Information recommendation method and related device

Abstract

The embodiment of the present application discloses an information recommendation method and related devices, the method comprising: determining public opinion information corresponding to a pet breed, the public opinion information is used to indicate the speech related to the pet breed published by the target group; analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed, the market public opinion is used to indicate the direction and / or heat of public opinion; determining the target pet breed that the user is interested in based on the user's historical behavior records and the market public opinion, the historical behavior records are used to indicate the behavior corresponding to the pet breed performed by the user on the client device; determining the target pet content that the user is interested in based on the target pet breed; and recommending the target pet content to the user's client device. The use of the embodiment of the present application helps to improve the accuracy of information recommendation and helps to improve user satisfaction.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an information recommendation method and related devices. Background Art

[0002] Currently, pet video recommendations are based on the user's historical browsing behavior. For example, based on the pet breed that the user has recently followed, videos related to the pet breed are pushed to the user. However, this push only takes into account the user's historical browsing behavior, and the accuracy of pet video recommendations is low, making it difficult to achieve personalized recommendations. Summary of the invention

[0003] The embodiments of the present application provide an information recommendation method and related devices, which are helpful to improve the accuracy of information recommendation and help to improve user satisfaction.

[0004] In a first aspect, an embodiment of the present application provides an information recommendation method, which is applied to a server, and the method includes:

[0005] Determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate comments related to the pet breed published by a target group, wherein the target group refers to a group that publishes comments on the pet breed;

[0006] Analyze the public opinion information to obtain market public opinion corresponding to the pet breed, where the market public opinion is used to indicate the direction and / or heat of public opinion;

[0007] Determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device;

[0008] Determining target pet content that the user is interested in based on the target pet breed, where the target pet content is used to indicate content corresponding to the target pet breed;

[0009] The target pet content is recommended to the client device of the user.

[0010] In a second aspect, an embodiment of the present application provides an information recommendation device, which is applied to a server. The device includes: a determination unit, an analysis unit, and a recommendation unit, wherein:

[0011] The determining unit is used to determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate the opinions related to the pet breed published by a target group, and the target group refers to the group that publishes opinions on the pet breed;

[0012] The analysis unit is used to analyze the public opinion information to obtain the market public opinion corresponding to the pet breed, and the market public opinion is used to indicate the direction and / or heat of public opinion;

[0013] The determination unit is further used to determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device;

[0014] The determination unit is further used to determine the target pet content that the user is interested in according to the target pet breed, and the target pet content is used to indicate the content corresponding to the target pet breed;

[0015] The recommendation unit is configured to recommend the target pet content to the client device of the user.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute instructions of some or all of the steps described in the first aspect of the embodiment of the present application.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0019] The implementation of the embodiments of the present application has the following beneficial effects:

[0020] It can be seen that the information recommendation method and related devices described in the embodiments of the present application can determine the public opinion information corresponding to the pet breed, analyze the public opinion information, obtain the market public opinion corresponding to the pet breed, determine the target pet breed that the user is interested in based on the user's historical behavior records and market public opinion, determine the target pet content that the user is interested in based on the target pet breed, and recommend the target pet content to the user's client device; in this way, combining the user's historical behavior records and market public opinion to recommend pet information to the user helps to accurately predict the target pet content that the user is interested in, thereby improving the accuracy of information recommendation and helping to improve user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1A It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0023] Figure 1B It is a flowchart of an information recommendation method provided in an embodiment of the present application;

[0024] Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0025] Figure 3 This is a block diagram of the functional units of an information recommendation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] The electronic device involved in the embodiments of the present application may be a portable electronic device including other functions such as a personal digital assistant and / or a music player function, such as a mobile phone, a tablet computer, a wearable electronic device with a wireless communication function (such as a smart watch), etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with an IOS system, an Android system, a Microsoft system, or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer (Laptop), etc. It should also be understood that in some other embodiments, the above-mentioned electronic device may not be a portable electronic device, but a desktop computer. The electronic device may also include a server.

[0030] See also Figure 1A , Figure 1A It is a structural diagram of an electronic device provided in an embodiment of the present application. The electronic device includes a processor and a memory, etc. Among them, the memory is connected to the processor. The processor is the control center of the electronic device, which uses various interfaces and lines to connect the various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory, and calling data stored in the memory, thereby monitoring the electronic device as a whole. The processor can be a central processing unit (CPU), a graphics processing unit (GPU) or a network processor (Neural-network Processing Unit, NPU).

[0031] Furthermore, the processor may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor.

[0032] The memory is used to store software programs and / or modules, and the processor executes various functional applications of the electronic device by running the software programs and / or modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a software program required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0033] Based on the above Figure 1A The electronic device described can execute the following information recommendation method, and the specific steps are as follows:

[0034] Determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate comments related to the pet breed published by a target group, wherein the target group refers to a group that publishes comments on the pet breed;

[0035] Analyze the public opinion information to obtain market public opinion corresponding to the pet breed, where the market public opinion is used to indicate the direction and / or heat of public opinion;

[0036] Determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device;

[0037] Determining target pet content that the user is interested in based on the target pet breed, where the target pet content is used to indicate content corresponding to the target pet breed;

[0038] The target pet content is recommended to the client device of the user.

[0039] It can be seen that the electronic device described in the embodiment of the present application can determine the public opinion information corresponding to the pet breed, analyze the public opinion information, obtain the market public opinion corresponding to the pet breed, determine the target pet breed that the user is interested in based on the user's historical behavior records and market public opinion, determine the target pet content that the user is interested in based on the target pet breed, and recommend the target pet content to the user's client device; in this way, combining the user's historical behavior records and market public opinion to recommend pet information to the user helps to accurately predict the target pet content that the user is interested in, thereby improving the accuracy of information recommendation and helping to improve user satisfaction.

