Point of interest selection method and apparatus, electronic device, and storage medium

Abstract

The application discloses a field-oriented interest point selection method and device and electronic equipment, and relates to the field of interest point selection. The specific implementation scheme is as follows: a target interest point is selected from a complete set of interest points, and a target field is determined; a sample set including a plurality of samples is acquired, each sample including a belonging field and the target interest point; the correlation between the target interest point and the target field is calculated by using the sample set; the interest point related to the target field is obtained according to the correlation; and the user interest point set related to the target field is selected by using the user interest point set. The applicability of the interest point selection is improved, the interest point selection can be better targeted to the user interest, and the scene of the increasing sample scale can be adapted.

Description

[0001] This application is a divisional application of the patent application with application number 201911129033.5, titled "Point of interest selection method, device and electronic equipment", and filed on November 18, 2019. TECHNICAL FIELD

[0002] The present application relates to the field of big data, in particular to the field of point of interest selection. BACKGROUND

[0003] The user point of interest selection technology refers to a technology of selecting a point of interest meeting certain business requirements from a plurality of (hundreds or even thousands) points of interest of a user. The business can be described as one or several explicitly expressed fields. At present, the collection of the user points of interest is generally completed by capturing the interaction signals of the user in the process of using the product, and this collection process has the characteristics of non-direction and no field distinction. However, when developing the functions of the product, the points of interest of the user in a certain specific field need to be collected. The existing methods for selecting the points of interest in the specific field include three kinds. The first kind is to find the content associated with the point of interest by using the unstructured data and the point of interest one by one. The second kind is to select the matching point of interest according to the query sentence. The third kind is a point of interest selection method based on the user attention degree. The key of this method is to use the attention degree mechanism to determine whether the name information and the corresponding address information of the point of interest match. The above three kinds of point of interest selection methods not only have low relevance between the selected points of interest and the specific field, but also cannot meet the requirement of selecting the points of interest strongly related to the specific field in a large-scale sample, and cannot select the points of interest more interested by the user. SUMMARY

[0004] The embodiments of the present application provide a point of interest selection method, device and electronic equipment to solve one or more technical problems in the prior art.

[0005] In a first aspect, the embodiments of the present application provide a point of interest selection method, comprising:

[0006] selecting a target point of interest from a point of interest set, and determining a target field;

[0007] obtaining a sample set including a plurality of samples, each sample including a belonging field and the target point of interest;

[0008] calculating a first sample probability that the belonging field of the sample and the target field are the same field, and a second sample probability that the belonging field of the sample and the target field are not the same field;

[0009] Based on the ratio of the first sample probability to the second sample probability, the first number of samples whose domain is the same as the target domain and the second number of samples whose domain is not the same as the target domain are obtained.

[0010] The correlation between the target interest point and the target domain is obtained based on the ratio of the first sample number to the second sample number.

[0011] Based on the relevance, the points of interest related to the target domain are obtained;

[0012] Traverse each interest point in the complete set of interest points, take each interest point as a target interest point, and use Bayesian principle to calculate the correlation between each target interest point and the target domain, and calculate multiple correlations;

[0013] Based on the multiple relevances, a set of interest points related to the target domain is obtained;

[0014] The intersection of the user interest point set and the interest point set related to the target domain is obtained to obtain the user interest point set related to the target domain.

[0015] In one possible implementation, a set of interest points related to the target domain is obtained based on the plurality of relevances, including:

[0016] Among the multiple relevance values, those greater than the relevance threshold are selected.

[0017] The target interest points corresponding to the obtained relevance scores are determined as interest points related to the target domain.

[0018] The selected interest points related to the target domain are combined into a set of interest points related to the target domain.

[0019] In one possible implementation, obtaining the relevance between the target interest point and the target domain based on the ratio of the first sample number to the second sample number includes:

[0020] The ratio of the first sample size to the second sample size is used as the relevance between the target interest point and the target domain.

