first candidate mount promotion object sequence.

[0064] Step 504: sort the first candidate mount promotion object sequence according to the weights of the candidate mount promotion objects, so as to determine a second candidate mount promotion object sequence from the first candidate mount promotion object sequence.

[0065] In the disclosed embodiment, each candidate mount promotion object can be scored according to the promotion influencing factor and the set weight corresponding to the promotion influencing factor to obtain the score of each candidate mount promotion object, and the score is used as the weight of each candidate mount promotion object. According to the weight, the candidate mount promotion object sequence is sorted to determine the second candidate mount promotion object sequence from the candidate mount promotion object sequence. For example, the candidate mount promotion object sequence is sorted from high to low according to the score of each candidate mount promotion object, and the candidate mount promotion objects with a score lower than the set score in the sorting result are discarded, and the candidate mount promotion objects with a score higher than the set score are retained, and the candidate mount promotion objects with a score higher than the set score are used as the second candidate mount promotion object sequence.

[0066] Step 505: sort the second candidate mount promotion object sequence according to the resource allocation information of the candidate mount promotion object, so as to determine a third candidate mount promotion object sequence from the second candidate mount promotion object sequence.

[0067] In the disclosed embodiment, different candidate mount promotion objects may correspond to different set resource allocation information. For each candidate mount promotion object in the candidate mount promotion object sequence, the candidate mount promotion object sequence may be sorted according to the set resource allocation information corresponding to each candidate mount promotion object, and the sorting result is used as the third candidate mount promotion object sequence. For example, the candidate mount promotion object sequence may be sorted from high to low according to the set resource allocation information of the candidate mount promotion object, and the sorting result is used as the third candidate mount promotion object sequence.

[0068] Step 506: According to the ranking result of the third candidate mount promotion object sequence, determine the target mount promotion object from the third candidate mount promotion object sequence, and make a mount recommendation.

[0069] Furthermore, a set number of candidate mount promotion objects may be selected from the third candidate mount promotion object sequence as target mount promotion objects for mount recommendation.

[0070] In summary, by sorting the candidate mount promotion object sequence according to the correlation between the candidate mount promotion object and the corresponding description object for each candidate mount promotion object in the candidate mount promotion object sequence, a first candidate mount promotion object sequence is determined from the candidate mount promotion object sequence; according to the weight of the candidate mount promotion object, the first candidate mount promotion object sequence is sorted to determine the second candidate mount promotion object sequence from the first candidate mount promotion object sequence; according to the resource allocation information of the candidate mount promotion object, the second candidate mount promotion object sequence is sorted to determine the third candidate mount promotion object sequence from the second candidate mount promotion object sequence, and according to the sorting result of the third candidate mount promotion object sequence, the target mount promotion object is determined from the third candidate mount promotion object sequence, and mount recommendation is performed. Therefore, according to the correlation between the candidate mount promotion object and the corresponding description object, the weight of the candidate promotion object and the resource allocation information of the candidate promotion object, the target mount promotion object can be accurately determined from the candidate mount promotion object sequence for mount recommendation.

[0071] In order to accurately obtain the target document suitable for the target promotion object, such as Figure 6 As shown, Figure 6 is a schematic diagram according to the sixth embodiment of the present disclosure. In the embodiment of the present disclosure, entities and description information of entities in a document to be processed can be extracted. When the description information meets the set conditions, the document to be processed is used as a target document. Figure 6 The illustrated embodiment may include the following steps:

[0072] Step 601, obtaining the document to be processed.

[0073] In the embodiments of the present disclosure, the document to be processed may be a document that the user needs to share, the document may be a document edited by the user, or a document downloaded from the network, which is not specifically limited in the present disclosure.

[0074] Step 602: When the document to be processed contains text information, extract the first entity and description information of the first entity from the text information.

[0075] In the embodiment of the present disclosure, when the document to be processed contains text information, the text information may be subjected to natural language processing to extract the first entity in the text information. For example, the text information may be subjected to word segmentation and information extraction to determine the first keyword in the text information.

[0076] In the embodiment of the present disclosure, a first entity corresponding to the first keyword is determined according to the first keyword, and a statistical analysis is performed on the first entity, and description information of the first entity is determined according to the statistical analysis result.

[0077] For example, the keyword is a product word, and the first entity corresponding to the product word is product A. The number of times that product A appears in all documents to be processed is counted, and the number of times that product A appears is used as the description information of product A.