[0040] See also Figure 1B , Figure 1B This is a flow chart of an information recommendation method provided by an embodiment of the present application. As shown in the figure, it is applied to Figure 1A The electronic device shown, the method recommended by this information includes:

[0041] 101. Determine the public opinion information corresponding to the pet breed.

[0042] The public opinion information may be used to indicate the comments related to pet breeds made by the target group, and the target group may refer to the group that makes comments on pet breeds. The pet breed may be one pet breed or multiple pet breeds, which is not limited here.

[0043] 102. Analyze the public opinion information to obtain market public opinion corresponding to the pet breed.

[0044] Among them, the above-mentioned market public opinion can be used to indicate the direction of public opinion and / or the heat of public opinion. For a specific pet breed, the direction of public opinion can include positive, negative and neutral. Among them, the positive direction of public opinion can refer to the target group's love and praise for the pet breed, the negative direction of public opinion can refer to the target group's disgust and derogation of the pet breed, and the neutral direction of public opinion can refer to the target group's neither love nor disgust for the pet breed, or indifference, or on the one hand likes certain characteristics of the pet breed, and on the other hand hates other characteristics of the pet breed. The heat of public opinion can be used to characterize the degree of concern of the target group for a certain pet breed. It can be understood that the higher the heat of public opinion, the more the target group cares about the pet breed.

[0045] 103. Determine the target pet breed that the user is interested in based on the user's historical behavior records and the market sentiment.

[0046] The above historical behavior records may be used to indicate the behaviors corresponding to the pet breeds performed by the user on the client device, for example, the user's search behaviors, browsing behaviors, comment behaviors, like behaviors, collection behaviors, forwarding behaviors, coin reward behaviors, etc. on the client device for a certain pet breed, which are not limited here.

[0047] 104. Determine target pet content that the user is interested in based on the target pet breed.

[0048] The target pet content may be used to indicate the content corresponding to the target pet breed. It is understandable that if the user is interested in the target pet breed, the user is also interested in the target pet content corresponding to the target pet breed.

[0049] 105. Recommend the target pet content to the client device of the user.

[0050] Among them, the client device of the above-mentioned user can refer to devices such as smart phones, smart TVs, smart wearable devices, smart computers, etc., or it can be an electronic device such as a car that can communicate with the server, which is not limited here.

[0051] In a specific implementation, the electronic device can determine public opinion information corresponding to one or more pet breeds. When analyzing the public opinion information corresponding to multiple pet breeds, the obtained market public opinions corresponding to the multiple pet breeds are analyzed, and the obtained market public opinions also correspond to the pet breeds. For a certain pet breed, based on the market public opinion corresponding to the pet breed and the behavior related to the pet breed performed by the user on the client device, it is determined whether the user is interested in the pet breed, and if so, the pet breed is determined as the target pet breed.

[0052] For example, for the pet species Cat A, the public opinion information corresponding to Cat A is determined, and the market public opinion obtained by analyzing the public opinion information is positive market public opinion, that is, the target group has a favorable attitude towards Cat A. Based on the user's behavior related to Cat A on the client device, such as the user frequently searching for news about Cat A on the web, browsing products related to Cat A, and the positive market public opinion corresponding to Cat A, it can be determined that the user is interested in Cat A, and Cat A is the target pet species.

[0053] According to the target pet breed, the target pet content can be determined and recommended to the user's client device. The user can browse, comment, like, collect, forward, reward, etc. the target pet content on the client device.

[0054] It can be seen that in the implementation manner of the present application, the electronic device can determine the public opinion information corresponding to the pet breed, analyze the public opinion information, obtain the market public opinion corresponding to the pet breed, determine the target pet breed that the user is interested in based on the user's historical behavior records and market public opinion, determine the target pet content that the user is interested in based on the target pet breed, and recommend the target pet content to the user's client device; in this way, combining the user's historical behavior records and market public opinion to recommend pet information to the user helps to accurately predict the target pet content that the user is interested in, thereby improving the accuracy of information recommendation and helping to improve user satisfaction.

[0055] In a possible example, analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed may include the following steps:

[0056] According to the information platform corresponding to the public opinion information, the public opinion information is divided into at least one platform public opinion information set;

[0057] According to the preset analysis rules, the public opinion information corresponding to each pet breed in the public opinion information set of each platform is analyzed respectively to obtain the target analysis value of each pet breed corresponding to each information platform;

[0058] The market sentiment corresponding to each of the pet breeds is determined according to at least one of the target analysis values.

[0059] Among them, the above-mentioned information platform can be used to indicate the social platform where the target group publishes public opinion information.

[0060] The above platform public opinion information set may be one or more, which is not limited here. The number of platform public opinion information sets may correspond to the number of information platforms, which is not limited here. Each platform public opinion information set may be used to indicate the public opinion information published on each information platform, and each platform public opinion information set includes at least one public opinion information corresponding to a pet breed.

[0061] The above-mentioned preset analysis rules may be pre-stored in the electronic device, or may be set by the user, which is not limited here.

[0062] For example, if the information platforms corresponding to the public opinion information are A, B, C, and D, the public opinion information is divided into the public opinion information set of platform A, the public opinion information set of platform B, the public opinion information set of platform C, and the public opinion information set of platform D. Among them, the pet breeds in the public opinion information set of platform A include cat A, cat B, and dog B, the pet breeds in the public opinion information set of platform B include rabbit C and cat B, the pet breeds in the public opinion information set of platform C include cat B, and the pet breeds in the public opinion information set of platform D include cat A.

