Method, device and electronic equipment for playing images

Abstract

The application is suitable for the technical field of intelligent album, and provides a method and device for playing images and electronic equipment. The application overcomes the technical problem of rigid arrangement order of intelligent album image playing in the prior art. The application collects at least one situational feature conforming to the current situation to generate a situational feature set; obtains a plurality of matched situational images according to the situational feature set; and plays the plurality of situational images according to the current situation. The application can perceive the current situation, obtain a plurality of matched situational images according to a situational feature set composed of situational features of the current situation, play the plurality of situational images according to the current situation, provide a personalized image playing method more suitable for the current life situation and current emotional state of the user, improve the situational adaptability of the intelligent album and the use experience of the user when reviewing images, and meet the use requirements of multiple application scenarios such as daily review and family scene sharing.

Description

Technical Field

[0001] This application belongs to the field of smart photo album technology, and in particular relates to methods, apparatus and electronic devices for playing images. Background Technology

[0002] Existing smart photo album products can typically play photos automatically. However, current smart photo albums usually only play photos in chronological or random order, resulting in a rigid playback arrangement that fails to fully satisfy the user experience. Summary of the Invention

[0003] This application provides a method, apparatus, and electronic device for playing images, which can solve the technical problem of rigid image arrangement order in existing smart photo albums.

[0004] In a first aspect, embodiments of this application provide a method for playing an image, including: Collect at least one context feature that fits the current context, and generate a context feature set; Based on the set of context features, obtain multiple context images that match the set of context features; Play the multiple context images according to the current context.

[0005] In one possible implementation of the first aspect, the at least one contextual feature includes at least one of the following: time feature, behavioral feature, content feature, and environmental feature; the collection of at least one contextual feature that conforms to the current context includes at least one of the following: Determine the time characteristics based on whether the current time matches the scheduled time; Determine behavioral characteristics based on the current user's preferred behaviors; Based on the newly added images, determine the content features; Determine environmental characteristics based on current weather data.

[0006] In one possible implementation of the first aspect, obtaining multiple context images matching the context feature set according to the context feature set includes: Based on the set of context features, query the topic database to obtain context topics that match the set of context features; Based on the given context theme, obtain one or more context labels; Based on the context tags, the photo album is queried to obtain multiple context images.

[0007] In one possible implementation of the first aspect, the at least one contextual feature corresponds to a corresponding weight, the topic library includes at least one candidate topic, and the step of querying the topic library according to the contextual feature set to obtain a contextual topic matching the contextual feature set includes: Based on the at least one contextual feature, query the topic database to obtain candidate topics that intersect with the at least one contextual feature; Based on the weights corresponding to the at least one context feature, determine the weighted matching scores of the context feature set and the at least one candidate topic respectively; The candidate topic with the highest weighted matching score is determined as the context topic that matches the context feature set.

[0008] In one possible implementation of the first aspect, the step of querying a topic library based on the context feature set to obtain a context topic that matches the context feature set further includes: Filter out candidate topics that meet the filtering conditions, which include at least one of the following: the matching score between the candidate topic and the content feature is less than a first threshold, or the candidate topic belongs to a topic that has been played in the first time period.

[0009] In one possible implementation of the first aspect, obtaining one or more context labels based on the context topic includes: Based on the aforementioned context theme, a tag library is queried to obtain a candidate tag set, which includes one or more candidate tags. Based on the set of contextual features, the candidate label set is adjusted to obtain one or more contextual labels.

[0010] In one possible implementation of the first aspect, the step of adjusting the candidate label set according to the context feature set to obtain one or more context labels includes at least one of the following: If the cosine similarity between the candidate label and the environmental feature is lower than the second threshold, the candidate label is filtered out. If the number of images containing the candidate tag in the album library is less than the third threshold, then the weight of the candidate tag is reduced. If the number of images with the candidate tag in the album library is greater than the fourth threshold, then the weight of the candidate tag is increased. If the number of images in the album library in the candidate tag set is less than the fifth threshold, then the tag corresponding to the behavioral feature is added to the candidate tag set.

[0011] In one possible implementation of the first aspect, playing the plurality of context images according to the current context includes: Based on the current context, the multiple context images are played and arranged to obtain playback information that conforms to the current context; Play the multiple contextual images according to the playback information.

