Recommendation method and device based on large model, electronic equipment and storage medium

Abstract

The invention provides a recommendation method and device based on a large model, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as deep learning, intelligent recommendation and large models. According to the specific implementation scheme, the method comprises the steps of determining interested content description information corresponding to a target user; to-be-recommended content, the description information of the interested content and current hot search statements are input into a large model, at least one recommendation card corresponding to the to-be-recommended content is generated, and the recommendation card comprises recommendation words associated with the to-be-recommended content; obtaining current behavior characteristics of the target user; and displaying at least one recommended card corresponding to the to-be-recommended content under the condition that the current behavior feature meets the display condition of the recommended card.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to the field of artificial intelligence technology such as deep learning, intelligent recommendation, and large models, and specifically to a recommendation method, device, electronic device, and storage medium based on a large model. Background Art

[0002] With the rapid development of the Internet, various information flow products have emerged. Information flow products distribute content products in a waterfall flow manner. Common information flow products include shopping applications, whose corresponding content products are commodities; news applications, whose corresponding content products are news information, etc.

[0003] However, current recommendation systems mostly use fixed words to recommend content, which is a single method and leads to poor recommendation effects and low accuracy. Summary of the invention

[0004] The present disclosure provides a recommendation method, device, electronic device and storage medium based on a large model.

[0005] According to a first aspect of the present disclosure, a large model-based recommendation method is provided, comprising:

[0006] Determine the description information of the content of interest corresponding to the target user;

[0007] Inputting the content to be recommended, the description information of the content of interest and the current hot search phrase into the big model, generating at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains a recommendation phrase associated with the content to be recommended;

[0008] Acquire current behavior characteristics of the target user;

[0009] When the current behavior feature satisfies the display condition of the recommendation card, at least one recommendation card corresponding to the content to be recommended is displayed.

[0010] According to a second aspect of the present disclosure, a large model-based recommendation device is provided, comprising:

[0011] A determination module, used to determine the description information of the content of interest corresponding to the target user;

[0012] A generation module, configured to input the content to be recommended, the description information of the content of interest and the current hot search phrase into the large model, and generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains a recommendation phrase associated with the content to be recommended;

[0013] An acquisition module, used to acquire the current behavior characteristics of the target user;

[0014] The display module is used to display at least one recommendation card corresponding to the content to be recommended when the current behavior characteristics meet the display conditions of the recommendation card.

[0015] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] 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 large model-based recommendation method as described in the first aspect.

[0019] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the large model-based recommendation method as described in the first aspect.

[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of the large model-based recommendation method as described in the first aspect.

[0021] The large model-based recommendation method, device, electronic device, and storage medium provided by the present disclosure have the following beneficial effects:

[0022] In the disclosed embodiment, the description information of the content of interest corresponding to the target user is first determined, and then the content to be recommended, the description information of the content of interest, and the current popular search sentence are input into the large model to generate at least one recommendation card corresponding to the content to be recommended, and then the current behavior characteristics of the target user are obtained. Finally, when the current behavior characteristics meet the display conditions of the recommendation card, at least one recommendation card corresponding to the content to be recommended is displayed. In this way, not only can different recommendation cards be generated for different users for the same content to be recommended by combining the description information of the content of interest and the popular search sentences of different users, so that the generated recommendation cards are more in line with the user's preferences, but also the recommendation cards can be displayed to the user according to the user's current behavior, thereby improving the diversity and accuracy of the recommendation form.

[0023] 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

[0024] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0025] Figure 1 is a flowchart of a large model-based recommendation method provided according to an embodiment of the present disclosure;

[0026] Figure 2 A schematic diagram of a process for determining description information of content of interest provided by an embodiment of the present disclosure;

[0027] Figure 3 A schematic diagram of displaying a recommendation card provided by an embodiment of the present disclosure;

[0028] Figure 4 A schematic diagram of displaying a recommendation card provided by an embodiment of the present disclosure;

[0029] Figure 5 is a flowchart of a large model-based recommendation method provided according to another embodiment of the present disclosure;

[0030] Figure 6 is a flowchart of a large model-based recommendation method provided according to another embodiment of the present disclosure;

[0031] Figure 7 is a flowchart of a large model-based recommendation method provided according to another embodiment of the present disclosure;

[0032] Figure 8 A schematic diagram of the structure of a click rate prediction model provided by an embodiment of the present disclosure;

[0033] Fig. 9 A schematic diagram of a display interface provided by an embodiment of the present disclosure;

[0034] Fig.10 A schematic diagram of displaying follow-up content provided by an embodiment of the present disclosure;

[0035] Fig.11 is a flowchart of a large model-based recommendation method provided according to another embodiment of the present disclosure;

[0036] Fig.12 is a structural schematic diagram of a large model-based recommendation device provided according to an embodiment of the present disclosure;

[0037] Fig.13 The block diagram is a block diagram of an electronic device for implementing the large model-based recommendation method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] 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.

[0039] The present disclosure relates to artificial intelligence technology fields such as deep learning, intelligent recommendation, and large models.

[0040] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0041] Deep learning (DL) is the process of learning the inherent laws and representation levels of sample data. The information obtained in the learning process is very helpful for interpreting data such as text, images, and sounds. The ultimate goal of deep learning is to enable machines to have analytical learning capabilities like humans and to recognize data such as text, images, and sounds.