[0021] Secondly, embodiments of this application provide a point-of-interest (POI) selection device, including:

[0022] The target determination module is used to select target points of interest from the entire set of points of interest and determine the target domain;

[0023] The sample acquisition module is used to acquire a sample set including multiple samples, each of which includes its own domain and the target interest point;

[0024] The relevance calculation module is configured to calculate a first sample probability that the field of the sample is the same as the target field, a second sample probability that the field of the sample is not the same as the target field, obtain a ratio of the first sample number that the field of the sample is the same as the target field and the second sample number that the field of the sample is not the same as the target field according to a ratio of the first sample probability and the second sample probability, and obtain the relevance between the target interest point and the target field according to a ratio of the first sample number and the second sample number.

[0025] The interest point selection module is configured to obtain the interest points related to the target field according to the relevance.

[0026] The interest point traversal module is configured to traverse each interest point in the interest point set, take each interest point as a target interest point, calculate the relevance between each target interest point and the target field by using the Bayesian principle, and obtain a plurality of relevances.

[0027] The interest point set acquisition module is configured to obtain the interest point set related to the target field according to the plurality of relevances.

[0028] The intersection module is configured to obtain the user interest point set related to the target field by performing an intersection operation on the user interest point set and the interest point set related to the target field.

[0029] In a possible implementation, the interest point set acquisition module includes:

[0030] The relevance screening submodule is configured to screen, from the plurality of relevances, a relevance that is greater than a relevance threshold.

[0031] The field-related interest point determination submodule is configured to determine, as the interest point related to the target field, a target interest point corresponding to the screened relevance.

[0032] The interest point set acquisition submodule is configured to group the interest points related to the target field that are screened to obtain the interest point set related to the target field.

[0033] In a possible implementation, the relevance calculation module is further configured to take the ratio of the first sample number and the second sample number as the relevance between the target interest point and the target field.

[0034] In a third aspect, an electronic device is provided, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0035] In a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to enable a computer to perform the method described above.

[0036] One embodiment of the above application has the following advantages or beneficial effects: the correlation between the target interest point and the target field is calculated by using a sample set, and the correlation is used to obtain a target field related interest point set, and the target field related interest point set is combined with a user interest point set to obtain a target field related user interest point set. This technical means overcomes the technical problem in the prior art that the correlation between the selected interest point and the specific field is low, and the specific field strongly related interest point cannot be selected in a large sample. The technical effect is achieved that the interest point related to the field and interested by the user can be selected without referring to the relevant knowledge of each field, and the applicability of the interest point selection is improved. Meanwhile, the technical effect of adapting to the scene of increasing sample size is achieved.

[0037] Other effects of the above optional mode will be described in the following with reference to specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings are used to better understand the present application, and do not limit the present application. Among them:

[0039] Figure 1 is a flowchart of an interest point selection method according to an embodiment of the present application;

[0040] Figure 2 is a scene diagram of an interest point selection method according to an embodiment of the present application;

[0041] Figure 3 is a flowchart of another interest point selection method according to an embodiment of the present application;

[0042] Figure 4 is a flowchart of another interest point selection method according to an embodiment of the present application;

[0043] Figure 5 is a flowchart of a correlation calculation method between a target interest point and a target field according to an embodiment of the present application;

[0044] Figure 6A structural block diagram of a point of interest selection device according to an embodiment of the present application is shown in FIG. 1.

[0045] Figure 7 A structural block diagram of another point of interest selection device according to an embodiment of the present application is shown in FIG. 2.

[0046] Figure 8 A structural block diagram of a calculation sub-module according to an embodiment of the present application is shown in FIG. 3.

[0047] Figure 9 A block diagram of an electronic device for implementing a point of interest selection method according to an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0048] The exemplary embodiments of the present application are described below with reference to the accompanying drawings, in which the details of the embodiments of the present application are provided to assist in the understanding of the present application. It should be apparent to those skilled in the art that various modifications and changes can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, the descriptions in the following are presented to describe the principles of the present application and to provide a concrete understanding of the present application. Accordingly, it should be understood that the scope of the present application is not limited by the descriptions.