[0078] Step 603: When the document to be processed includes picture information, object recognition is performed on the picture information to determine the second entity and description information of the second entity included in the picture information.

[0079] In an embodiment of the present disclosure, when the document to be processed contains image information, image recognition can be performed on the image information, and the second entity in the image information and the description information of the second entity can be determined based on the image recognition result. For example, the second entity is product category A, and the number of times the product category A appears in all the documents to be processed is counted, and the number of times the product category A appears is used as the description information of the product category A.

[0080] Step 604: In response to the description information of the first entity and / or the description information of the second entity satisfying a set condition, determining that the document to be processed is a target document.

[0081] Furthermore, all the first entities and / or second entities and the corresponding description information in the document to be processed are compared with the set conditions, and when the description information corresponding to the first entity and / or the second entity in the document to be processed meets the set conditions, the document to be processed is used as the target document. For example, the description information of the first entity and / or the second entity is the number of times that commodity A appears, the number of times that commodity category A appears, etc., when the number of times that commodity A appears is greater than or equal to the first set number of times, and / or the number of times that commodity category A appears is greater than or equal to the second set number of times, the document to be processed is used as the target document.

[0082] Step 605: Use the first entity and / or the second entity as at least one description object in the target document.

[0083] In an embodiment of the present disclosure, after acquiring a target document, the first entity and / or the second entity in the target document may be used as at least one description object in the target document.

[0084] Step 606: Determine, based on the description object, a sequence of candidate mount promotion objects that match the description object.

[0085] Step 607: for each candidate mount promotion object in the candidate mount promotion object sequence, according to the promotion feature information of each candidate mount promotion object, determine the target mount promotion object from the candidate mount promotion object sequence, and make a mount recommendation.

[0086] In the embodiments of the present disclosure, Figure 7 As shown, after the target mount promotion object is recommended and the relevant user confirms the mount, the client can display the target mount promotion object. For example, the color of the description object in the target document can be displayed differently from the color of other texts, and the icon of the target mount promotion object corresponding to the description object can be displayed above or below the description object (such as Figure 7 At the same time, you can also display pictures of target promotion objects that are the same or similar to the pictures in the target document (such as Figure 7 As shown in ③ on the right side of the figure), it should be noted that when there are multiple target mount promotion objects, a fixed entrance can be set (such as Figure 7 When a user clicks on the fixed entrance, the page can display the target mount promotion object sequence.

[0087] In summary, by acquiring a document to be processed; when the document to be processed contains text information, extracting the first entity and the description information of the first entity contained in the text information; when the document to be processed contains image information, performing object recognition on the image information to determine the second entity and the description information of the second entity contained in the image information; in response to the description information of the first entity and / or the description information of the second entity satisfying the set conditions, determining that the document to be processed is a target document; taking the first entity and / or the second entity as at least one description object in the target document, thereby, according to the content of the document to be processed, the target document suitable for mounting the target promotion object and the description object in the target document can be accurately determined.

[0088] The recommendation method of the disclosed embodiment obtains a target document and at least one description object in the target document; determines a sequence of candidate mount promotion objects that match the description object according to the description object; and determines a target mount promotion object from the candidate mount promotion object sequence according to the promotion feature information of each candidate mount promotion object for each candidate mount promotion object in the candidate mount promotion object sequence, and makes a mount recommendation. Thus, by extracting description objects from the target document suitable for the mount promotion object through content understanding, and determining the target mount promotion object from the sequence of candidate promotion objects that match the description object according to the promotion feature information, automatic recommendation of mount promotion objects can be achieved, the mounting threshold of promotion objects is lowered, and the mounting ratio and efficiency of promotion objects of documents are improved.

[0089] In order to implement the above embodiments, the present disclosure also proposes a recommendation device.

[0090] Figure 8 is a schematic diagram according to the seventh embodiment of the present disclosure, Figure 8 As shown, the recommendation device 800 includes: a first acquisition module 810 , a first determination module 820 and a recommendation module 830 .

[0091] Among them, the first acquisition module 810 is used to acquire the target document and at least one description object in the target document; the first determination module 820 is used to determine a sequence of candidate mount promotion objects matching the description object based on the description object; the recommendation module 830 is used to determine the target mount promotion object from the candidate mount promotion object sequence according to the promotion feature information of each candidate mount promotion object in the candidate mount promotion object sequence, and make a mount recommendation.