[0042] Intelligent recommendation, as an important means of information filtering and personalized services, is centered on integrating multi-dimensional information such as users' historical behavior data, interest preferences, and contextual environment, and using algorithm models to automatically analyze and predict users' potential needs or interests, and then recommend content, products, services, or social relationships that may interest users.

[0043] The large model can also be called the Foundation Model. The model extracts knowledge through billions of corpora or images, learns and then produces a large model with billions of parameters.

[0044] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0045] The following describes a large model-based recommendation method, device, electronic device, and storage medium according to an embodiment of the present disclosure with reference to the accompanying drawings.

[0046] It should be noted that the executor of the big model-based recommendation method of this embodiment is a big model-based recommendation device, which can be implemented by software and / or hardware. The device can be configured in an electronic device, and the electronic device may include but is not limited to a terminal, a server, etc.

[0047] Figure 1It is a flowchart of a large model-based recommendation method provided according to an embodiment of the present disclosure.

[0048] like Figure 1 As shown, the large model-based recommendation method includes:

[0049] S101, determining the description information of the content of interest corresponding to the target user.

[0050] The target user may be a user to whom content is to be recommended.

[0051] The description information of the content of interest may include the type of content of interest (eg, sports, music, entertainment, etc.) and the emotional classification of the content of interest (eg, happy, touching, etc.).

[0052] In some embodiments, based on the target user's profile and historical consumption content, the description information of the content of interest corresponding to the target user is determined.

[0053] In some embodiments, a portrait of the target user can be generated based on the user's age, gender, interests, etc.

[0054] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of personal information such as the user's age, gender, points of interest, etc. have been subject to the user's consent, are in compliance with the relevant laws and regulations, and do not violate public order and good morals.

[0055] Among them, historical consumption content may be the title, content, classification, cover image, video, etc. corresponding to the resources with which the target users have interacted and with a relatively high degree of completion.

[0056] In some embodiments, the target user's portrait, historical consumption content, and prompt words may be input into the big model, and the big model may capture the target user's content description information of interest.

[0057] Figure 2 A schematic diagram of a process for determining description information of content of interest provided by an embodiment of the present disclosure. Figure 2 As shown in the figure, the text and prompt words related to the historical consumption content are first encoded through the language instruction encoder to obtain the text feature H q ; The information of the images, videos and other modalities related to the historical consumption content is encoded through the vision encoder and then projected into the input embedding feature space of the large model to obtain the visual feature H v , to achieve feature alignment of different modalities, and finally the text feature H q and visual features H v, input to the large model (Language Model), and get the vector X of the large model response a , and then obtain the description information of the content of interest corresponding to the target user.

[0058] S102, input the content to be recommended, the description information of the content of interest and the current hot search sentence into the big model, and generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains the recommendation words associated with the content to be recommended.

[0059] The content to be recommended may be content to be recommended to the user. The number of the content to be recommended may be one or more. This disclosure does not limit this.

[0060] Among them, the current hot search sentence may be a sentence with a high search volume.

[0061] In some embodiments, the recommendation card may also include cover content (such as pictures, videos, etc.) that matches the recommendation.

[0062] In some embodiments, a recommendation word corresponding to the content to be recommended may be generated based on the content to be recommended, description information of the content of interest and current popular search sentences, and then a recommendation card may be generated based on the recommendation word.

[0063] The big model used to generate the recommendation card corresponding to the content to be recommended and the big model used to determine the description information of the content of interest can be the same big model or different big models, which is not limited in the present disclosure.

[0064] S103, obtaining the current behavior characteristics of the target user.

[0065] The current behavior feature of the target user may be the behavior of the target user browsing the displayed content in the display interface. For example, the behavior of the target user clicking on the displayed content, the length of time the target user watches the displayed content, the behavior of the target user sliding the display interface, etc. This disclosure does not limit this.

[0066] S104: When the current behavior feature satisfies a display condition of a recommendation card, display at least one recommendation card corresponding to the content to be recommended.

[0067] In some embodiments, the display conditions may include that the target user clicks on the displayed content a large number of times, stays there for a long time, swipes, turns pages frequently, has no clicks, etc.

[0068] Figure 3 A display diagram of a recommendation card provided by an embodiment of the present disclosure is shown as follows: Figure 3As shown, the display interface includes recommendation cards and other content except recommendation cards. The recommendation cards include recommendation words and guidance information (for example, click to expand related content for you).

[0069] Figure 4 A display diagram of a recommendation card provided by an embodiment of the present disclosure is shown as follows: Figure 4 As shown, the display interface includes recommendation cards and other content except recommendation cards. The recommendation cards include recommendation words, cover content, and guidance information (for example, click to expand related content for you).

[0070] In the disclosed embodiment, the description information of the content of interest corresponding to the target user is first determined, and the content to be recommended, the description information of the content of interest, and the current popular search statements are input into the large model to generate at least one recommendation card corresponding to the content to be recommended, and then the current behavior characteristics of the target user are obtained. Finally, when the current behavior characteristics meet the display conditions of the recommendation card, at least one recommendation card corresponding to the content to be recommended is displayed. In this way, not only can different recommendation cards be generated for different users for the same content to be recommended by combining the description information of the content of interest and the popular search statements of different users, so that the generated recommendation cards are more in line with the user's preferences, but also the recommendation cards can be displayed to the user according to the user's current behavior, thereby improving the diversity and accuracy of the recommendation forms.