[0063] According to the preset analysis rules, the public opinion information corresponding to Cat B in the public opinion information set of platform A is analyzed to obtain the target analysis value a corresponding to Cat B on platform A. The public opinion information corresponding to Cat B in the public opinion information set of platform B is analyzed to obtain the target analysis value b corresponding to Cat B on platform B. The public opinion information corresponding to Cat B in the public opinion information set of platform C is analyzed to obtain the target analysis value c corresponding to Cat B on platform C. According to the target analysis values ​​a, b, and c corresponding to Cat B on multiple information platforms, the market public opinion corresponding to Cat B is determined.

[0064] The market sentiment analysis method for other pet breeds is similar to the above method and will not be repeated here. It should be noted that, as described in the above example, the public opinion information corresponding to the pet breed C rabbit only appears in the public opinion information set of platform B, which means that only platform B has public opinion information related to C rabbit, so it is only necessary to determine the market sentiment corresponding to C rabbit based on the target analysis value corresponding to C rabbit on platform B.

[0065] It can be seen that in the implementation manner of the present application, the electronic device can divide the public opinion information into at least one platform public opinion information set according to the information platform corresponding to the public opinion information, and analyze the public opinion information corresponding to each pet breed in each platform public opinion information set according to the preset analysis rules, and obtain the target analysis value of each pet breed corresponding to each information platform, and determine the market public opinion corresponding to each pet breed according to the target analysis value. In this way, the public opinion information corresponding to the pet breeds is classified and analyzed according to the different information platforms, which helps to accurately determine the market public opinion corresponding to each pet breed.

[0066] In a possible example, analyzing the public opinion information corresponding to each pet breed in each platform public opinion information set according to a preset analysis rule to obtain a target analysis value for each pet breed corresponding to each information platform may include the following steps:

[0067] Determine the information direction corresponding to each public opinion information of the current pet breed in the current platform public opinion information set;

[0068] Determine the amount of support corresponding to each piece of public opinion information;

[0069] Calculating a first total support amount of the positive public opinion information and a second total support amount of the negative public opinion information;

[0070] A target analysis value of the current pet breed corresponding to the current information platform is determined according to the first total support amount, the second total support amount and a preset relationship.

[0071] The above information orientation can be used to indicate the target group's emotional inclination towards the current pet breed, and the information orientation includes positive orientation and negative orientation. For example, positive public opinion information can be: the pet breed has a mild temper and has not caused any injuries, while negative public opinion information can be: the pet breed has a violent temper and has caused one or more injuries.

[0072] The preset relationship is: P = a*(1.2*mn). P is the target analysis value of the current pet breed corresponding to the current information platform, a is the impact factor corresponding to the current information platform, m is the first total support amount of the positive public opinion information, and n is the second total support amount of the negative public opinion information.

[0073] It should be noted that, considering the phenomenon that pet lovers or pet haters are too concentrated on certain platforms, or that a certain pet breed is particularly loved or hated on a certain social platform, in order to ensure the accuracy of the analysis of the market sentiment corresponding to the pet breed, a corresponding impact factor can be set for each information platform. For example, if a social platform is famous for loving pets or hating pets, the corresponding impact factor a can be set smaller.

[0074] In addition, it is known from the common sense of communication and psychology that the spread range of negative public opinion information is usually wider than that of positive public opinion information, and its spread speed is usually faster than that of positive public opinion information. Therefore, the first total support amount m of positive public opinion information is processed, and the first total support amount of positive public opinion information is appropriately increased, that is, 1.2*m is used to represent the actual first total support amount of positive public opinion information. In this way, the target analysis value is closer to the real public opinion, which helps to further ensure the accuracy of public opinion analysis, thereby helping to ensure the accuracy of information recommendation.

[0075] In a specific implementation, the amount of support corresponding to the public opinion information can be determined based on the following behaviors: the number of likes corresponding to the public opinion information, the amount of rewards received, and other behaviors that indicate support for the speech, and the public opinion information itself can also be counted as 1 amount of support.

[0076] For example, the public opinion information of cat breed A in the current platform public opinion information set is obtained as "Cats of breed A have a mild temper and have not hurt anyone" and "Cats of breed A have a violent temper and have hurt many people in the past". The number of likes corresponding to the public opinion information "Cats of breed A have a mild temper and have not hurt anyone" is 256. The number of likes corresponding to the public opinion information "Cats of breed A have a violent temper and have hurt many people in the past" is 25.

[0077] Analyze the information direction corresponding to each piece of public opinion information separately, and determine that the information direction corresponding to the public opinion information "Cats of breed A have a mild temper and have not caused any injuries" is positive, and the information direction corresponding to the public opinion information "Cats of breed A have a violent temper and have caused many injuries" is negative. And determine the support amount corresponding to each piece of public opinion information: The public opinion information "Cats of breed A have a mild temper and have not caused any injuries" has 256 likes, so m=256+1=257. The public opinion information "Cats of breed A have a violent temper and have caused many injuries" has 25 likes, so n=25+1=26.

[0078] If the impact factor corresponding to the current information platform is 0.9, then according to the calculation formula of the target analysis value P=a*(1.2*mn), the target analysis value corresponding to the breed A cat in the current information platform is calculated to be P=0.9*(1.2*257-26).