[0092] As a possible implementation method of the embodiment of the present disclosure, the promotion feature information includes: the correlation between the candidate mount promotion object and the corresponding description object; the recommendation module 830 is specifically used to: for each candidate mount promotion object in the candidate mount promotion object sequence, sort the candidate mount promotion object sequence according to the correlation between the candidate mount promotion object and the corresponding description object, so as to determine a first candidate mount promotion object sequence from the candidate mount promotion object sequence; according to the sorting result of the first candidate mount promotion object sequence, determine the target mount promotion object from the first candidate mount promotion object sequence, and make a mount recommendation.

[0093] As a possible implementation method of the embodiment of the present disclosure, the promotion feature information includes: the weight of the candidate promotion object; the recommendation module 830 is also used to: for each candidate mount promotion object in the candidate mount promotion object sequence, sort the candidate mount promotion object sequence according to the weight of the candidate mount promotion object to determine a second candidate mount promotion object sequence from the candidate mount promotion object sequence; according to the sorting result of the second candidate mount promotion object sequence, determine the target mount promotion object from the second candidate mount promotion object sequence, and make a mount recommendation.

[0094] As a possible implementation method of the embodiment of the present disclosure, the promotion feature information includes: resource allocation information of the candidate promotion object; the recommendation module 830 is also used to: for each candidate mount promotion object in the candidate mount promotion object sequence, sort the candidate mount promotion object sequence according to the resource allocation information of each candidate mount promotion object to determine a third candidate mount promotion object sequence from the candidate mount promotion object sequence; according to the sorting result of the third candidate mount promotion object sequence, determine the target mount promotion object from the third candidate mount promotion object sequence, and make a mount recommendation.

[0095] As a possible implementation manner of the embodiment of the present disclosure, the weight of each candidate mounting promotion object is determined according to the promotion influencing factor corresponding to each candidate promotion object; the recommendation device also includes: a second acquisition module and a second determination module.

[0096] Among them, the second acquisition module is used to obtain the promotion influencing factors corresponding to each candidate mount promotion object in the candidate mount promotion object sequence; the second determination module is used to score each candidate mount promotion object according to the promotion influencing factors to obtain the score of each candidate mount promotion object; the second determination module is also used to determine the weight of the corresponding candidate mount promotion object according to the score of each candidate mount promotion object.

[0097] As a possible implementation method of the embodiment of the present disclosure, the first acquisition module 810 is specifically used to: acquire a document to be processed; when the document to be processed contains text information, extract a first entity contained in the text information and description information of the first entity; when the document to be processed contains image information, perform object recognition on the image information to determine a second entity contained in the image information and description information of the second entity; in response to the description information of the first entity and / or the description information of the second entity satisfying a set condition, determine that the document to be processed is a target document; accordingly, the first acquisition module is also used to: use the first entity and / or the second entity as at least one description object in the target document.

[0098] The recommendation device of the disclosed embodiment obtains a target document and at least one description object in the target document; determines a sequence of candidate mounting promotion objects matching the description object according to the description object; and determines a target mounting promotion object from the candidate mounting promotion object sequence according to the promotion feature information of each candidate mounting promotion object for each candidate mounting promotion object in the candidate mounting promotion object sequence, and makes a mounting recommendation. Thus, by obtaining a description object from the content in the target document suitable for the mounting promotion object, and determining the target mounting promotion object from the sequence of candidate promotion objects matching the description object according to the promotion feature information, automatic recommendation of mounting promotion objects can be achieved, the mounting threshold of promotion objects is lowered, and the mounting ratio and efficiency of promotion objects of documents are improved.

[0099] It should be noted that in the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information are all carried out with the user's consent, and are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0100] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the above embodiment.

[0101] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method described in the above embodiment.

[0102] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in the above embodiment is implemented.

[0103] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0104] Fig. 9A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0105] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0106] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as the recommendation method. For example, in some embodiments, the recommendation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the recommendation method in any other appropriate manner (e.g., by means of firmware).

[0108] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0110] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0113] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other. The server may also be a server of a distributed system, or a server combined with a blockchain.