[0012] Secondly, embodiments of this application provide an apparatus for playing images, comprising: The first acquisition module is used to acquire at least one context feature that matches the current context and generate a context feature set; The second obtaining module is used to obtain multiple situation images that match the situation feature set based on the situation feature set; The third playback module is used to play the multiple context images according to the current context.

[0013] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device performs the method as described in any one of the first aspects above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any one of the first aspects above.

[0015] Fifthly, embodiments of this application provide a computer program product, which includes a computer program that, when run, causes the method as described in any one of the first aspects above to be performed.

[0016] The beneficial effects of the first aspect of this application compared with the prior art are: This application overcomes the technical problem of rigid image playback and arrangement order in existing smart photo albums. This application collects at least one contextual feature that matches the current context, generates a contextual feature set, obtains multiple contextual images matching the contextual feature set, and plays multiple contextual images according to the current context. This application can perceive the current context and obtain multiple matching contextual images based on the contextual feature set composed of the contextual features of the current context. This allows for the playback of multiple contextual images according to the current context, providing a more personalized image playback method that better fits the user's current life situation and emotional state. This improves the contextual adaptability of smart photo albums and the user experience when viewing and reviewing images, meeting the needs of users in multiple application scenarios such as daily memory review and family scene sharing.

[0017] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic flowchart of an image playback method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a method for playing images according to another embodiment of this application; Figure 3 This is a schematic diagram of the structure of an image playback device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0021] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0022] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0023] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0024] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0026] Figure 1 This is a schematic flowchart of an image playback method provided in an embodiment of this application.

[0027] The image playback method provided in this application can be applied to hardware or software products of smart photo albums. When used as a hardware product, a smart photo album can take various forms, such as a photo frame or a poster. When used as a software product, a smart photo album can take the form of an app or software program. In this application, "image" includes, but is not limited to, static images such as pictures and photos, as well as dynamic images such as videos and animated photos.

[0028] Furthermore, this application can also be applied to various scenarios. First, in the personal consumer electronics field, such as the daily automatic photo album review scenario of devices like smart photo frames, smart TVs, smartphones, and smart tablets. Second, in smart home scenarios, such as the emotional connection and memory review scenario of smart home control screens and home audio-visual systems. Third, in commercial service scenarios, such as creating a themed atmosphere and providing customer care in offline stores, boutique hotels, and cultural tourism homestays. Fourth, in public culture and cultural tourism scenarios, such as displaying local culture and life memories in scenic spots, museums, and community cultural centers. Fifth, in education and school scenarios, such as recording campus life and student growth through smart screens and electronic class signs.

[0029] The technical solution comprising steps S11 to S13 of this application can be triggered at a fixed time or in response to user triggering. For example, this technical solution can be triggered periodically at various times such as 7:00 AM and 8:00 PM daily. Through the mechanism of timed triggering and automatic updates, a continuous intelligent personalized photo album service can be achieved without manual user intervention. For example, this application can cycle through the technical solution comprising steps S11 to S13 daily, continuously obtaining the latest set of contextual features to continuously obtain contextual images that better match the latest context, updating and generating a daily dynamic photo album, providing users with a personalized image review experience that fits their daily life context.

[0030] S11, Collect at least one context feature that fits the current context, and generate a context feature set.

[0031] The current context includes, but is not limited to, information that matches the current characteristics, such as the current date, current or recent user behavior, currently or recently added images, and current weather.

[0032] Contextual features refer to characteristic information that fits the current context. For example, if the current date is a user's birthday or wedding anniversary, then the contextual features could be "birthday" or "wedding anniversary". Similarly, if the current weather is raining or snowing, then the contextual features could be "rainy day" or "snowy day".

[0033] After collecting at least one contextual feature that fits the current context, these contextual features can be combined to generate a contextual feature set. This contextual feature set includes at least one contextual feature that fits the current context. For example, the contextual feature set could be "birthday, rainy day," or "wedding anniversary, snowy day," etc.

[0034] S12, Based on the context feature set, obtain multiple context images that match the context feature set.

[0035] A contextual image is an image whose content matches the current context.