[0079] It can be seen that in the embodiment of the present application, the electronic device can determine the information direction corresponding to each public opinion information of the current pet breed in the public opinion information set of the current platform, determine the support amount corresponding to each public opinion information, calculate the first total support amount of the positively pointed public opinion information and the second total support amount of the negatively pointed public opinion information, and obtain the target analysis value of the current pet breed corresponding to the current information platform through the above calculation formula. This will help the target analysis value to be closer to the real public opinion, help to further ensure the accuracy of the public opinion analysis, and thus help to ensure the accuracy of information recommendation.

[0080] In a possible example, if there are multiple platform public opinion information sets, determining the market public opinion corresponding to each pet breed according to the target analysis value may include the following steps:

[0081] Adding the target analysis values ​​of each of the information platforms corresponding to the current pet breed to obtain a total target analysis value;

[0082] When the total value of the target analysis is a positive number, the market public opinion is determined to be positive public opinion;

[0083] When the total value of the target analysis is a negative number, the market public opinion is determined to be negative public opinion;

[0084] When the total value of the target analysis is zero, it is determined that the market public opinion is neutral public opinion.

[0085] For example, for cats of breed A, the target analysis value corresponding to platform A is Pa = 0.9*(1.2*257-26), the target analysis value corresponding to platform B is Pb = 1*(1.2*280-342), and the target analysis value corresponding to platform C is Pc = 0.6*(1.2*2784-2930). Adding the target analysis values ​​of multiple information platforms, the total target analysis value is 0.9*(1.2*257-26)+1*(1.2*280-342)+0.7*(1.2*2784-3930)=-164.28. Since the total target analysis value is a negative number, it can be determined that the long-term public opinion is negative public opinion, that is, the target group has a dislike attitude towards this pet breed.

[0086] In this way, processing the target analysis values ​​corresponding to multiple information platforms will help obtain more comprehensive and objective information, help further ensure the accuracy of public opinion analysis, and thus help ensure the accuracy of information recommendations.

[0087] In a possible example, analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed may include the following steps:

[0088] According to the information type corresponding to the public opinion information, the public opinion information is divided into at least one classified public opinion information set;

[0089] Determine the amount of public opinion information corresponding to each pet breed in each of the classified public opinion information sets;

[0090] For the current pet breed, according to the preset mapping relationship between the information type and the reference weight, the reference weight corresponding to each information type is determined, and the target weight corresponding to each classified public opinion information set is determined;

[0091] According to the target weight, weighted calculation is performed on the quantity of the public opinion information in the classified public opinion information set to obtain a predicted public opinion heat value corresponding to the current pet breed;

[0092] The market public opinion corresponding to the current pet breed is determined according to the predicted public opinion heat value.

[0093] The above information types may include at least one of audio, video, text, and pictures.

[0094] Among them, the above-mentioned classified public opinion information set can be one or more, which is not limited here. The number of classified public opinion information sets can correspond to the number of types of information types, which is not limited here. Each classified public opinion information set can be used to indicate the public opinion information corresponding to each information type, and each classified public opinion information set includes public opinion information corresponding to at least one pet breed.

[0095] Among them, the mapping relationship between the above-mentioned preset information types and reference weights can be pre-stored in the electronic device, or can be set by the user, which is not limited here. It should be noted that considering the differences in the propagation speed and propagation range of different information types, for example, the propagation range of video information is wider than that of text information. Therefore, different reference weights can be set for different information types, which helps to improve the accuracy of predicting the heat of public opinion.

[0096] For example, if the information types corresponding to public opinion information include audio, video, text, and pictures, the public opinion information is divided into a classified public opinion information set corresponding to audio information, a classified public opinion information set corresponding to video information, a classified public opinion information set corresponding to text information, and a classified public opinion information set corresponding to picture information. Among them, the pet breeds in the classified public opinion information set corresponding to audio information include cat A, dog B, and rabbit C, of ​​which there are 60 audio information about cat A. The pet breeds in the classified public opinion information set corresponding to video information include cat A and mouse D, of which there are 213 video information about cat A. The pet breeds in the classified public opinion information set corresponding to text information include cat A, of which there are 800 text information about cat A, and the pet breeds in the classified public opinion information set corresponding to picture information include rabbit C.

[0097] According to the mapping relationship between the preset information type and the reference weight, the reference weight corresponding to the audio information is determined to be 0.9, and the target weight corresponding to the classified public opinion information set corresponding to the audio information is 0.9. The reference weight corresponding to the video information is 1.1, and the target weight corresponding to the classified public opinion information set corresponding to the video information is 1.1. The reference weight corresponding to the text information is 0.86, and the target weight corresponding to the classified public opinion information set corresponding to the text information is 0.86. The reference weight corresponding to the picture information is 0.7, and the target weight corresponding to the classified public opinion information set corresponding to the picture information is 0.7.

[0098] For cat A, the predicted public opinion heat value of the classified public opinion information set corresponding to audio information is 0.9*60, the predicted public opinion heat value of the classified public opinion information set corresponding to video information is 1.1*213, the predicted public opinion heat value of the classified public opinion information set corresponding to text information is 0.86*800, and the predicted public opinion heat value of the classified public opinion information set corresponding to image information is 0.7*0. The predicted public opinion heat value of cat A is 0.9*60+1.1*213+0.86*800+0.7*0. It can be understood that the higher the predicted public opinion heat value, the greater the public opinion heat corresponding to the current pet breed.