[0071] Figure 5 is a flowchart of a recommendation method based on a large model provided according to another embodiment of the present disclosure, such as Figure 5 As shown, the large model-based recommendation method includes:

[0072] S501: Determine the description information of the content of interest corresponding to the target user.

[0073] S502: Acquire first interaction information of each candidate content in the candidate content library within a first preset time period.

[0074] The candidate content in the candidate content library may be content that has been displayed on the platform.

[0075] The first preset period may be one week, one month, one day, etc. This disclosure does not limit this.

[0076] The first interactive information may be other users' browsing, clicking, feedback and other behaviors on the candidate content.

[0077] S503: Determine the current content to be recommended from the candidate content library according to the first interaction information of each candidate content.

[0078] In the disclosed embodiment, candidate content with more interactions can be determined as content to be recommended based on the first interaction information, so as to recommend the candidate content with more interactions to the target user, thereby increasing the probability of the target user clicking on the recommendation card, thereby improving the accuracy of the recommendation.

[0079] In some embodiments, the score of each candidate content can be comprehensively determined based on the first interaction information, and then the candidate content with a higher score is determined as the content to be recommended. In some embodiments, the more clicks a candidate content has, the higher the score, and the more users are interested in the candidate content, the higher the score.

[0080] S504: Input the content to be recommended, the description information of the content of interest and the current hot search phrases into the big model to generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains a recommendation phrase associated with the content to be recommended.

[0081] S505: Acquire the current behavior characteristics of the target user.

[0082] S506: When the current behavior characteristic satisfies the display condition of the recommendation card, display at least one recommendation card corresponding to the content to be recommended.

[0083] The specific implementation of steps S504 to S506 can refer to the detailed description in other embodiments of the present disclosure, and will not be described in detail here.

[0084] In the disclosed embodiment, the first interaction information of each candidate content in the candidate content library within the first preset time period is obtained, and then the current content to be recommended is determined from the candidate content library based on the first interaction information of each candidate content, and then the content to be recommended, the description information of the content of interest and the current popular search sentence are input into the large model to generate at least one recommendation card corresponding to the content to be recommended, and finally, when the current behavior characteristics of the target user meet the display conditions of the recommendation card, at least one recommendation card corresponding to the content to be recommended is displayed. In this way, the content to be recommended can be determined based on the first interaction information of each candidate content, so that the more popular candidate content can be recommended to the target user, and then the popular content can be displayed to different users in different recommendation forms, so that the recommendation card corresponding to the generated popular content is more in line with the user's preferences, further improving the accuracy of the recommendation.

[0085] Figure 6 is a flowchart of a recommendation method based on a large model provided according to another embodiment of the present disclosure; Figure 6 As shown, the large model-based recommendation method includes:

[0086] S601: Determine the description information of the content of interest corresponding to the target user.

[0087] S602: Input the content to be recommended, description information of the content of interest and the current hot search phrases into the big model to generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains recommendation words associated with the content to be recommended.

[0088] S603, obtaining the current behavior characteristics of the target user.

[0089] The specific implementation of steps S601 to S603 can refer to the detailed description in other embodiments of the present disclosure, and will not be described in detail here.

[0090] S604: When the current behavior characteristic satisfies the display condition of the recommended card, determine the type of the currently satisfied display condition.

[0091] In some embodiments, the types of display conditions may include a first type and a second type.

[0092] In some embodiments, the first type is a behavior with positive and active characteristics, such as a large number of clicks, a long stay time, etc. The second type is a behavior with negative and passive characteristics, such as sliding, high frequency of page turning, no click behavior, etc.

[0093] S605: Determine target recommended content based on the type of the satisfied display condition.

[0094] In some embodiments, when the satisfied display condition is of the first type, the target recommended content is determined based on the content currently consumed by the target user.

[0095] It should be noted that when the display conditions satisfied by the target user's behavioral characteristics are of the first type, it means that the target user is more interested in the content currently consumed. Therefore, based on the content currently consumed, the target recommended content related to the currently consumed content can be selected from the recommended content, so that the recommended content finally displayed is more in line with the target user's current interests, thereby increasing the probability of the target user clicking on the displayed recommendation card and further improving the accuracy of the recommendation.

[0096] In some embodiments, when the display condition satisfied by the behavior characteristics of the target user is of the first type, the to-be-recommended content that is of the same type as the currently consumed content may be determined as the target recommended content.

[0097] For example, if the currently consumed content is of the music type, then the to-be-recommended content of the music type is determined as the target recommended content.

[0098] In some embodiments, when the display condition satisfied by the behavior characteristics of the target user is of the first type, the to-be-recommended content whose similarity to the currently consumed content is greater than a first threshold is determined as the target recommended content.

[0099] In some embodiments, the similarity between the content to be recommended and the currently consumed content may be determined by methods such as pre-similarity and Euclidean distance.

[0100] In the disclosed embodiment, the content to be recommended that has a strong correlation with the currently consumed content can be determined as the target recommended content based on the two dimensions of the type of the currently consumed content and the similarity between the content and the currently consumed content. This not only increases the possibility that the determined target recommended content will be clicked by the target user, thereby improving the accuracy of the recommendation, but also increases the diversification of information related to the currently consumed content.