[0036] Content analysis can be performed on images in the photo library, and the image content of each image can be labeled using methods such as text vector representation. After obtaining a set of context features consisting of at least one context feature that matches the current context, for example, the photo library can be queried based on the text vector representation of the context features contained in the context feature set to obtain multiple context images that match the corresponding text vector representation. The image content of these context images usually also matches the corresponding text vector representation, so the image content of these context images also matches the current context. For example, when the context feature set is "birthday, rainy day", the image content of the context images that can be obtained usually also includes the user's childhood photos, the user's photos on rainy days, etc.

[0037] S13, Play multiple context images according to the current context.

[0038] In this article, "playing multiple contextual images" refers to displaying multiple images sequentially in a certain order.

[0039] When playing multiple contextual images, the playback order and theme text can be designed according to the current context. For example, when the contextual features are "birthday, rainy day", multiple contextual images of the user can be played according to the user's past growth experience from distant to recent. Text such as "Happy Birthday" can also be generated and displayed to the user along with the contextual images to enhance the atmosphere.

[0040] This application overcomes the technical problem of rigid image playback and arrangement order in existing smart photo albums. This application collects at least one contextual feature that matches the current context, generates a contextual feature set, obtains multiple contextual images matching the contextual feature set, and plays multiple contextual images according to the current context. This application can perceive the current context and obtain multiple matching contextual images based on the contextual feature set composed of the contextual features of the current context. This allows for the playback of multiple contextual images according to the current context, providing a more personalized image playback method that better fits the user's current life situation and emotional state. This improves the contextual adaptability of smart photo albums and the user experience when viewing and reviewing images, meeting the needs of users in multiple application scenarios such as daily memory review and family scene sharing.

[0041] In one embodiment, at least one contextual feature includes at least one of the following: time feature, behavioral feature, content feature, and environmental feature. In the above embodiment, collecting at least one contextual feature that conforms to the current context in S11 includes at least one of the following S111 to S114.

[0042] S111, determine the time characteristics based on whether the current time matches the scheduled time.

[0043] For example, it can detect whether the current date is a traditional festival, family anniversary, birthday, or whether it falls within the working hours of a weekday, the rest period of a weekday, or the rest period of a weekend.

[0044] S112, Determine behavioral characteristics based on the current user's preferred behavior.

[0045] For example, you can analyze a user's historical image playback data to extract behavioral characteristics such as the user's preferred image types and preferred playback times.

[0046] S113, Determine content features based on the newly added image.

[0047] It can scan current or recently added images in the photo library, and optionally, it can select images from the same period in history, such as images from the same date last year, and extract the tag distribution features of these images as content features.

[0048] S114, Determine environmental characteristics based on current weather data.

[0049] It can obtain real-time weather data (such as sunny, rainy, snowy, etc.) of the user's location as environmental features.

[0050] It should be noted that the information collection process (such as the facial image collection process, fingerprint information collection process, etc.) / feature extraction process / user movement trajectory tracking involved in this application are all performed with the user's knowledge and permission. That is, the information collection process / feature extraction process / user movement trajectory tracking comply with the requirements of relevant standards and do not constitute acts that harm the public interest.

[0051] This application uses at least one of time features, behavioral features, content features, and environmental features as contextual features to obtain feature information that matches the current context, accurately obtain life scenes and emotional states that are close to the user, and thus lay the technical foundation for obtaining contextual images that match the current context and providing image playback methods that match the current context.

[0052] In one embodiment, in S12 of the above embodiment, multiple situational images matching the situational feature set are obtained according to the situational feature set, including the following S121 to S123.

[0053] S121. Based on the set of context features, query the topic database to obtain context topics that match the set of context features.

[0054] Here, a request to "generate a topic for the current context" can be initiated to the topic library based on the context feature set. The topic library pre-stores multiple semantic topics, such as "family reunion," "outdoor sunshine," and "cozy home." The topic library can select a context topic that fits the current context from multiple semantic topics based on the context feature set, such as "Spring Festival reunion, auspicious snow for a bountiful year."

[0055] S122, Based on the context theme, obtain one or more context labels.