[0099] The market public opinion analysis method for other pet breeds is similar to the above method and will not be repeated here. It should be noted that, as described in the above example, the public opinion information corresponding to the pet breed Ding rat only appears in the classified public opinion information set corresponding to the video information. In this case, it is only necessary to determine the market public opinion corresponding to Ding rat based on the predicted public opinion heat value of Ding rat in the classified public opinion information set corresponding to the video information.

[0100] It can be seen that in the embodiments of the present application, the electronic device can classify the public opinion information into at least one classified public opinion information set according to the information type corresponding to the public opinion information, determine the number of public opinion information corresponding to each pet breed in each classified public opinion information set, and for the current pet breed, determine the reference weight corresponding to each information type according to the mapping relationship between the preset information type and the reference weight, and determine the target weight corresponding to each classified public opinion information set; according to the target weight, perform weighted calculation on the number of public opinion information in the classified public opinion information set to obtain the predicted public opinion heat value corresponding to the current pet breed; according to the predicted public opinion heat value, determine the market public opinion corresponding to the current pet breed; in this way, classifying and analyzing the public opinion information corresponding to the pet breed according to the different information types helps to accurately determine the market public opinion corresponding to each pet breed.

[0101] In a possible example, the historical behavior records include positive behavior records, negative behavior records, and neutral behavior records, the market public opinion includes positive public opinion, negative public opinion, and neutral public opinion, and determining the target pet breed that the user is interested in based on the user's historical behavior records and the market public opinion includes:

[0102] When the historical behavior record is the positive behavior record and the market public opinion is the positive public opinion, determining the current pet breed as the target pet breed;

[0103] When the historical behavior record is the negative behavior record and the market public opinion is the negative public opinion, the current pet breed is determined as a non-target pet breed.

[0104] Among them, positive behavior records can be used to represent the behavior of users expressing positive public opinion information on a certain pet breed, and can also be used to represent the behavior of users expressing support for positive public opinion information corresponding to a certain pet breed, and can also be used to represent the behavior of users expressing opposition to negative public opinion information corresponding to a certain pet breed, without limitation here.

[0105] Among them, negative behavior records can be used to represent the behavior of users publishing negative public opinion information on a certain pet breed, and can also be used to represent the behavior of users expressing support for negative public opinion information corresponding to a certain pet breed, and can also be used to represent the behavior of users expressing opposition to positive public opinion information corresponding to a certain pet breed, without limitation here.

[0106] Among them, neutral behavior records can be used to represent the behavior that the user has not yet made any comments on a certain pet breed, and can also be used to represent the behavior that the user has not yet expressed support or opposition to public opinion information corresponding to a certain pet breed, without any limitation here.

[0107] In the specific implementation, possible situations are shown in the following table.

[0108] Historical behavior records Market sentiment Target pet breed Positive Positive Target pet breeds Positive Negative Non-target pet breeds Positive neutral Target pet breeds Negative Positive Non-target pet breeds Negative Negative Non-target pet breeds Negative neutral Non-target pet breeds neutral Positive Target pet breeds neutral Negative Non-target pet breeds neutral neutral Non-target pet breeds

[0109] It can be seen that in the embodiment of the present application, based on the user's historical behavior record and market public opinion, it is determined whether the current pet breed is the target pet breed. When the current pet breed is the target pet breed, the target pet content corresponding to the target pet breed is determined, and the target pet content is recommended to the user's client device. This helps to accurately predict the target pet content that the user is interested in, thereby improving the accuracy of information recommendation and helping to improve user satisfaction.

[0110] In a possible example, if there are multiple pet breeds, determining the public opinion information corresponding to the pet breeds may include the following steps:

[0111] Obtain original public opinion information within a preset time period;

[0112] The original public opinion information is processed according to the keywords corresponding to each of the pet breeds to obtain the public opinion information corresponding to each of the pet breeds.

[0113] Among them, the above-mentioned preset time length can be set according to factors such as pet breed, search scope of original public opinion information, user settings, etc., and is not limited here. For example, it can be 5 days, 7 days, 10 days, 15 days, 30 days, 3 months, half a year, one year, etc.

[0114] The above-mentioned original public opinion information is used to indicate the opinions expressed by the target group. The original public opinion information includes public opinion information related to pet breeds and information unrelated to pet breeds.

[0115] The keywords corresponding to the above-mentioned pet breeds may be the names of the pet breeds or the unique characteristics of the pet breeds, which are not limited here.

[0116] In the specific implementation, the original public opinion information within the preset time period is obtained, and the original public opinion information is filtered and classified according to the keywords corresponding to the pet breeds. If there are multiple pet breeds, the public opinion information corresponding to the multiple pet breeds can be obtained. In this way, filtering and classifying the original public opinion information helps to reduce the amount of information processing in the subsequent process and improve the efficiency of information recommendation.

[0117] In accordance with the above embodiment, please refer to Figure 2 , Figure 2 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor. In the embodiment of the present application, the program includes instructions for executing the following steps:

[0118] Determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate comments related to the pet breed published by a target group, wherein the target group refers to a group that publishes comments on the pet breed;

[0119] Analyze the public opinion information to obtain the market public opinion corresponding to the pet breed, where the market public opinion is used to indicate the direction and / or heat of public opinion;

[0120] Determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device;

[0121] Determining target pet content that the user is interested in based on the target pet breed, the target pet content being used to indicate content corresponding to the target pet breed;

[0122] The target pet content is recommended to the client device of the user.

