Item recommendation method, device, equipment and readable storage medium

Abstract

The present invention provides an item recommendation method, device, equipment and readable storage medium, which relates to the field of information technology of the Internet of Things. The item recommendation method includes dividing the historical playback records of a user into several categories, determining the heat value of the items in each category, and determining the first score of each item in the historical negative feedback record of the user; generating a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records; generating attenuation information for attenuating the second score based on the heat value; attenuating the second score based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set; reordering the first recommended item set according to the third score and the first score to obtain a second recommended item set; and determining the target recommended item based on the second recommended item set. The problem of poor recommendation effect of the existing recommendation method can be solved.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things information technology, and in particular to an item recommendation method, device, equipment and readable storage medium. Background Art

[0002] With the advancement of science and technology, personalized video recommendation technology is becoming more and more popular among the public. In the current recommendation method, when generating recommendation results, it tends to recommend items with higher popularity. Since most of the items with higher popularity are similar, this recommendation method makes the recommendation results more concentrated, and even duplicate recommendations may occur, which affects the user experience and fails to recommend results suitable for users. It can be seen that the recommendation effect of the existing recommendation method is poor. Summary of the invention

[0003] Embodiments of the present invention provide an item recommendation method, device, equipment and readable storage medium to solve the problem that the recommendation effect of the existing recommendation method is poor.

[0004] To solve the above technical problems, the present invention is achieved as follows:

[0005] In a first aspect, an embodiment of the present invention provides an item recommendation method, comprising:

[0006] Divide the user's historical playback records into several categories, determine the popularity value of the items in each category, and determine the first score of each item in the user's historical negative feedback records;

[0007] generating a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records;

[0008] generating attenuation information for attenuating the second score based on the heat value;

[0009] Attenuating the second score based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set;

[0010] reordering the first recommended item set according to the third score and the first score to obtain a second recommended item set;

[0011] A target recommended item is determined based on the second recommended item set.

[0012] In a second aspect, an embodiment of the present invention provides an item recommendation device, comprising:

[0013] A first processing unit, configured to classify the user's historical playback records into a plurality of categories, determine the popularity value of items in each category, and determine a first score of each item in the user's historical negative feedback records;

[0014] A first generating unit, configured to generate a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback record;

[0015] A second generating unit, configured to generate attenuation information for attenuating the second score based on the heat value;

[0016] a second processing unit, configured to attenuate the second score based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set;

[0017] a sorting unit, configured to re-sort the first recommended item set according to the third score and the first score to obtain a second recommended item set;

[0018] A determination unit is used to determine a target recommended item based on the second recommended item set.

[0019] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the item recommendation method described in the first aspect.

[0020] In a fourth aspect, an embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the item recommendation method described in the first aspect are implemented.

[0021] In an embodiment of the present invention, the user's historical playback records are divided into several categories, and the popularity value of the items in each category is determined, and the first score of each item in the user's historical negative feedback record is determined; a first recommended item set and a second score corresponding to each item in the first recommended item set are generated based on the historical playback records; attenuation information for attenuating the second score is generated based on the popularity value; the second score is attenuated based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set; the first recommended item set is reordered according to the third score and the first score to obtain a second recommended item set; and the target recommended item is determined based on the second recommended item set. In this way, by generating attenuation information and further attenuating each item based on the attenuation information, items with user bias in the recommended items can be removed, suitable items can be recommended to each user, and the recommendation effect can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0023] Figure 1 is a flow chart of an item recommendation method provided by an embodiment of the present invention;

[0024] Figure 2 is a module diagram of an item recommendation device provided by an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of a module structure of an electronic device provided by an embodiment of the present invention;

[0026] Figure 4 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] See also Figure 1 , Figure 1 is a flow chart of an item recommendation method provided by an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0029] Step 101: Classify the user's historical playback records into several categories, determine the popularity value of the items in each category, and determine the first score of each item in the user's historical negative feedback records.

[0030] In this implementation, the item may refer to a video or a commodity. Taking video as an example, the recommended result may be different types of animation videos or TV series.

[0031] In addition, the user's historical playback records may be corresponding records of items that have been recommended to the user and played by the user, thereby generating interactive behaviors with the user; the user's historical negative feedback records may be corresponding records of items that have been recommended to the user but not selected by the user, thereby not played by the user, and no interactive behaviors with the user.

[0032] Specifically, dividing the user's historical playback records into several categories can refer to classifying them according to the category of the items, such as animation, movies, or home theater. Different users have different preferences for different categories. The popularity value of the items in each category refers to the popularity of the items in this category for all users. For example, if the popularity of science fiction movies is high, the popularity value of the items in this category is high. The first score of each item in the user's historical negative feedback record reflects the degree to which the item is not popular with the user, that is, the probability of not being played by the user.

[0033] Step 102: Generate a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records.