[0101] In some embodiments, when the satisfied display condition is of the second type, the target recommended content is determined based on the content currently displayed on the display interface.

[0102] It should be noted that when the display conditions satisfied by the target user's behavioral characteristics are of the second type, it means that the target user is not interested in the content currently displayed on the interface. Therefore, based on the currently displayed content, target consumption content that is not related to the currently displayed content can be selected from the recommended content to be recommended, and other content that may be of interest to the target user can be recommended, thereby increasing the probability of the target user clicking on the displayed recommendation card and thereby improving the accuracy of the recommendation.

[0103] In some embodiments, when the display condition satisfied by the behavior characteristics of the target user is of the second type, the to-be-recommended content whose similarity to the currently displayed content is less than a second threshold is determined as the target recommended content.

[0104] In some embodiments, the second threshold is less than or equal to the first threshold.

[0105] In some embodiments, when the display condition satisfied by the behavior characteristics of the target user is of the second type, the to-be-recommended content that is not of the same type as the currently displayed content is determined as the target recommended content.

[0106] For example, if the currently displayed content is of music type, then the non-music type of recommended content is determined as the target recommended content.

[0107] In the disclosed embodiment, the to-be-recommended content that is not associated with the currently consumed content can be determined as the target recommended content based on two dimensions: the type of the currently displayed content and the similarity between the to-be-recommended content and the currently displayed content. This can provide the target user with the target recommended content of interest as much as possible, further improving the accuracy of the recommendation.

[0108] S606: Display the recommendation card corresponding to the target recommended content.

[0109] In the disclosed embodiment, after the content to be recommended, the description information of the content of interest and the current hot search phrases are input into the large model, at least one recommendation card corresponding to the content to be recommended is generated, wherein the recommendation card contains the recommendation phrase associated with the content to be recommended, and when the current behavior characteristics of the target user meet the display conditions of the recommendation card, the type of the currently met display conditions is determined, and based on the type of the met display conditions, the target recommended content is determined, and finally the recommendation card corresponding to the target recommended content is displayed. In this way, the target recommended content that the user may be more interested in can be determined based on the type of display conditions met by the current behavior characteristics of the target user, thereby further improving the accuracy of the recommendation.

[0110] Figure 7 is a flowchart of a recommendation method based on a large model provided according to another embodiment of the present disclosure; Figure 7 As shown, the large model-based recommendation method includes:

[0111] S701, determining the description information of the content of interest corresponding to the target user.

[0112] S702: Input the content to be recommended, description information of the content of interest and the current hot search phrases into the big model to generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains recommendation words associated with the content to be recommended.

[0113] S703, obtaining the current behavior characteristics of the target user.

[0114] S704: When the current behavior feature satisfies a display condition of a recommendation card, display at least one recommendation card corresponding to the content to be recommended.

[0115] The specific implementation of steps S701 to S704 can refer to the detailed description in other embodiments of the present disclosure, and will not be described in detail here.

[0116] S705: For each recommended card, determine the click rate of the recommended card based on the click rate prediction model.

[0117] The click rate prediction model may be a reward model, and the structure of the click rate prediction model may be a Decoder-only Transformer structure.

[0118] In some embodiments, the recommendation words in the recommendation card, the target user's behavior sequence in the second preset time period, and the target user's portrait are input into the click rate prediction model to obtain the click rate. Thus, the target user's click rate on the recommendation card can be more accurately estimated by combining the target user's portrait and behavior information.

[0119] In some embodiments, Figure 8 A schematic diagram of a click rate prediction model provided by an embodiment of the present disclosure is shown in FIG. Figure 8 As shown, the training method of the click rate prediction model may include: obtaining training data, wherein the training data includes recommendation language samples, user portrait samples, user historical behavior sequence samples and click rate labels. The recommendation language samples, user portrait samples, user historical behavior sequence samples and click rate labels are input into the click rate prediction model to be trained to obtain the predicted click rate and the predicted behavior sequence corresponding to the historical behavior sequence, and the target loss is determined according to the recommendation loss between the predicted click rate and the click rate label, and the contrastive loss between the historical behavior sequence and the predicted behavior sequence, and the click rate prediction model is trained.

[0120] The i+1th behavior can be predicted based on the first i behaviors in the historical behavior sequence to obtain a predicted behavior sequence. In some embodiments, the remaining behaviors except the first i behaviors can be masked by a masked-transformer, so that the i+1th behavior can be predicted based on the first i behaviors in the historical behavior sequence.

[0121] The second preset time period may be a time period before the current moment.

[0122] The behavior sequence corresponding to the second preset time period may be the target user's click, feedback, and browsing behaviors on the content within the second preset time period.

[0123] In some embodiments, third sample data is determined, wherein the third sample data includes corresponding click information of the recommended card and consumption information of the follow-up content of the recommended card, and the third sample data is used to update and train the click-through rate prediction model. Thus, the click-through rate prediction model can be updated according to the click information of the target user on the recommended card and the consumption information of the follow-up content, thereby improving the accuracy of the click-through rate prediction model in predicting the click-through rate.

[0124] S706: Obtain second interaction information corresponding to the recommended card.