[0123] It can be seen that the electronic device described in the embodiment of the present application can determine the public opinion information corresponding to the pet breed, analyze the public opinion information, obtain the market public opinion corresponding to the pet breed, determine the target pet breed that the user is interested in based on the user's historical behavior records and market public opinion, determine the target pet content that the user is interested in based on the target pet breed, and recommend the target pet content to the user's client device; in this way, combining the user's historical behavior records and market public opinion to recommend pet information to the user helps to accurately predict the target pet content that the user is interested in, thereby improving the accuracy of information recommendation and helping to improve user satisfaction.

[0124] In a possible example, in analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed, the program includes instructions for executing the following steps:

[0125] According to the information platform corresponding to the public opinion information, the public opinion information is divided into at least one platform public opinion information set, wherein the information platform is used to indicate the social platform on which the target group publishes the public opinion information, each platform public opinion information set is used to indicate the public opinion information published on each information platform, and each platform public opinion information set includes at least one public opinion information corresponding to the pet breed;

[0126] According to the preset analysis rules, the public opinion information corresponding to each pet breed in the public opinion information set of each platform is analyzed respectively to obtain the target analysis value of each pet breed corresponding to each information platform;

[0127] The market sentiment corresponding to each of the pet breeds is determined according to at least one of the target analysis values.

[0128] In one possible example, in terms of analyzing the public opinion information corresponding to each pet breed in each platform public opinion information set according to a preset analysis rule to obtain a target analysis value for each pet breed corresponding to each information platform, the program includes instructions for executing the following steps:

[0129] Determine the information orientation corresponding to each public opinion information of the current pet breed in the current platform public opinion information set, wherein the information orientation is used to indicate the emotional tendency of the target group towards the current pet breed, and the information orientation includes positive orientation and negative orientation;

[0130] Determine the amount of support corresponding to each piece of public opinion information;

[0131] Calculating a first total support amount of the positive public opinion information and a second total support amount of the negative public opinion information;

[0132] A target analysis value of the current pet breed corresponding to the current information platform is determined according to the first total support amount, the second total support amount and a preset relationship.

[0133] In a possible example, if there are multiple platform public opinion information sets, in determining the market public opinion corresponding to each pet breed according to the target analysis value, the above program includes instructions for executing the following steps:

[0134] Adding the target analysis values ​​of each of the information platforms corresponding to the current pet breed to obtain a total target analysis value;

[0135] When the total value of the target analysis is a positive number, the market public opinion is determined to be positive public opinion;

[0136] When the total value of the target analysis is a negative number, the market public opinion is determined to be negative public opinion;

[0137] When the total value of the target analysis is zero, it is determined that the market public opinion is neutral public opinion.

[0138] In a possible example, in analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed, the program includes instructions for executing the following steps:

[0139] According to the information type corresponding to the public opinion information, the public opinion information is divided into at least one classified public opinion information set, wherein the information type includes at least one of audio, video, text, and picture, each of the classified public opinion information sets is used to indicate the public opinion information corresponding to each of the information types, and each of the classified public opinion information sets includes at least one of the public opinion information corresponding to the pet breed;

[0140] Determine the amount of public opinion information corresponding to each pet breed in each of the classified public opinion information sets;

[0141] For the current pet breed, according to the preset mapping relationship between the information type and the reference weight, the reference weight corresponding to each information type is determined, and the target weight corresponding to each classified public opinion information set is determined;

[0142] According to the target weight, weighted calculation is performed on the quantity of the public opinion information in the classified public opinion information set to obtain a predicted public opinion heat value corresponding to the current pet breed;

[0143] The market public opinion corresponding to the current pet breed is determined according to the predicted public opinion heat value.

[0144] In a possible example, the historical behavior records include positive behavior records, negative behavior records, and neutral behavior records, and the market public opinion includes positive public opinion, negative public opinion, and neutral public opinion. In determining the target pet breed that the user is interested in based on the user's historical behavior records and the market public opinion, the above program includes instructions for performing the following steps:

[0145] When the historical behavior record is the positive behavior record and the market public opinion is the positive public opinion, determining the current pet breed as the target pet breed;

[0146] When the historical behavior record is the negative behavior record and the market public opinion is the negative public opinion, the current pet breed is determined as a non-target pet breed.

[0147] In a possible example, if there are multiple pet breeds, in determining the public opinion information corresponding to the pet breed, the program includes instructions for performing the following steps:

[0148] Acquire original public opinion information within a preset time period, where the original public opinion information is used to indicate the opinions expressed by the target group;

[0149] The original public opinion information is processed according to the keywords corresponding to each of the pet breeds to obtain the public opinion information corresponding to each of the pet breeds.

[0150] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should be easily aware that, in combination with the units and algorithm steps of each example described in the embodiment provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0151] The embodiment of the present application can divide the functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0152] See also Figure 3 , Figure 3 is a functional unit composition block diagram of an information recommendation device 300 involved in an embodiment of the present application, wherein the device 300 comprises: a determination unit 301, an analysis unit 302 and a recommendation unit 303, wherein:

[0153] The determining unit 301 is used to determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate the opinions related to the pet breed published by a target group, and the target group refers to the group that publishes opinions on the pet breed;

[0154] The analysis unit 302 is used to analyze the public opinion information to obtain the market public opinion corresponding to the pet breed, and the market public opinion is used to indicate the direction and / or heat of public opinion;

[0155] The determination unit 301 is further used to determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device;

[0156] The determination unit 301 is further used to determine the target pet content that the user is interested in according to the target pet breed, and the target pet content is used to indicate the content corresponding to the target pet breed;

[0157] The recommendation unit 303 is configured to recommend the target pet content to the client device of the user.