[0049] Embodiment One

[0050] In one specific embodiment, as shown in FIG. 1, a point of interest selection method is provided, comprising: Figure 1

[0051] Step S10: selecting a target point of interest from a point of interest set and determining a target field;

[0052] Step S20: obtaining a sample set comprising a plurality of samples, each sample comprising a field of belonging and the target point of interest;

[0053] Step S30: calculating a correlation between the target point of interest and the target field using the sample set;

[0054] Step S40: obtaining a point of interest related to the target field according to the correlation.

[0055] ​In an example, the sample can be a video, an article, a picture, or the like, which is a carrier of content browsed by a user. The content browsed by the user can be classified to obtain a plurality of fields. For example, a science and technology field, a sports field, a finance field, a cooking field, an art field, or the like. The interest point refers to a project in which the user is interested in each field. For example, the interest points in the sports field can include football, volleyball, diving, artistic gymnastics, and the like. The interest points in the finance field can include stocks, funds, and the like. The interest points in the science and technology field can include manned spacecraft, intelligent robots, smart home appliances, smart phones, and the like. The interest point universe contains all interest points in each field, a target interest point is selected from the interest point universe, and a target field corresponding to the target interest point is determined.

[0056] A sample set including a plurality of samples is obtained. Each sample includes a field to which the sample belongs and at least one interest point. For example, a video program of the sample "China on a Tongue" corresponds to a cooking field, and contains interest points including Chinese food, western food, various food materials, and the like. An article of the sample "Real Record of Huawei Mobile Phone Release" corresponds to a science and technology field, and contains interest points such as smart phones and 5G networks. It should be noted that in the case where any interest point in the interest point universe can be a target interest point, in order to facilitate obtaining the correlation between the interest points in the interest point universe and the target field, when selecting the samples in the sample set, each sample can at least contain an interest point in the interest point universe that can be a target interest point.

[0057] As shown in Figure 2 , in the embodiment, the target field and the target interest point are associated by using sample data. Specifically, the correlation between the target interest point and the target field is calculated according to the field label, the sample data, and the interest point universe. The Bayesian principle can be selected to calculate a first probability that the field to which the sample containing the target interest point belongs is the target field, a second probability that the field to which the sample containing the target interest point belongs is not the target field, and a ratio of the first probability and the second probability to obtain the correlation between the target interest point and the target field. According to the correlation, the interest points related to the target field are obtained. For example, if the correlation is greater than a correlation threshold, the interest points related to the target field are determined.

[0058] The interest point selection method provided by the embodiment calculates the correlation between the target interest point and the target field by using the sample set, and further obtains the interest points related to the target field by using the correlation. Without referring to the related knowledge of each target field, the interest points related to the target field can be selected, and the applicability of the interest point selection is improved.

[0059] In an embodiment, as shown in Figure 3 , further comprising:

[0060] Step S50: traversing the whole set of interest points, and calculating a plurality of relevancies;

[0061] Step S60: obtaining a set of interest points related to the target field according to the plurality of relevancies;

[0062] Step S70: obtaining a set of user interest points related to the target field by intersecting the set of user interest points with the set of interest points related to the target field.

[0063] In this embodiment, all interest points in the whole set of interest points are traversed as target interest points, and the relevancy between each target interest point and the target field can be calculated by using the Bayesian principle. The plurality of calculated relevancies are compared with a relevancy threshold, and the relevancies greater than the relevancy threshold are screened, and then the target interest points corresponding to the screened relevancies are obtained to form a set of interest points related to the target field. Finally, the set of user interest points is considered, and the intersection of the set of user interest points and the set of interest points related to the target field is obtained to obtain a set of user interest points related to the target field. For example, in the case of the target field being the science and technology field, the interest points related to the target field selected from the whole set of interest points can include mobile phones, aerospace, robots, and smart home appliances. The set of user interest points includes 5G, smart speakers, mobile phones, the history of philosophy, and baking. After intersection, the set of user interest points related to the science and technology field includes 5G, smart speakers, and mobile phones.