[0034] In this implementation, the second score corresponding to each item in the first recommended item set reflects the degree to which the item is popular with users, that is, the probability of being played by users.

[0035] Step 103: Generate attenuation information for attenuating the second score based on the heat value.

[0036] Here, attenuation refers to removing the bias existing in the items corresponding to the second score. The bias is that the item is popular due to the category or characteristics of the item itself, and the system has the possibility of recommending the item first based on its popularity.

[0037] Step 104: decay the second score based on the decay information to obtain a third score corresponding to each item in the first recommended item set.

[0038] The third score is the degree to which the items in the first recommended item set are popular with users after attenuation and debiasing.

[0039] Step 105: reorder the first recommended item set according to the third score and the first score to obtain a second recommended item set.

[0040] The second recommended item set may be obtained by re-sorting the items in descending order of scores, or may be obtained by re-sorting the items in ascending order of scores.

[0041] Step 106: Determine a target recommended item based on the second recommended item set.

[0042] The above-mentioned item recommendation method, by generating attenuation information and further performing attenuation processing on each item based on the attenuation information, can remove items with user bias from the recommended items, recommend appropriate items to each user, and improve the recommendation effect.

[0043] Optionally, the user's historical playback records are divided into several categories, and the popularity value of the items in each category is determined, and the first score of each item in the historical negative feedback record is determined, including:

[0044] Obtain the user's historical playback records, negative feedback records, and feature data corresponding to items in the historical playback records;

[0045] Classifying the items in the user's historical playback records into several categories according to the feature data corresponding to the items in the historical playback records;

[0046] Generate a popularity value for each item in the corresponding category. The popularity value is used to indicate the number of users who interact with the item.

[0047] A negative feedback item set is generated according to historical negative feedback records, and a first score of each negative feedback item in the negative feedback item set is determined, where the first score is used to indicate the number of times the negative feedback item is not selected by the user during the recommendation process.

[0048] In this embodiment, the feature data may be information associated with the item, which may be the original category of the item, or text used to describe the subject type of the object, or text representing the plot of the item. This is only an example and is not limiting.

[0049] Specifically, when the objects are classified into several categories, they can be classified according to the original categories in the feature data corresponding to the objects, or they can be classified by clustering the objects. This is only an example and not a limitation.

[0050] Further, the popularity value of each item is calculated based on the user's historical playback records. In this embodiment, the popularity value is expressed as H j The category of the item is represented by C j express.

[0051] Optionally, generating a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records includes:

[0052] Determine the user's items of interest based on feature data corresponding to the items in the historical playback records;

[0053] Generate a first set of recommended items according to candidate items corresponding to similarities exceeding a similarity threshold, where the similarity is used to indicate the similarity between the candidate items and the items of interest;

[0054] A second score is generated for each item in the first recommended item set based on the magnitude of the similarity.

[0055] In this implementation, the items of interest may be items that have been played more times by the user in the historical playback records. Generating the first recommended item set based on the items of interest to the user can make the generated first recommended item set close to the user's interests. Further, the second score of each item in the first recommended item set is determined according to the magnitude of the similarity. For example, if the similarity between item A and the items of interest is 70%, and the similarity between item B and the items of interest is 30%, then the second score of item A is greater than the second score of item B.

[0056] In addition, the first recommended item set may be generated by using an item-based collaborative filtering method, which is only used as an example and is not limited here.

[0057] Specifically, in this embodiment, for user u, the recommendation result is S u , the score of each recommendation result is R i .

[0058] Optionally, generating attenuation information for attenuating the second score based on the heat value includes:

[0059] Determine the heat decay weight corresponding to each category;

[0060] Based on the heat value and the heat decay weight, a decay function for decaying the second score is generated.

[0061] In this embodiment, the heat decay weight is determined as The attenuation function is established to satisfy the following formula.

[0062]

[0063] In the formula, F i Represents the third score after attenuation by the attenuation function, R i Represents the second score, represents the decay function.

[0064] In this embodiment, the heat decay weight is determined, and different heat decay weights can be set according to different item categories, thereby improving the adaptability and flexibility of the item recommendation method for different scenarios. Optionally, the first recommended item set is reordered according to the third score and the first score to obtain the second recommended item set, including:

[0065] Normalizing the first score to obtain a normalized value;

[0066] A fourth score of each item in the first recommended item set is calculated according to the third score and the normalized value, and the first recommended item set is reordered according to the fourth score to obtain a second recommended item set.

[0067] In this implementation, the first score may be recorded as Ni Since the items in the negative feedback record were recommended to the user, but the user did not select and click on them, the first score can be normalized to 0-1. Specifically, the maximum and minimum normalization method can be used. Here, it is only an example and not limited. In other feasible implementations, other methods can be used for normalization. However, no matter how it is changed, it is within the scope of protection of the embodiments of this application.