[0125] In some embodiments, the second interaction information corresponding to the recommended card is determined based on the click information corresponding to the recommended card and the consumption information of the follow-up content of the recommended card, wherein the follow-up content is the content displayed after the recommended card is clicked. Thus, the interaction information of the two dimensions of the click situation of the recommended card and the consumption information of the follow-up content can be combined to provide more comprehensive interaction information for accurately determining the score of the recommended card, thereby improving the accuracy of the determined score of the recommended card.

[0126] The click information corresponding to the recommended card may include the click information of the target user on the recommended card, or the number of clicks on the recommended card by other users, or the ratio of the number of clicks on the recommended card to the number of recommendations.

[0127] The consumption information of the follow-up content of the recommendation card may include the consumption information of the follow-up content by the target user, and may also include the consumption information of the follow-up content by other users. This disclosure does not limit this.

[0128] Fig. 9 A schematic diagram of a display interface provided by an embodiment of the present disclosure is shown as follows: Fig. 9 As shown, in Figure 3 or Figure 4 When a recommendation card in the video is clicked, waiting information can be displayed in the display interface (for example, fresh content will be presented to you soon).

[0129] Fig.10 A schematic diagram of displaying follow-up content provided by an embodiment of the present disclosure is shown in FIG. Fig.10 As shown, after the recommendation card is clicked, the display interface will be refreshed to display follow-up content 1, follow-up content 2, etc. related to the recommendation.

[0130] S707: Determine a score for the recommended card based on the click rate and the second interaction information.

[0131] In some embodiments, the higher the click-through rate, the higher the score; the click information corresponding to the recommended card indicates that the greater the ratio of the number of clicks to the number of recommendations, the higher the score; the consumption information of the follow-up content of the recommended card indicates that the better the quality of the follow-up content, the higher the score.

[0132] In some embodiments, when the second interaction information includes the consumption information of the follow-up content, the correlation between the follow-up resources and the recommendation words can be determined based on the consumption information of the follow-up content, and then the quality of the follow-up resources can be evaluated based on the consumption information of the follow-up content and the correlation between the follow-up resources and the recommendation words. Then, the score of the recommendation card can be comprehensively analyzed by combining the click-through rate, the evaluation of the follow-up resources, and the click information corresponding to the recommendation card.

[0133] In some embodiments, the follow-up content clicked by the user can be used as a positive sample, and the follow-up content not clicked can be displayed as a negative sample. The third model can be fine-tuned through comparative learning to achieve the correlation evaluation between the follow-up resources and the recommendation. Then, the correlation between the follow-up resources and the recommendation can be determined through the third model.

[0134] S708, determining first sample data, wherein the first sample data includes the score of the recommendation card, the content to be recommended corresponding to the recommendation card, the description information of the content of interest to the target user, and the popular search statements, and the first sample data is used to update and train the large model.

[0135] In the disclosed embodiment, after determining the score corresponding to the recommended card, the large model can be updated and trained based on the score of the recommended card, the recommended content corresponding to the recommended card, the target user's content description information of interest, and popular search statements, thereby improving the performance of the large model. In subsequent recommendation tasks, recommended cards that the target user is more interested in can be generated, thereby improving the accuracy of recommendations.

[0136] In the disclosed embodiment, after displaying at least one recommendation card corresponding to the content to be recommended, the click rate of the recommendation card can be determined for each recommendation card based on the click rate prediction model, the second interaction information corresponding to the recommendation card can be obtained, the score of the recommendation card can be determined based on the click rate and the second interaction information, and finally the first sample data can be determined, wherein the first sample data includes the score of the recommendation card, the content to be recommended corresponding to the recommendation card, the description information of the content of interest to the target user and the popular search sentences, and the first sample data is used to update and train the large model. Thus, the quality of the recommendation card can be comprehensively judged from the predicted click rate of the recommendation card and the real interaction information of the recommendation card, and then based on the quality of the recommendation card, the content to be recommended corresponding to the recommendation card, the description information of the content of interest to the target user and the popular search sentences, the large model can be guided to be updated, thereby improving the performance of the large model, so that in subsequent recommendation tasks, recommendation cards that the target user is more interested in can be generated, thereby improving the accuracy of the recommendation.

[0137] Fig.11 is a flowchart of a recommendation method based on a large model provided according to another embodiment of the present disclosure; Fig.11 As shown, the large model-based recommendation method includes:

[0138] S1101, determining the description information of the content of interest corresponding to the target user.

[0139] S1102, input the content to be recommended, the description information of the content of interest and the current hot search sentence into the big model, and generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains the recommendation words associated with the content to be recommended.

[0140] S1103, obtaining the current behavior characteristics of the target user.

[0141] S1104: When the current behavior feature satisfies a display condition of a recommendation card, display at least one recommendation card corresponding to the content to be recommended.

[0142] S1105: For each recommended card, determine the click rate of the recommended card based on the click rate prediction model.

[0143] S1106: Obtain second interaction information corresponding to the recommended card.

[0144] S1107: Determine a score for the recommended card based on the click rate and the second interaction information.

[0145] The specific implementation of steps S1101 to S1107 can refer to the detailed description in other embodiments of the present disclosure, and will not be described in detail here.

[0146] S1108: When any to-be-recommended content corresponds to at least two recommendation cards, determine recommendation weights corresponding to the at least two recommendation cards respectively based on the score of each of the at least two recommendation cards.