[0114] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0115] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0116] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A recommendation method, comprising: Acquire a target document and at least one description object in the target document; According to the description object, determining a sequence of candidate mount promotion objects matching the description object; For each candidate mount promotion object in the candidate mount promotion object sequence, sort the candidate mount promotion object sequence according to the relevance between the candidate mount promotion object and the corresponding description object, and determine a first candidate mount promotion object sequence from the candidate mount promotion object sequence; According to the weights of the candidate mount promotion objects, the first candidate mount promotion object sequence is sorted, and a second candidate mount promotion object sequence is determined from the first candidate mount promotion object sequence, wherein the weight of each candidate mount promotion object is determined according to the promotion influencing factors corresponding to each candidate promotion object, and the promotion influencing factors include: the authority of the promotion object platform, the cost-effectiveness of each candidate mount promotion object, the service guarantee of each candidate mount promotion object, the evaluation information of each candidate mount promotion object, and the sales information of each candidate mount promotion object; According to the resource allocation information of the candidate mount promotion objects, the second candidate mount promotion object sequence is sorted, and a third candidate mount promotion object sequence is determined from the second candidate mount promotion object sequence, wherein the resource allocation information includes the proportion allocation information of the promotion price of the candidate mount promotion objects; According to the ranking result of the third candidate mount promotion object sequence, a target mount promotion object is determined from the third candidate mount promotion object sequence, and a mount recommendation is performed.

2. The method according to claim 1, before sorting the first candidate mount promotion object sequence according to the weights of the candidate mount promotion objects and determining the second candidate mount promotion object sequence from the first candidate mount promotion object sequence, further comprises: Obtaining promotion influencing factors corresponding to each candidate mount promotion object in the candidate mount promotion object sequence; Scoring each of the candidate mount promotion objects according to the promotion influencing factors to obtain a score for each of the candidate mount promotion objects; According to the score of each candidate mount promotion object, the weight of the corresponding candidate mount promotion object is determined.

3. The method according to claim 1, wherein: The obtaining of the target document comprises: Get the documents to be processed; In a case where the document to be processed contains text information, extracting a first entity and description information of the first entity contained in the text information; In a case where the document to be processed includes picture information, performing object recognition on the picture information to determine a second entity included in the picture information and description information of the second entity; In response to the description information of the first entity and / or the description information of the second entity satisfying a set condition, determining that the to-be-processed document is a target document; Accordingly, obtaining at least one description object in the target document includes: The first entity and / or the second entity is used as at least one description object in the target document.

4. A recommendation device, comprising: A first acquisition module, used to acquire a target document and at least one description object in the target document; A first determination module, configured to determine, according to the description object, a sequence of candidate mount promotion objects matching the description object; A recommendation module, configured to sort the candidate mount promotion object sequence according to the relevance between the candidate mount promotion object and the corresponding description object for each candidate mount promotion object in the candidate mount promotion object sequence, and determine a first candidate mount promotion object sequence from the candidate mount promotion object sequence; According to the weights of the candidate mount promotion objects, the first candidate mount promotion object sequence is sorted, and a second candidate mount promotion object sequence is determined from the first candidate mount promotion object sequence, wherein the weight of each candidate mount promotion object is determined according to the promotion influencing factors corresponding to each candidate promotion object, and the promotion influencing factors include: the authority of the promotion object platform, the cost-effectiveness of each candidate mount promotion object, the service guarantee of each candidate mount promotion object, the evaluation information of each candidate mount promotion object, and the sales information of each candidate mount promotion object; According to the resource allocation information of the candidate mount promotion objects, the second candidate mount promotion object sequence is sorted, and a third candidate mount promotion object sequence is determined from the second candidate mount promotion object sequence, wherein the resource allocation information includes the proportion allocation information of the promotion price of the candidate mount promotion objects; According to the ranking result of the third candidate mount promotion object sequence, a target mount promotion object is determined from the third candidate mount promotion object sequence, and a mount recommendation is performed.

5. The device according to claim 4, further comprising: A second acquisition module is used to acquire promotion influencing factors corresponding to each candidate mount promotion object in the candidate mount promotion object sequence; A second determination module is used to score each of the candidate mount promotion objects according to the promotion influencing factors to obtain a score of each of the candidate mount promotion objects; The second determination module is further used to determine the weight of the corresponding candidate mount promotion object according to the score of each candidate mount promotion object.

6. The device according to claim 4, wherein: The first acquisition module is specifically used to: Get the documents to be processed; In a case where the document to be processed contains text information, extracting a first entity and description information of the first entity contained in the text information; In a case where the document to be processed includes picture information, performing object recognition on the picture information to determine a second entity included in the picture information and description information of the second entity; In response to the description information of the first entity and / or the description information of the second entity satisfying a set condition, determining that the to-be-processed document is a target document; Accordingly, the first acquisition module is further used for: The first entity and / or the second entity is used as at least one description object in a target document.

7. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 3.

9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 3.

Images