[0056] Here, after obtaining the context theme, a request to retrieve "context tags" can be initiated from the tag library based on the context theme. The tag library pre-stores multiple tags. The tag library can then select context tags from these tags that best fit the current context based on the context theme.

[0057] S123, based on the context tags, query the photo library to obtain multiple context images.

[0058] Based on the text vector representation of context tags, a vector search algorithm can be used to select multiple images from the photo library with high vector matching degrees to the context tags as context images. For example, an open-source image search algorithm can be used. The input context tag vector can be used, and the open-source image search algorithm can directly return several images that best match the context tags (high cosine similarity between the tag vector and the image vector), resulting in multiple context images for final playback.

[0059] This application provides a specific implementation method for obtaining multiple contextual images that match a contextual feature set. By obtaining matching contextual themes and then matching contextual tags based on the contextual feature set, the accuracy of the obtained contextual images can be guaranteed. Furthermore, based on the mapping relationship between semantic themes and tags, combined with vector search technology, this application can achieve efficient matching of image content and themes, thereby improving the accuracy of personalized recommendations.

[0060] In one embodiment, at least one context feature corresponds to a corresponding weight, and the topic library includes at least one candidate topic. In the above embodiment, S121 is to query the topic library according to the context feature set to obtain the context topic that matches the context feature set, including the following S1211 to S1213.

[0061] S1211, Based on at least one contextual feature, query the topic database to obtain candidate topics that intersect with at least one contextual feature.

[0062] First, a preliminary screening step can be performed using a candidate pool. Topics that intersect with at least one contextual feature are selected from the topic database as candidate topics. For example, if the environmental feature is "rainy day," then candidate topics such as "walking in the rain" and "listening to the rain" are selected.

[0063] S1212, Based on the weights corresponding to at least one context feature, determine the weighted matching scores of the context feature set and at least one alternative topic respectively.

[0064] This application's embodiments primarily illustrate examples where the contextual feature set simultaneously includes four features: time features, behavioral features, content features, and environmental features. The contextual feature set is represented by V={Ft,Fc,Fb,Fe}, where Ft represents the time feature, Fc represents the content feature, Fb represents the behavioral feature, and Fe represents the environmental feature. Those skilled in the art should understand that implementations including any one, two, or three of these four features in the contextual feature set also fall within the scope of this application. Each feature has a corresponding weight, and the sum of the four weights can, for example, be 1. A larger weight indicates a greater influence of the corresponding feature on topic selection and decision-making. Examples of the weights corresponding to the four features are illustrated below.

[0065] The weight of the time feature Ft is Wt=0.4. The weight of the time feature is a core weight and has the highest priority (such as statutory holidays and personal anniversaries).

[0066] The weight of content feature Fc is Wc=0.3. The weight of content feature is a basic weight. A higher weight for content feature can ensure that the number of images corresponding to the candidate themes selected later is sufficient to meet the playback conditions. For example, it can ensure that a large number of newly added or historical photos from the same period can be scanned for the candidate themes later.

[0067] The weight of behavioral feature Fc is Wb=0.2. The weight of behavioral features is a personalized weight, which can be adjusted based on the user's historical clicks and retention time.

[0068] The weight of environmental feature Fe is We=0.1. The weight of environmental feature is an auxiliary weight, used to create an atmosphere based on real-time weather data.

[0069] The weighted matching scores of the set of context features and at least one alternative topic can be calculated based on the following formula (1), according to the weights corresponding to at least one context feature.

[0070] (1) Where Tn represents the candidate topic, Fi represents any one of the time feature, behavior feature, content feature, and environment feature, Wi represents the weight of any one of the time feature, behavior feature, content feature, and environment feature, MatchScore(Fi, Tn) represents the matching degree between any feature of any dimension and the candidate topic keywords (for example, it can be determined based on cosine similarity, and the corresponding features are all non-negative numbers, with values ​​from 0 to 1), and S(Tn) represents the weighted matching score between the context feature set and at least one candidate topic.

[0071] S1213, the candidate topic with the highest weighted matching score is determined as the context topic that matches the context feature set.

[0072] After obtaining the weighted matching scores of each candidate topic, the candidate topic with the highest weighted matching score can be identified as the situation topic that matches the situation feature set.