[0158] It can be seen that the information recommendation device provided in the embodiment of the present application can determine the public opinion information corresponding to the pet breed, analyze the public opinion information, obtain the market public opinion corresponding to the pet breed, determine the target pet breed that the user is interested in based on the user's historical behavior records and market public opinion, determine the target pet content that the user is interested in based on the target pet breed, and recommend the target pet content to the user's client device; in this way, combining the user's historical behavior records and market public opinion to recommend pet information to the user, helps to accurately predict the target pet content that the user is interested in, thereby improving the accuracy of information recommendation and helping to improve user satisfaction.

[0159] In a possible example, in analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed, the analyzing unit 302 is specifically used to:

[0160] According to the information platform corresponding to the public opinion information, the public opinion information is divided into at least one platform public opinion information set, wherein the information platform is used to indicate the social platform on which the target group publishes the public opinion information, each platform public opinion information set is used to indicate the public opinion information published on each information platform, and each platform public opinion information set includes at least one public opinion information corresponding to the pet breed;

[0161] According to the preset analysis rules, the public opinion information corresponding to each pet breed in the public opinion information set of each platform is analyzed respectively to obtain the target analysis value of each pet breed corresponding to each information platform;

[0162] The market sentiment corresponding to each of the pet breeds is determined according to at least one of the target analysis values.

[0163] In a possible example, in analyzing the public opinion information corresponding to each pet breed in each platform public opinion information set according to a preset analysis rule, and obtaining a target analysis value of each pet breed corresponding to each information platform, the analysis unit 302 is specifically used to:

[0164] Determine the information orientation corresponding to each public opinion information of the current pet breed in the current platform public opinion information set, wherein the information orientation is used to indicate the emotional tendency of the target group towards the current pet breed, and the information orientation includes positive orientation and negative orientation;

[0165] Determine the amount of support corresponding to each piece of public opinion information;

[0166] Calculating a first total support amount of the positive public opinion information and a second total support amount of the negative public opinion information;

[0167] A target analysis value of the current pet breed corresponding to the current information platform is determined according to the first total support amount, the second total support amount and a preset relationship.

[0168] In a possible example, if there are multiple platform public opinion information sets, in determining the market public opinion corresponding to each pet breed according to the target analysis value, the analysis unit 302 is specifically used to:

[0169] Adding the target analysis values ​​of each of the information platforms corresponding to the current pet breed to obtain a total target analysis value;

[0170] When the total value of the target analysis is a positive number, the market public opinion is determined to be positive public opinion;

[0171] When the total value of the target analysis is a negative number, the market public opinion is determined to be negative public opinion;

[0172] When the total value of the target analysis is zero, it is determined that the market public opinion is neutral public opinion.

[0173] In a possible example, in analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed, the analyzing unit 302 is specifically used to:

[0174] According to the information type corresponding to the public opinion information, the public opinion information is divided into at least one classified public opinion information set, wherein the information type includes at least one of audio, video, text, and picture, each of the classified public opinion information sets is used to indicate the public opinion information corresponding to each of the information types, and each of the classified public opinion information sets includes at least one of the public opinion information corresponding to the pet breed;

[0175] Determine the amount of public opinion information corresponding to each pet breed in each of the classified public opinion information sets;

[0176] For the current pet breed, according to the preset mapping relationship between the information type and the reference weight, the reference weight corresponding to each information type is determined, and the target weight corresponding to each classified public opinion information set is determined;

[0177] According to the target weight, weighted calculation is performed on the quantity of the public opinion information in the classified public opinion information set to obtain a predicted public opinion heat value corresponding to the current pet breed;

[0178] The market public opinion corresponding to the current pet breed is determined according to the predicted public opinion heat value.

[0179] In a possible example, the historical behavior records include positive behavior records, negative behavior records, and neutral behavior records, and the market public opinion includes positive public opinion, negative public opinion, and neutral public opinion. In determining the target pet breed that the user is interested in based on the user's historical behavior records and the market public opinion, the determination unit 301 is specifically used to:

[0180] When the historical behavior record is the positive behavior record and the market public opinion is the positive public opinion, determining the current pet breed as the target pet breed;

[0181] When the historical behavior record is the negative behavior record and the market public opinion is the negative public opinion, the current pet breed is determined as a non-target pet breed.

[0182] In a possible example, if there are multiple pet breeds, in determining the public opinion information corresponding to the pet breeds, the analyzing unit 302 is specifically used to:

[0183] Acquire original public opinion information within a preset time period, where the original public opinion information is used to indicate the opinions expressed by the target group;

[0184] The original public opinion information is processed according to the keywords corresponding to each of the pet breeds to obtain the public opinion information corresponding to each of the pet breeds.

[0185] It can be understood that the functions of each program module of the information recommendation device of this embodiment can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0186] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes a control platform.

[0187] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes a control platform.