[0147] In some embodiments, at least two recommendation cards may be generated for the same content to be recommended, wherein the recommendation words in each recommendation card are different.

[0148] In some embodiments, a recommended card with a higher score has a higher recommendation weight.

[0149] S1109, determine the second sample data, wherein the second sample data includes a recommendation card, a recommendation weight corresponding to the recommendation card, any content to be recommended, description information of the content of interest to the target user, and popular search statements, and the second sample data is used to update and train the large model.

[0150] In the disclosed embodiment, after determining the recommendation weight corresponding to the recommendation card, the big model can be updated and trained based on any content to be recommended, the recommendation card corresponding to any recommended content, the recommendation weight corresponding to the recommendation card, the target user's content description information and popular search statements, so that the big model can learn the recommendation weight corresponding to the recommendation card corresponding to any content to be recommended, and then when any recommended content is recommended again, the recommendation card with a higher recommendation weight can be displayed to the user first, thereby improving the recommendation accuracy.

[0151] In the disclosed embodiment, after displaying the recommendation card corresponding to at least one content to be recommended, the click rate of the recommendation card can be determined for each recommendation card based on the click rate prediction model, and the second interaction information corresponding to the recommendation card can be obtained. The score of the recommendation card can be determined based on the click rate and the second interaction information. In the case where any content to be recommended corresponds to at least two recommendation cards, the recommendation weights corresponding to the at least two recommendation cards can be determined based on the score of each recommendation card in the at least two recommendation cards, and finally the second sample data can be determined, wherein the second sample data includes the recommendation card, the recommendation weight corresponding to the recommendation card, any content to be recommended, the description information of the content of interest of the target user, and the popular search statements, and the second sample data is used to update the training of the large model. Thus, the recommendation weight of the recommendation card can be determined according to the score of the recommendation card, and the large model can be guided to learn the recommendation weight corresponding to the recommendation card under any content to be recommended, and then when any recommended content is recommended again, the recommendation card with a higher recommendation weight can be displayed to the user first, thereby improving the accuracy of the recommendation.

[0152] Fig.12 is a structural schematic diagram of a large model-based recommendation device provided according to an embodiment of the present disclosure;

[0153] like Fig.12 As shown, the large model-based recommendation device 1200 includes:

[0154] Determination module 1201, used to determine the description information of the content of interest corresponding to the target user;

[0155] A generating module 1202 is used to input the content to be recommended, the description information of the content of interest and the current hot search phrase into the big model, and generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains a recommendation phrase associated with the content to be recommended;

[0156] The acquisition module 1203 is used to acquire the current behavior characteristics of the target user;

[0157] The display module 1204 is used to display at least one recommendation card corresponding to the content to be recommended when the current behavior characteristics meet the display conditions of the recommendation card.

[0158] In some embodiments of the present disclosure, a first processing module is further included, which is used to:

[0159] Acquire first interaction information of each candidate content in the candidate content library within a first preset time period;

[0160] According to the first interactive information of each candidate content, the current content to be recommended is determined from the candidate content library.

[0161] In some embodiments of the present disclosure, the display module 1204 is used to:

[0162] When the current behavior feature satisfies the display condition of the recommended card, determining the type of the currently satisfied display condition;

[0163] Determining target recommended content based on the type of display conditions that are met;

[0164] Display the recommendation card corresponding to the target recommended content.

[0165] In some embodiments of the present disclosure, the display module 1204 is used to:

[0166] In the case where the display condition satisfied is of the first type, determining the target recommended content based on the content currently consumed by the target user; or,

[0167] When the satisfied display condition is of the second type, target recommended content is determined based on the content currently displayed on the display interface.

[0168] In some embodiments of the present disclosure, the display module 1204 is used to:

[0169] Determine the to-be-recommended content of the same type as the currently consumed content as the target recommended content; or,

[0170] The to-be-recommended content whose similarity to the currently consumed content is greater than a first threshold is determined as the target recommended content.

[0171] In some embodiments of the present disclosure, the display module 1204 is used to:

[0172] Determine the to-be-recommended content whose similarity to the currently displayed content is less than a second threshold as the target recommended content; or

[0173] The to-be-recommended content that is not of the same type as the currently displayed content is determined as the target recommended content.

[0174] In some embodiments of the present disclosure, a second processing module is further included, which is used to:

[0175] For each recommended card, determine the click rate of the recommended card based on the click rate prediction model;

[0176] Obtaining second interaction information corresponding to the recommended card;

[0177] Determine a score of the recommended card based on the click rate and the second interaction information;

[0178] Determine first sample data, wherein the first sample data includes the score of the recommendation card, the content to be recommended corresponding to the recommendation card, the description information of the content of interest to the target user, and the popular search statements, and the first sample data is used to update and train the large model.

[0179] In some embodiments of the present disclosure, the second processing module is further configured to:

[0180] In the case where any to-be-recommended content corresponds to at least two recommendation cards, determining recommendation weights corresponding to the at least two recommendation cards respectively based on the score of each of the at least two recommendation cards;

[0181] Determine second sample data, wherein the second sample data includes recommendation cards, recommendation weights corresponding to the recommendation cards, any content to be recommended, description information of the content of interest to the target user, and popular search statements, and the second sample data is used to update and train the large model.