[0068] Specifically, the fourth score can be calculated in the following manner:

[0069]

[0070] In the formula, Q i represents the fourth score, Represents the normalized value index.

[0071] Further, in this embodiment, the first recommended item set is reordered in descending order according to the fourth score to obtain a second recommended item set. Optionally, determining the target recommended item based on the second recommended item set includes:

[0072] Items in the second recommended item set whose scores exceed a preset score threshold are selected as target recommended items.

[0073] In this way, by generating attenuation information and further performing attenuation processing on each item based on the attenuation information, items with user bias can be removed from the recommended items, suitable items can be recommended to each user, and the recommendation effect can be improved.

[0074] See also Figure 2 . Figure 2 The present embodiment provides an item recommendation device 200, comprising:

[0075] The first processing unit 201 is used to classify the user's historical playback records into several categories, and determine the popularity value of the items in each category, and determine the first score of each item in the user's historical negative feedback records;

[0076] A first generating unit 202, configured to generate a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback record;

[0077] A second generating unit 203, configured to generate attenuation information for attenuating the second score based on the heat value;

[0078] A second processing unit 204 is configured to decay the second score based on the decay information to obtain a third score corresponding to each item in the first recommended item set;

[0079] A sorting unit 205, configured to re-sort the first recommended item set according to the third score and the first score to obtain a second recommended item set;

[0080] The determining unit 206 is configured to determine a target recommended item based on the second recommended item set.

[0081] The first processing unit 201 is specifically used for:

[0082] Obtaining the user's historical playback records, negative feedback records, and feature data corresponding to items in the historical playback records;

[0083] Classifying the items in the user's historical playback records into a plurality of categories according to the feature data corresponding to the items in the historical playback records;

[0084] Generate a popularity value for each item in a corresponding category, where the popularity value is used to indicate the number of users who have interacted with the item;

[0085] A negative feedback item set is generated according to the historical negative feedback records, and a first score of each negative feedback item in the negative feedback item set is determined, where the first score is used to indicate the number of times the negative feedback item is not selected by the user during the recommendation process.

[0086] Optionally, the first generating unit 202 is specifically configured to:

[0087] Determining the user's items of interest based on feature data corresponding to the items in the historical playback records;

[0088] Generate a first recommended item set according to candidate items corresponding to similarities exceeding a similarity threshold, wherein the similarity is used to indicate the similarity between the candidate items and the items of interest;

[0089] A second score for each item in the first recommended item set is generated based on the magnitude of the similarity.

[0090] Optionally, the second generating unit 203 is specifically configured to:

[0091] Determine the heat decay weight corresponding to each category;

[0092] Based on the heat value and the heat decay weight, a decay function for decaying the second score is generated.

[0093] Optionally, the sorting unit 205 is specifically configured to:

[0094] Normalizing the first score to obtain a normalized value;

[0095] A fourth score of each item in the first recommended item set is calculated according to the third score and the normalized value, and the first recommended item set is reordered according to the fourth score to obtain a second recommended item set.

[0096] Optionally, the determining unit 206 is specifically configured to:

[0097] Items in the second recommended item set whose scores exceed a preset score threshold are selected as target recommended items.

[0098] The item recommendation device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0099] The item recommendation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0100] The item recommendation device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0101] Optional, such as Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0102] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0103] Figure 4A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0104] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .

[0105] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system.

[0106] Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0107] The processor 410 is used for:

[0108] Divide the user's historical playback records into several categories, determine the popularity value of the items in each category, and determine the first score of each item in the user's historical negative feedback records;

[0109] generating a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records;

[0110] generating attenuation information for attenuating the second score based on the heat value;

[0111] Attenuating the second score based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set;

[0112] reordering the first recommended item set according to the third score and the first score to obtain a second recommended item set;

[0113] A target recommended item is determined based on the second recommended item set.

[0114] Optionally, the processor 410 is further configured to:

[0115] Obtaining the user's historical playback records, negative feedback records, and feature data corresponding to items in the historical playback records;

[0116] Classifying the items in the user's historical playback records into a plurality of categories according to the feature data corresponding to the items in the historical playback records;

[0117] Generate a popularity value for each item in a corresponding category, where the popularity value is used to indicate the number of users who have interacted with the item;

[0118] A negative feedback item set is generated according to the historical negative feedback records, and a first score of each negative feedback item in the negative feedback item set is determined, where the first score is used to indicate the number of times the negative feedback item is not selected by the user during the recommendation process.

[0119] Optionally, the processor 410 is further configured to:

[0120] Determining the user's items of interest based on feature data corresponding to the items in the historical playback records;

[0121] Generate a first recommended item set according to candidate items corresponding to similarities exceeding a similarity threshold, wherein the similarity is used to indicate the similarity between the candidate items and the items of interest;

[0122] A second score for each item in the first recommended item set is generated based on the magnitude of the similarity.