[0064] In this embodiment, the set of interest points related to the target field is combined with the set of user interest points to obtain a set of user interest points related to the target field. Since the set of user interest points is considered, the selection of interest points can be better targeted to the user's interests. In addition, since the relevancy calculation process of each target interest point and the target field is independent of each other, it can adapt to the scenario of increasing sample size. At the same time, it also makes the overall calculation process parallelizable, greatly reducing the overall calculation time. It can be applied in scenarios such as obtaining user portrait data and recommending content of interest in various fields to users.

[0065] In one embodiment, as shown in Figure 4 Step S60:

[0066] Step S601: screening the relevancies greater than the relevancy threshold from the plurality of relevancies;

[0067] Step S602: determining the target interest points corresponding to the screened relevancies as the interest points related to the target field;

[0068] Step S603: forming the set of interest points related to the target field by using the screened interest points related to the target field.

[0069] In one embodiment, as shown inFigure 4 As shown, step S30 comprises:

[0070] Step S301: obtaining the relevance between the target interest point and the target domain according to the ratio of the first sample number of the samples whose belonging domain is the same as the target domain, and the second sample number of the samples whose belonging domain is not the same as the target domain.

[0071] In an example, since the target interest point has been selected from the interest point set, in the sample set, the samples containing the target interest point are first screened out. It is judged whether the belonging domain of each sample is the same as the target domain. According to the judgment result, the samples with the same domain are screened out to obtain the first sample number, and the samples with different domains are screened out to obtain the second sample number. The ratio of the first sample number and the second sample number is the relevance between the target interest point and the target domain. The target interest point and the target domain are associated by using the sample set, without referring to the relevant knowledge of each target domain, the interest point related to the target domain can be selected.

[0072] In an embodiment, as shown in Figure 5 Step S301 comprises:

[0073] Step S3011: calculating the first sample probability of the samples whose belonging domain is the same as the target domain, and the second sample probability of the samples whose belonging domain is not the same as the target domain;

[0074] Step S3012: obtaining the ratio of the first sample number and the second sample number according to the ratio of the first sample probability and the second sample probability;

[0075] Step S3013: taking the ratio of the first sample number and the second sample number as the relevance between the target interest point and the target domain.

[0076] In an example, the interest points corresponding to all domains can constitute the interest point set S: S={att1,att2,…,attn}. The interest point set S can be obtained by the following steps. i ,…,att n},|S|=n. att i is a certain interest point in the set. Each sample can be expressed as t i : t i =(y i ,x i ). Wherein, y i ∈{0,1} represents whether the sample belongs to the target domain D (0 represents not belonging, 1 represents belonging), x i ={att i，1 ,att i，2 ,…,att i，kis a true subset of the set of interest points and represents the set of interest points involved in the sample.

[0077] Bayes' theorem is a theorem about conditional probability (or marginal probability) of random events A and B. According to Bayes' theorem, when a sample contains only one interest point att i , the probability p(y i =1|x=att i ) that the sample belongs to the target domain D, and the probability p(y i =0|x=att i ) that the sample does not belong to the target domain D when the sample contains the interest point can be calculated.

[0078]

[0079]

[0080] wherein, in formula (1), p(x=att i ) is the probability that the sample contains the interest point, p(y i =1) is the probability that the sample belongs to the target domain D, and p(x=att i |y i =1) is the probability that the sample contains the interest point when the sample belongs to the target domain D; in formula (2), p(y i =0) is the probability that the sample does not belong to the target domain D, and p(x=att i |y i =0) is the probability that the sample contains the interest point when the sample does not belong to the target domain D. When the result of formula (1) is greater than that of formula (2), the probability that the sample belongs to the domain D when the sample contains att i is greater than the probability that the sample does not belong to the domain D when the sample contains att i , and it can be considered that the probability that the interest point att i belongs to the domain D is greater than the probability that the interest point does not belong to the domain D. Since the denominators of formula (1) and formula (2) are the same, the numerators can be directly compared in the calculation process. That is:

[0081]

[0082]

[0083] wherein, N, N + , N - , respectively represent the total number of samples, the number of samples belonging to the target domain D, the number of samples not belonging to the target domain D, and the number of samples containing the interest point att iThe number of samples, and the number of interest points att contained in samples that do not belong to the target domain D. i The number of samples.