[0073] This application embodiment queries a topic database based on at least one contextual feature to obtain candidate topics that intersect with at least one contextual feature; it determines the weighted matching score between the contextual feature set and at least one candidate topic based on the weight corresponding to the at least one contextual feature; and it identifies the candidate topic with the highest weighted matching score as the contextual topic that matches the contextual feature set. This application embodiment constructs a multi-dimensional weighted matching algorithm for determining candidate topics based on contextual features. It can normalize one or more collected contextual features, calculate the score of each candidate topic through a weighted scoring model, and then select the most matching topic for output. This application embodiment improves the matching degree between the selected contextual topic and the current context.

[0074] In one embodiment, S121 in the above embodiment, querying the topic library according to the context feature set to obtain the context topic that matches the context feature set, further includes the following S1214.

[0075] S1214, Filter out candidate topics that meet the filtering conditions. The filtering conditions include at least one of the following: the matching score between the candidate topic and the content features is less than the first threshold, or the candidate topic belongs to a topic that has been played in the first time period.

[0076] If the matching score (MatchScore(Fc,Tn)) between the candidate topic Tn and the content feature Fc is less than the first threshold (e.g., 0.1), it means that there are almost no images in the smart album that match the content of the candidate topic. Therefore, no matter how high the matching scores of other dimensions of the candidate topic are, the candidate topic will not be determined as a context topic. Candidate topics with a matching score of less than the first threshold are rejected outright, ensuring that there are enough images corresponding to the selected context topics for playback.

[0077] If a candidate theme has been played within the past (e.g., within the past 7 days), the weighted matching score S(Tn) of that candidate theme is lowered. This ensures that the selected scenario theme has not been played within the past, thus maintaining a sense of novelty for users when using the smart album.

[0078] This application embodiment ensures that the selected context theme has a sufficient number of context images by filtering out candidate themes that meet the filtering conditions, and also ensures that the selected context theme is not a recently played theme, thus ensuring the user's sense of novelty when using the smart album.

[0079] In one application embodiment, the context feature plan includes the following features: time feature Ft is "Chinese New Year's Day", environmental feature Fe is "snowfall", and behavioral feature Fb is "frequently checking family photos". The weighted matching score calculation result of the candidate theme and the context feature set in this application embodiment is as follows: Candidate theme T1 "Auspicious Snow for a Bountiful Year" has a high matching degree with the environmental feature. Candidate theme T2 "Spring Festival" has an even higher matching degree with the time feature, and due to the greater weight of the time feature, candidate theme T2 has the highest weighted matching score. Candidate theme T3 "Animals" will not be selected due to its low matching score. Finally, candidate theme T2 is determined as the context theme, and the context theme to be played is "Chinese New Year's Day: Reunion in Auspicious Snow".

[0080] In one embodiment, in the above embodiment S122, one or more context labels are obtained according to the context theme, including the following S1221 and S1222.

[0081] S1221, Based on the context topic, query the tag library to obtain a set of candidate tags, which includes one or more candidate tags.

[0082] The tag library contains multiple tags. By querying the tag library based on the context topic, a set of candidate tags, including one or more candidate tags, can be obtained.

[0083] S1222, Based on the context feature set, adjust the candidate label set to obtain one or more context labels.

[0084] The process of adjusting the candidate label set based on the context feature set includes, but is not limited to, removing candidate labels from the candidate label set based on the context feature set, and / or adding candidate labels to the candidate label set.

[0085] In this embodiment, instead of simply querying the tag library based on the context theme to obtain candidate tags, the candidate tag set is adjusted in conjunction with the context feature set to ensure that the obtained context expressions are more in line with the current context.

[0086] In one embodiment, in S1222 of the above embodiment, the candidate label set is adjusted according to the context feature set to obtain one or more context labels, including at least any one of the following S12221 to S12224.

[0087] Here, with the theme of "Spring Festival Reunion", the candidate tag set is as follows. Provide examples for [family, dinner party, outdoor fireworks, red, cleaning, temple fair].

[0088] S12221, If ​​the cosine similarity between the candidate label and the environmental features is lower than the second threshold, filter out the candidate label.