[0123] Optionally, the processor 410 is further configured to:

[0124] Determine the heat decay weight corresponding to each category;

[0125] Based on the heat value and the heat decay weight, a decay function for decaying the second score is generated.

[0126] Optionally, the processor 410 is further configured to:

[0127] Normalizing the first score to obtain a normalized value;

[0128] A fourth score of each item in the first recommended item set is calculated according to the third score and the normalized value, and the first recommended item set is reordered according to the fourth score to obtain a second recommended item set.

[0129] Optionally, the processor 410 is further configured to:

[0130] Items in the second recommended item set whose scores exceed a preset score threshold are selected as target recommended items.

[0131] In the embodiment of the present application, the electronic device 400 generates attenuation information and further performs attenuation processing on each item based on the attenuation information, thereby removing items with user bias from the recommended items, recommending suitable items to each user, and improving the recommendation effect.

[0132] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 409 may be used to store software programs and various data, including but not limited to applications and operating systems. The processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 410.

[0133] The embodiment of the present application also provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, the above Figure 1 The various processes of the method embodiment can achieve the same technical effect, and to avoid repetition, they will not be described here.

[0134] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0135] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. An item recommendation method, characterized in that: include: Divide the user's historical playback records into several categories, determine the popularity value of the items in each category, and determine the first score of each item in the user's historical negative feedback records; generating a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records; generating attenuation information for attenuating the second score based on the heat value; Attenuating the second score based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set; reordering the first recommended item set according to the third score and the first score to obtain a second recommended item set; Determining a target recommended item based on the second recommended item set; The step of generating a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback records includes: Determining the user's items of interest based on feature data corresponding to the items in the historical playback records; Generate a first recommended item set according to candidate items corresponding to similarities exceeding a similarity threshold, wherein the similarity is used to indicate the similarity between the candidate items and the items of interest; generating a second score for each item in the first recommended item set based on the magnitude of the similarity; The step of generating attenuation information for attenuating the second score based on the heat value includes: Determine the heat decay weight corresponding to each category; Based on the heat value and the heat decay weight, a decay function for decaying the second score is generated.

2. The item recommendation method according to claim 1, characterized in that: The method of dividing the user's historical playback records into several categories, determining the popularity value of the items in each category, and determining the first score of each item in the historical negative feedback records includes: Obtaining the user's historical playback records, negative feedback records, and feature data corresponding to items in the historical playback records; Classifying the items in the user's historical playback records into a plurality of categories according to the feature data corresponding to the items in the historical playback records; Generate a popularity value for each item in a corresponding category, where the popularity value is used to indicate the number of users who have interacted with the item; A negative feedback item set is generated according to the historical negative feedback records, and a first score of each negative feedback item in the negative feedback item set is determined, where the first score is used to indicate the number of times the negative feedback item is not selected by the user during the recommendation process.

3. The item recommendation method according to claim 1, characterized in that: The step of reordering the first recommended item set according to the third score and the first score to obtain a second recommended item set includes: Normalizing the first score to obtain a normalized value; A fourth score of each item in the first recommended item set is calculated according to the third score and the normalized value, and the first recommended item set is reordered according to the fourth score to obtain a second recommended item set.

4. The item recommendation method according to claim 1, characterized in that: The determining a target recommended item based on the second recommended item set includes: Items in the second recommended item set whose scores exceed a preset score threshold are selected as target recommended items.

5. An item recommendation device, characterized in that: include: A first processing unit, configured to classify the user's historical playback records into a plurality of categories, determine the popularity value of items in each category, and determine a first score of each item in the user's historical negative feedback records; A first generating unit, configured to generate a first recommended item set and a second score corresponding to each item in the first recommended item set based on the historical playback record; A second generating unit, configured to generate attenuation information for attenuating the second score based on the heat value; a second processing unit, configured to attenuate the second score based on the attenuation information to obtain a third score corresponding to each item in the first recommended item set; a sorting unit, configured to re-sort the first recommended item set according to the third score and the first score to obtain a second recommended item set; a determining unit, configured to determine a target recommended item based on the second recommended item set; The first generating unit is specifically used for: Determining the user's items of interest based on feature data corresponding to the items in the historical playback records; Generate a first recommended item set according to candidate items corresponding to similarities exceeding a similarity threshold, wherein the similarity is used to indicate the similarity between the candidate items and the items of interest; generating a second score for each item in the first recommended item set based on the magnitude of the similarity; The second generation unit is specifically used for: Determine the heat decay weight corresponding to each category; Based on the heat value and the heat decay weight, a decay function for decaying the second score is generated.

6. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the item recommendation method as described in any one of claims 1 to 4.

7. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the item recommendation method as described in any one of claims 1 to 4 are implemented.

Images