[0188] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0189] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0190] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0191] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0192] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0193] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0194] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0195] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An information recommendation method, characterized in that: Applied to a server, the method comprises: Determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate comments related to the pet breed published by a target group, wherein the target group refers to a group that publishes comments on the pet breed; Analyze the public opinion information to obtain market public opinion corresponding to the pet breed, wherein the market public opinion is used to indicate the direction and / or heat of public opinion; including: dividing the public opinion information into at least one platform public opinion information set according to the information platform corresponding to the public opinion information, wherein the information platform is used to indicate the social platform on which the target group publishes the public opinion information, each platform public opinion information set is used to indicate the public opinion information published on each information platform, and each platform public opinion information set includes at least one public opinion information corresponding to the pet breed; Determine the information orientation corresponding to each public opinion information of the current pet breed in the current platform public opinion information set, wherein the information orientation is used to indicate the emotional tendency of the target group towards the current pet breed, and the information orientation includes positive orientation and negative orientation; Determine the amount of support corresponding to each piece of public opinion information; Calculating a first total support amount of the positive public opinion information and a second total support amount of the negative public opinion information; According to the first total support amount, the second total support amount and a preset relationship, the target analysis value of the current pet breed corresponding to the current information platform is determined; the preset relationship is P=a (1.2 mn), P is the target analysis value of the current pet breed corresponding to the current information platform, a is the impact factor corresponding to the current information platform, m is the first total support amount of the positive public opinion information, and n is the second total support amount of the negative public opinion information; Determining the market sentiment corresponding to each pet breed according to at least one of the target analysis values; Determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device; Determining target pet content that the user is interested in based on the target pet breed, where the target pet content is used to indicate content corresponding to the target pet breed; The target pet content is recommended to the client device of the user.

2. The method according to claim 1, characterized in that If there are multiple platform public opinion information sets, determining the market public opinion corresponding to each pet breed according to the target analysis value includes: Adding the target analysis values ​​of each of the information platforms corresponding to the current pet breed to obtain a total target analysis value; When the total value of the target analysis is a positive number, the market public opinion is determined to be positive public opinion; When the total value of the target analysis is a negative number, the market public opinion is determined to be negative public opinion; When the total value of the target analysis is zero, it is determined that the market public opinion is neutral public opinion.

3. The method according to claim 1, characterized in that The analyzing the public opinion information to obtain the market public opinion corresponding to the pet breed includes: According to the information type corresponding to the public opinion information, the public opinion information is divided into at least one classified public opinion information set, wherein the information type includes at least one of audio, video, text, and picture, each of the classified public opinion information sets is used to indicate the public opinion information corresponding to each of the information types, and each of the classified public opinion information sets includes at least one of the public opinion information corresponding to the pet breed; Determine the amount of public opinion information corresponding to each pet breed in each of the classified public opinion information sets; For the current pet breed, according to the preset mapping relationship between the information type and the reference weight, the reference weight corresponding to each information type is determined, and the target weight corresponding to each classified public opinion information set is determined; According to the target weight, weighted calculation is performed on the quantity of the public opinion information in the classified public opinion information set to obtain a predicted public opinion heat value corresponding to the current pet breed; The market public opinion corresponding to the current pet breed is determined according to the predicted public opinion heat value.

4. The method according to any one of claims 1 to 3, characterized in that: The historical behavior records include positive behavior records, negative behavior records, and neutral behavior records, the market public opinion includes positive public opinion, negative public opinion, and neutral public opinion, and determining the target pet breed that the user is interested in based on the user's historical behavior records and the market public opinion includes: When the historical behavior record is the positive behavior record and the market public opinion is the positive public opinion, determining the current pet breed as the target pet breed; When the historical behavior record is the negative behavior record and the market public opinion is the negative public opinion, the current pet breed is determined as a non-target pet breed.

5. The method according to claim 1, characterized in that If there are multiple pet breeds, determining the public opinion information corresponding to the pet breeds includes: Acquire original public opinion information within a preset time period, where the original public opinion information is used to indicate the opinions expressed by the target group; The original public opinion information is processed according to the keywords corresponding to each of the pet breeds to obtain the public opinion information corresponding to each of the pet breeds.

6. An information recommendation device, characterized in that: Applied to a server, the device comprises: a determination unit, an analysis unit and a recommendation unit, wherein: The determining unit is used to determine public opinion information corresponding to a pet breed, wherein the public opinion information is used to indicate the opinions related to the pet breed published by a target group, and the target group refers to the group that publishes opinions on the pet breed; The analysis unit is used to analyze the public opinion information to obtain the market public opinion corresponding to the pet breed, and the market public opinion is used to indicate the direction and / or heat of public opinion; specifically, it is used to: divide the public opinion information into at least one platform public opinion information set according to the information platform corresponding to the public opinion information, wherein the information platform is used to indicate the social platform on which the target group publishes the public opinion information, each platform public opinion information set is used to indicate the public opinion information published on each information platform, and each platform public opinion information set includes at least one public opinion information corresponding to the pet breed; Determine the information orientation corresponding to each public opinion information of the current pet breed in the current platform public opinion information set, wherein the information orientation is used to indicate the emotional tendency of the target group towards the current pet breed, and the information orientation includes positive orientation and negative orientation; Determine the amount of support corresponding to each piece of public opinion information; Calculating a first total support amount of the positive public opinion information and a second total support amount of the negative public opinion information; According to the first total support amount, the second total support amount and a preset relationship, the target analysis value of the current pet breed corresponding to the current information platform is determined; the preset relationship is P=a (1.2 mn), P is the target analysis value of the current pet breed corresponding to the current information platform, a is the impact factor corresponding to the current information platform, m is the first total support amount of the positive public opinion information, and n is the second total support amount of the negative public opinion information; Determining the market sentiment corresponding to each pet breed according to at least one of the target analysis values; The determination unit is further used to determine the target pet breed that the user is interested in based on the user's historical behavior record and the market public opinion, wherein the historical behavior record is used to indicate the behavior corresponding to the pet breed performed by the user on the client device; The determination unit is further used to determine the target pet content that the user is interested in according to the target pet breed, and the target pet content is used to indicate the content corresponding to the target pet breed; The recommendation unit is configured to recommend the target pet content to the client device of the user.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program comprises instructions for executing the steps in the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute instructions of the steps in the method according to any one of claims 1 to 5.

Images