[0089] The cosine similarity between candidate labels and environmental features Fe can be calculated to perform semantic consistency filtering. If the environmental feature Fe is "indoor / home", candidate labels such as "outdoor fireworks" and "temple fair" can be reduced or eliminated from the candidate label set to prevent irrelevant image content, such as images containing the words "outdoor" or "outdoors", from being searched in subsequent steps based on these irrelevant candidate labels.

[0090] S12222, If the number of images with a candidate label in the album library is less than the third threshold, then reduce the weight of the candidate label.

[0091] S12223, If the number of images with a candidate label in the album library is greater than the fourth threshold, then increase the weight of the candidate label.

[0092] The system can pre-query the number of images corresponding to each tag in the album library. If the number of images for a subsequent tag (such as "cleaning") in the album library is less than a third threshold, the weight of that candidate tag is reduced to decrease the number of images retrieved through that tag. If the number of images for a candidate tag (such as "family") in the album library is greater than a fourth threshold, the weight of that candidate tag is increased. By detecting the number of images for candidate tags in the album library, content density verification can be achieved through weight adjustment.

[0093] S12224, If the number of images in the album library in the candidate label set is less than the fifth threshold, then the label corresponding to the behavioral feature is added to the candidate label set.

[0094] If the candidate label set If the number of images in the album is less than the fifth threshold, meaning the content coverage of the candidate tag set is insufficient in the current context, then the tag corresponding to the behavioral feature Fb can be added to the candidate tag set to achieve "dynamic semantic reinforcement". For example, if the number of images in the album is less than the fifth threshold and the user has recently taken many photos of pets, then the tag "pet" corresponding to the behavioral feature can be added to the candidate tag set.

[0095] This application embodiment adjusts the candidate label set according to the context feature set, which can avoid problems such as an overly bloated candidate label set and a candidate label set that does not match the context of the day, thus ensuring the accuracy of subsequent image search.

[0096] In one embodiment, S13 of the above embodiment plays multiple context images according to the current context, including the following S131 and S132.

[0097] S131, Based on the current context, play and arrange multiple context images to obtain playback information that conforms to the current context.

[0098] For example, the playback order of multiple contextual images can be adjusted based on the contextual logic (the sequence of events in the context) or the chronological order of the context. Another example is the ability to automatically generate personalized playback titles that fit the current context (such as "Reunion Amidst Auspicious Snow on the First Day of the Lunar New Year"). The arranged playback order and titles can be saved as playback information.

[0099] S132, Play multiple contextual images according to the playback information.

[0100] After obtaining playback information that matches the current context, multiple context images can be played according to the playback information. For example, multiple context images can be played in a pre-arranged playback order, the playback title can be displayed, and transition effects can be added between two context images to enhance the user's visual experience.

[0101] This application embodiment arranges the playback of multiple contextual images according to the current context to obtain playback information that matches the current context; and plays multiple contextual images according to the playback information. This application embodiment supports the dynamic playback of multiple contextual images according to the time and plot logic of the current context, and can generate personalized titles, enhancing the user's immersion and emotional resonance when reviewing contextual images.

[0102] Figure 2 This is a schematic flowchart of an image playback method provided in another embodiment of this application.

[0103] The smart album can trigger the album playback process at a set time every day, as shown in steps S21 to S232 below.

[0104] S21, Collect at least one context feature that matches the current context, and generate a context feature set.

[0105] Here, we can integrate multi-dimensional contextual features, such as time features, behavioral features, content features, and environmental features.

[0106] S221. Based on the set of context features, query the topic database to obtain context topics that match the set of context features.

[0107] After generating the contextual feature set, you can request the topic library to generate today's topic. After the topic library generates today's topic, it can return today's topic to the smart album, such as the contextual topic "Spring Festival Reunion, Auspicious Snow and Bountiful Year".

[0108] S222, Based on the context theme, obtain one or more context labels.

[0109] You can request context tags corresponding to a context theme from the tag library. Accordingly, the tag library returns one or more context tags that match the context theme.

[0110] S223, based on the context tags, query the photo library to obtain multiple context images.

[0111] Based on the text vectors of context labels, images with high cosine similarity can be searched in the photo library to obtain multiple context images with matching vectors.