[0182] In some embodiments of the present disclosure, the second processing module is used to:

[0183] The second interaction information corresponding to the recommended card is determined according to the click information corresponding to the recommended card and the consumption information of the follow-up content of the recommended card, wherein the follow-up content is the content displayed after the recommended card is clicked.

[0184] In some embodiments of the present disclosure, the second processing module is used to:

[0185] The recommendation words in the recommendation card, the behavior sequence of the target user in the second preset time period, and the portrait of the target user are input into the click-through rate prediction model to obtain the click-through rate.

[0186] In some embodiments of the present disclosure, the device further includes a third processing module, which is used to:

[0187] Determine third sample data, wherein the third sample data includes corresponding click information of the recommended card and consumption information of follow-up content of the recommended card, and the third sample data is used to update and train the click rate prediction model.

[0188] It should be noted that the aforementioned explanation of the large model-based recommendation method is also applicable to the large model-based recommendation device of this embodiment, and will not be repeated here.

[0189] In the disclosed embodiment, the description information of the content of interest corresponding to the target user is first determined, and the content to be recommended, the description information of the content of interest, and the current popular search statements are input into the large model to generate at least one recommendation card corresponding to the content to be recommended, and then the current behavior characteristics of the target user are obtained. Finally, when the current behavior characteristics meet the display conditions of the recommendation card, at least one recommendation card corresponding to the content to be recommended is displayed. In this way, not only can different recommendation cards be generated for different users for the same content to be recommended by combining the description information of the content of interest and the popular search statements of different users, so that the generated recommendation cards are more in line with the user's preferences, but also the recommendation cards can be displayed to the user according to the user's current behavior, thereby improving the diversity and accuracy of the recommendation forms.

[0190] 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.

[0191] Fig.13 A schematic block diagram of an example electronic device 800 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.

[0192] like Fig.13 As shown, the device 1300 includes a computing unit 1301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from a storage unit 1308 into a random access memory (RAM) 1303. In the RAM 1303, various programs and data required for the operation of the device 1300 can also be stored. The computing unit 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0193] A number of components in the device 1300 are connected to the I / O interface 1305, including: an input unit 1306, such as a keyboard, a mouse, etc.; an output unit 1307, such as various types of displays, speakers, etc.; a storage unit 1308, such as a disk, an optical disk, etc.; and a communication unit 1309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1309 allows the device 1300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0194] The computing unit 1301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1301 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 1301 performs the various methods and processes described above, such as a recommendation method based on a large model. For example, in some embodiments, the recommendation method based on a large model may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1300 via the ROM 1302 and / or the communication unit 1309. When the computer program is loaded into the RAM 1303 and executed by the computing unit 1301, one or more steps of the recommendation method based on the large model described above may be performed. Alternatively, in other embodiments, the computing unit 1301 may be configured to execute the large model-based recommendation method in any other appropriate manner (eg, by means of firmware).

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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).

[0199] 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.

[0200] 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 between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0201] 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.

[0202] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In the description of the present disclosure, the words "if" and "if" used can be interpreted as "at the time of" or "when" or "in response to determination" or "under the circumstances of".

[0203] 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 based on a large model, comprising: Determine the description information of the content of interest corresponding to the target user; Inputting the content to be recommended, the description information of the content of interest and the current hot search phrase into the big model, generating at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains a recommendation phrase associated with the content to be recommended; Acquire current behavior characteristics of the target user; When the current behavior feature satisfies the display condition of the recommendation card, at least one recommendation card corresponding to the content to be recommended is displayed.

2. The method of claim 1, wherein: Before inputting the content to be recommended, the description information of the content of interest and the current hot search phrase into the big model to generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card includes a recommendation phrase associated with the content to be recommended, the method further includes: Acquire first interaction information of each candidate content in the candidate content library within a first preset time period; According to the first interactive information of each candidate content, the current content to be recommended is determined from the candidate content library.

3. The method of claim 1, wherein: The step of displaying at least one recommendation card corresponding to the content to be recommended when the current behavior feature meets the display condition of the recommendation card includes: In the case where the current behavior characteristic satisfies the display condition of the recommendation card, determining the type of the display condition currently satisfied; Determining target recommended content based on the type of the satisfied display condition; Display the recommendation card corresponding to the target recommended content.

4. The method of claim 3, wherein: The determining target recommended content based on the type of the satisfied display condition includes: In the case where the satisfied display condition is of the first type, determining the target recommended content based on the content currently consumed by the target user; or When the satisfied display condition is of the second type, the target recommended content is determined based on the content currently displayed on the display interface.

5. The method of claim 4, wherein: The determining the target recommended content based on the content currently consumed by the target user includes: Determine the to-be-recommended content of the same type as the currently consumed content as the target recommended content; or The to-be-recommended content whose similarity with the currently consumed content is greater than a first threshold is determined as the target recommended content.

6. The method of claim 4, wherein: The determining the target recommended content based on the content currently displayed on the display interface includes: Determine the to-be-recommended content whose similarity to the currently displayed content is less than a second threshold as the target recommended content; or The to-be-recommended content that is not of the same type as the currently displayed content is determined as the target recommended content.