[0084] In this embodiment, the correlation calculation method based on probability can effectively improve the correlation between the target interest point and the target domain.

[0085] As can be seen from the analysis in the above embodiments, when When the relevance threshold is 1, att i The probability of belonging to target domain D is greater than att. i The probability that an interest point (att) does not belong to the target domain D can be considered as the probability of that point not belonging to the target domain D. i It has a strong positive correlation with the target domain D. Of course, the correlation threshold can also take other values, and can be adaptively adjusted according to actual calculations, all of which are within the protection scope of this implementation method.

[0086] Merge all points of interest that are strongly positively correlated with the specified domain D to form a set S. D ,Right now:

[0087]

[0088] For a given user, the final result is the selection of common interest points with S from all their interest points. Assume user u's set of interest points is S. u ={att1, att2, ..., att i , ...,att k}, then the set of interest points related to domain D is:

[0089] S u，D =S D ∩S u

[0090] Example 2

[0091] In another specific implementation, such as Figure 6 As shown, an interest point selection device 100 is provided, comprising:

[0092] The target determination module 110 is used to select target interest points from the entire set of interest points and determine the target domain;

[0093] The sample acquisition module 120 is used to acquire a sample set including multiple samples, each sample including its domain and target interest points;

[0094] The relevance calculation module 130 is used to calculate the relevance between the target interest point and the target domain using a sample set;

[0095] The interest point selection module 140 is configured to obtain the interest points related to the target field according to the correlation degrees.

[0096] In one embodiment, as shown in FIG. 2, the interest point selection apparatus 200 further includes: Figure 7

[0097] The interest point traversal module 150 is configured to traverse the entire set of interest points and calculate a plurality of correlation degrees.

[0098] The interest point set obtaining module 160 is configured to obtain a set of interest points related to the target field according to the plurality of correlation degrees.

[0099] The intersection module 170 is configured to obtain the set of user interest points related to the target field by performing an intersection operation on the set of user interest points and the set of interest points related to the target field.

[0100] In one embodiment, as shown in FIG. 2, the interest point set obtaining module 160 includes: Figure 7 The correlation degree screening submodule 161 is configured to screen the correlation degrees greater than the correlation degree threshold value from the plurality of correlation degrees.

[0101] The field-related interest point determining submodule 162 is configured to determine the target interest points corresponding to the screened correlation degrees as the interest points related to the target field.

[0102] The interest point set obtaining submodule 163 is configured to form the interest points related to the target field screened out into the set of interest points related to the target field.

[0103] In one embodiment, as shown in FIG. 2, the correlation degree calculation module 130 includes:

[0104] Figure 7 The calculation submodule 131 is configured to obtain the correlation degree between the target interest point and the target field according to the ratio of the first sample number to the second sample number, where the first sample number is the number of samples whose fields belong to the same field as the target field, and the second sample number is the number of samples whose fields do not belong to the same field as the target field.

[0105] In one embodiment, as shown in FIG. 2, the calculation submodule 131 includes:

[0106] The first calculation unit 1311 is configured to calculate a first sample probability that the field of a sample belongs to the same field as the target field, and a second sample probability that the field of the sample does not belong to the same field as the target field. Figure 8 The second calculation unit 1312 is configured to obtain the ratio of the first sample number to the second sample number according to the ratio of the first sample probability to the second sample probability.

[0107] The second calculation unit 1312 is configured to obtain the ratio of the first sample number to the second sample number according to the ratio of the first sample probability to the second sample probability.

[0108] The second calculation unit 1312 is configured to obtain the ratio of the first sample number to the second sample number according to the ratio of the first sample probability to the second sample probability.​​

[0109] The third calculation unit 1313 is configured to take the ratio of the first sample number and the second sample number as the correlation between the target interest point and the target field.

[0110] The functions of each module in the apparatuses in the embodiments of the present application can be referred to the corresponding description in the above method, which will not be repeated here.