[0112] S231, Based on the current context, play and arrange multiple context images to obtain playback information that conforms to the current context.

[0113] The playback order can be dynamically arranged, and personalized titles can be generated. This playback order and personalized titles can be stored as playback information.

[0114] S232, Play multiple contextual images according to the playback information.

[0115] Play multiple contextual images according to the stored playback information, and begin displaying today's dynamic photo album.

[0116] The smart photo album provided in this application embodiment can be automatically updated daily, providing a personalized image review experience that matches the context of the day.

[0117] This application's intelligent photo album system can realize image storage and playback. The tag library and theme library can collaboratively complete multi-dimensional image tag annotation and semantic theme-tag mapping construction. This application's embodiment overcomes the rigid playback order problem of existing technologies where photo albums can only play images in a fixed chronological order. This application's embodiment provides an intelligent planning logic of "current context perception, context theme matching, and dynamic arrangement of playback order." Through the system's pre-construction of a multi-dimensional tag system and theme mapping relationship, multi-dimensional perception is achieved by integrating multiple context features daily. Context themes that fit the day's context are matched and generated. Context images related to the context theme are filtered based on the many-to-many mapping between the theme library and tag library. Context images are then associated with context tags. The playback order is dynamically arranged and personalized titles are generated. The process of initiating context image playback is then realized, achieving intelligent photo album dynamic planning playback that closely reflects the user's life context and emotional state. This application's embodiment can replace the single-time, manually filtered image playback logic with multi-dimensional context perception, and can replace fixed playback with theme-driven dynamic arrangement.

[0118] Figure 3 This is a schematic diagram of the structure of an image playback device provided in an embodiment of this application.

[0119] like Figure 3 As shown, the image playback device includes a first acquisition module 31, a second acquisition module 32, and a third playback module 33.

[0120] The first acquisition module 31 is used to acquire at least one context feature that conforms to the current context and generate a context feature set; The second obtaining module 32 is used to obtain multiple situation images that match the situation feature set based on the situation feature set; The third playback module 33 is used to play the multiple context images according to the current context.

[0121] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3 Based on the corresponding embodiment, the at least one contextual feature includes at least one of the following: time feature, behavioral feature, content feature, and environmental feature, and the first acquisition module 31 is used to perform at least one of the following: Determine the time characteristics based on whether the current time matches the scheduled time; Determine behavioral characteristics based on the current user's preferred behaviors; Based on the newly added images, determine the content features; Determine environmental characteristics based on current weather data.

[0122] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3Based on the corresponding embodiment, the second obtaining module 32 includes: The fourth acquisition module is used to query the topic library based on the context feature set to obtain context topics that match the context feature set; The fifth acquisition module is used to obtain one or more context tags based on the context theme; The sixth module is used to query the photo album library based on the context tags to obtain multiple context images.

[0123] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3 Based on the corresponding embodiments, the at least one contextual feature corresponds to a corresponding weight, the topic library includes at least one candidate topic, and the fourth obtaining module is used for: Based on the at least one contextual feature, query the topic database to obtain candidate topics that intersect with the at least one contextual feature; Based on the weights corresponding to the at least one context feature, determine the weighted matching scores of the context feature set and the at least one candidate topic respectively; The candidate topic with the highest weighted matching score is determined as the context topic that matches the context feature set.

[0124] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3 Based on the corresponding embodiment, the fourth obtaining module is further configured to: Filter out candidate topics that meet the filtering conditions, which include at least one of the following: the matching score between the candidate topic and the content feature is less than a first threshold, or the candidate topic belongs to a topic that has been played in the first time period.

[0125] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3 Based on the corresponding embodiments, the fifth obtaining module is used for: Based on the aforementioned context theme, a tag library is queried to obtain a candidate tag set, which includes one or more candidate tags. Based on the set of contextual features, the candidate label set is adjusted to obtain one or more contextual labels.

[0126] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3 Based on the corresponding embodiments, the fifth obtaining module is used for at least one of the following: If the cosine similarity between the candidate label and the environmental feature is lower than the second threshold, the candidate label is filtered out. If the number of images containing the candidate tag in the album library is less than the third threshold, then the weight of the candidate tag is reduced. If the number of images with the candidate tag in the album library is greater than the fourth threshold, then the weight of the candidate tag is increased. If the number of images in the album library in the candidate tag set is less than the fifth threshold, then the tag corresponding to the behavioral feature is added to the candidate tag set.