7. The method according to any one of claims 1 to 6, wherein: After displaying the recommendation card corresponding to at least one content to be recommended, the method further includes: For each recommended card, determining the click rate of the recommended card based on the click rate prediction model; Acquire second interaction information corresponding to the recommended card; Determining a score of the recommended card based on the click rate and the second interaction information; Determine first sample data, wherein the first sample data includes the score of the recommendation card, the content to be recommended corresponding to the recommendation card, the description information of the content of interest to the target user and the popular search statements, and the first sample data is used to update and train the large model.

8. The method of claim 7, wherein: After determining the score of the recommended card, the method further includes: In the case where any to-be-recommended content corresponds to at least two recommendation cards, determining the recommendation weights respectively corresponding to the at least two recommendation cards based on the score of each of the at least two recommendation cards; Determine second sample data, wherein the second sample data includes recommendation cards, recommendation weights corresponding to the recommendation cards, any content to be recommended, description information of the content of interest to the target user, and the popular search statements, and the second sample data is used to update and train the large model.

9. The method of claim 7, wherein: The acquiring the second interaction information corresponding to the recommended card includes: The second interaction information corresponding to the recommendation card is determined according to the click information corresponding to the recommendation card and the consumption information of the follow-up content of the recommendation card, wherein the follow-up content is the content displayed after the recommendation card is clicked.

10. The method of claim 7, wherein: The step of determining the click rate of each recommended card based on the click rate prediction model includes: The recommendation words in the recommendation card, the behavior sequence of the target user in the second preset time period and the portrait of the target user are input into the click rate prediction model to obtain the click rate.

11. The method of claim 10, wherein: The method further comprises: Determine third sample data, wherein the third sample data includes corresponding click information of the recommended card and consumption information of follow-up content of the recommended card, and the third sample data is used to update and train the click-through rate prediction model.

12. A recommendation device based on a large model, comprising: A determination module, used to determine the description information of the content of interest corresponding to the target user; A generation module, configured to input the content to be recommended, the description information of the content of interest and the current hot search phrase into the large model, and generate at least one recommendation card corresponding to the content to be recommended, wherein the recommendation card contains a recommendation phrase associated with the content to be recommended; An acquisition module, used to acquire the current behavior characteristics of the target user; The display module is used to display at least one recommendation card corresponding to the content to be recommended when the current behavior characteristics meet the display conditions of the recommendation card.

13. The device of claim 12, wherein: Also included is a first processing module, configured to: Acquire first interaction information of each candidate content in the candidate content library within a first preset time period; According to the first interactive information of each candidate content, the current content to be recommended is determined from the candidate content library.

14. The device of claim 12, wherein: The display module is used for: In the case where the current behavior characteristic satisfies the display condition of the recommendation card, determining the type of the display condition currently satisfied; Determining target recommended content based on the type of the satisfied display condition; Display the recommendation card corresponding to the target recommended content.

15. The device of claim 14, wherein: The display module is used for: In the case where the satisfied display condition is of the first type, determining the target recommended content based on the content currently consumed by the target user; or When the satisfied display condition is of the second type, the target recommended content is determined based on the content currently displayed on the display interface.

16. The device of claim 15, wherein: The display module is used for: Determine the to-be-recommended content of the same type as the currently consumed content as the target recommended content; or The to-be-recommended content whose similarity with the currently consumed content is greater than a first threshold is determined as the target recommended content.

17. The device of claim 15, wherein: The display module is used for: Determine the to-be-recommended content whose similarity to the currently displayed content is less than a second threshold as the target recommended content; or The to-be-recommended content that is not of the same type as the currently displayed content is determined as the target recommended content.

18. The device according to any one of claims 12 to 17, wherein: Also included is a second processing module, configured to: For each recommended card, determining the click rate of the recommended card based on the click rate prediction model; Acquire second interaction information corresponding to the recommended card; Determining a score of the recommended card based on the click rate and the second interaction information; Determine first sample data, wherein the first sample data includes the score of the recommendation card, the content to be recommended corresponding to the recommendation card, the description information of the content of interest to the target user and the popular search statements, and the first sample data is used to update and train the large model.

19. The device of claim 18, wherein: The second processing module is further used for: In the case where any to-be-recommended content corresponds to at least two recommendation cards, determining the recommendation weights respectively corresponding to the at least two recommendation cards based on the score of each of the at least two recommendation cards; Determine second sample data, wherein the second sample data includes recommendation cards, recommendation weights corresponding to the recommendation cards, any content to be recommended, description information of the content of interest to the target user, and the popular search statements, and the second sample data is used to update and train the large model.

20. The apparatus of claim 18, wherein: The second processing module is used to: The second interaction information corresponding to the recommendation card is determined according to the click information corresponding to the recommendation card and the consumption information of the follow-up content of the recommendation card, wherein the follow-up content is the content displayed after the recommendation card is clicked.

21. The apparatus of claim 18, wherein: The second processing module is used to: The recommendation words in the recommendation card, the behavior sequence of the target user in the second preset time period and the portrait of the target user are input into the click rate prediction model to obtain the click rate.

22. The device of claim 21, wherein: The device further comprises a third processing module, configured to: Determine third sample data, wherein the third sample data includes corresponding click information of the recommended card and consumption information of follow-up content of the recommended card, and the third sample data is used to update and train the click-through rate prediction model.

23. 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 11.

24. 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 11.

25. A computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 11.

Images