[0127] Another embodiment of the present invention discloses an image playback device. This embodiment is based on the above... Figure 3 Based on the corresponding embodiment, the third playback module 33 is used for: Based on the current context, the multiple context images are played and arranged to obtain playback information that conforms to the current context; Play the multiple contextual images according to the playback information.

[0128] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0130] This application also provides an electronic device. For example... Figure 4 As shown, the electronic device 4 includes: at least one processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, wherein the processor 40 executes the computer program 42 to implement the steps in any of the above-described method embodiments.

[0131] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0132] This application provides a computer program product, which includes a computer program that, when run, causes the steps described in the various method embodiments above to be performed.

[0133] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographic device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0134] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0135] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0136] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of playing an image, characterized by, include: Collect at least one context feature that fits the current context, and generate a context feature set; Based on the set of context features, obtain multiple context images that match the set of context features; Play the multiple context images according to the current context.

2. The method of claim 1, wherein, The at least one contextual feature includes at least one of the following: time feature, behavioral feature, content feature, and environmental feature; the collection of at least one contextual feature that conforms to the current context includes at least one of the following: Determine the time characteristics based on whether the current time matches the scheduled time; Determine behavioral characteristics based on the current user's preferred behaviors; Based on the newly added images, determine the content features; Determine environmental characteristics based on current weather data.

3. The method of claim 1 or 2, wherein, The step of obtaining multiple context images that match the context feature set includes: Based on the set of context features, query the topic database to obtain context topics that match the set of context features; Based on the given context theme, obtain one or more context labels; Based on the context tags, the photo album is queried to obtain multiple context images.

4. The method as described in claim 3, characterized in that, The at least one contextual feature corresponds to a specific weight, the topic library includes at least one candidate topic, and the step of querying the topic library based on the contextual feature set to obtain a contextual topic that matches the contextual feature set includes: Based on the at least one contextual feature, query the topic database to obtain candidate topics that intersect with the at least one contextual feature; Based on the weights corresponding to the at least one context feature, determine the weighted matching scores of the context feature set and the at least one candidate topic respectively; The candidate topic with the highest weighted matching score is determined as the context topic that matches the context feature set.

5. The method of claim 4, wherein, The step of querying the topic database based on the context feature set to obtain context topics that match the context feature set further includes: Filter out candidate topics that meet the filtering conditions, which include at least one of the following: the matching score between the candidate topic and the content feature is less than a first threshold, or the candidate topic belongs to a topic that has been played in the first time period.

6. The method of claim 3, wherein, The step of obtaining one or more context labels based on the context theme includes: Based on the aforementioned context theme, a tag library is queried to obtain a candidate tag set, which includes one or more candidate tags. Based on the set of contextual features, the candidate label set is adjusted to obtain one or more contextual labels.

7. The method of claim 6, wherein, The step of adjusting the candidate label set based on the context feature set to obtain one or more context labels includes at least one of the following: If the cosine similarity between the candidate label and the environmental feature is lower than the second threshold, the candidate label is filtered out. If the number of images containing the candidate tag in the album library is less than the third threshold, then the weight of the candidate tag is reduced. If the number of images with the candidate tag in the album library is greater than the fourth threshold, then the weight of the candidate tag is increased. If the number of images in the album library in the candidate tag set is less than the fifth threshold, then the tag corresponding to the behavioral feature is added to the candidate tag set.

8. The method of claim 1, wherein, Playing the multiple context images according to the current context includes: Based on the current context, the multiple context images are played and arranged to obtain playback information that conforms to the current context; Play the multiple contextual images according to the playback information.

9. An apparatus for playing an image, characterized by include: The first acquisition module is used to acquire at least one context feature that matches the current context and generate a context feature set; The second obtaining module is used to obtain multiple situation images that match the situation feature set based on the situation feature set; The third playback module is used to play the multiple context images according to the current context.

10. An electronic device, comprising: The device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device performs the method as described in any one of claims 1-8.

Images