[0111] According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

[0112] As shown in Figure 9 is a block diagram of an electronic device for a field-oriented interest point selection method according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown in the electronic device, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit the implementations of the present application described and / or claimed in this document.

[0113] As shown in Figure 9 The electronic device includes one or more processors 901, memory 902, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected using different buses, and can be mounted on a common main board or otherwise installed as needed. The processor can process instructions executed within the electronic device, including graphical information stored in the memory or on the memory to display a graphical user interface (GUI) on an external input / output device, such as a display device coupled to the interface. In other embodiments, multiple processors and / or buses can be used with multiple memories and multiple memory, if necessary. Similarly, multiple electronic devices can be connected, each providing part of the necessary operations (e.g., as a server array, a set of blade servers, or a multi-processor system). Figure 9 The processor 901 is taken as an example in the electronic device.

[0114] The memory 902 is a non-transitory computer readable storage medium provided by the present application. The memory stores instructions executable by at least one processor, so that the at least one processor executes a field-oriented interest point selection method provided by the present application. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to execute a field-oriented interest point selection method provided by the present application.

[0115] The memory 902, as a kind of non-transient computer readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules of a field-oriented interest point selection method in the embodiments of the present application (for example, the target determination module 110, the sample acquisition module 120, the correlation calculation module 130, the interest point selection module 140 shown in the above description). Figure 6 The processor 901 can execute various function applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 902, that is, implement the field-oriented interest point selection method in the above method embodiments.

[0116] The memory 902 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created by use of the electronic device according to the field-oriented interest point selection method and the like. In addition, the memory 902 can include a high-speed random access memory, and can also include a non-transient memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transient solid-state memory device. In some embodiments, the memory 902 can optionally include a memory disposed remotely with respect to the processor 901, and these remote memories can be connected to the electronic device according to the field-oriented interest point selection method through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0117] The electronic device according to the field-oriented interest point selection method can further include an input device 903 and an output device 904. The processor 901, the memory 902, the input device 903 and the output device 904 can be connected by a bus or other means, Figure 9 For example, by a bus connection.

[0118] The input device 903 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device according to the field-oriented interest point selection method, such as touch screen, keypad, mouse, trackpad, touchpad, pointing stick, one or more mouse buttons, trackball, joystick, etc. The output device 904 can include a display device, an auxiliary lighting device (such as an LED), a tactile feedback device (such as a vibration motor), etc. The display device can include but is not limited to a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device can be a touch screen.

[0119] Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0120] These computer programs (also known as programs, software, software applications or code) include machine instructions for the programmable processor, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0121] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0122] The systems and techniques described here can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of these, e.g., a client server. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0123] The computer system can include clients and servers. The clients and the servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0124] According to the technical scheme of the embodiment of the present application, the correlation between the selected interest point and the specified field is obtained by determining whether the sample belongs to the specified field in the case of containing the selected interest point, and calculating the probability. Whether the selected interest point is the interest point related to the specified field is determined by the correlation. The interest point related to the field can be selected without referring to the relevant knowledge of each field, and the applicability of the interest point selection is improved. Since the correlation calculation processes of each interest point are independent of each other, the scene of increasing sample size is adapted by low-cost horizontal expansion, and the correlation between the finally selected interest point and the specified field is high based on the probability-based correlation calculation method.

[0125] It should be understood that various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in different order, as long as the desired results of the technical scheme disclosed in the present application can be achieved, which is not limited herein.

[0126] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A point of interest selection method characterized by, The method comprises the following steps: selecting a target interest point from a complete set of interest points and determining a target field; obtaining a sample set comprising a plurality of samples, each sample comprising a field of origin and the target interest point; calculating a first sample probability that the field of origin of the sample is the same field as the target field, and a second sample probability that the field of origin of the sample is not the same field as the target field; obtaining a ratio of a first sample number to a second sample number according to a ratio of the first sample probability to the second sample probability; the first sample number is the number of samples whose field of origin is the same field as the target field, and the second sample number is the number of samples whose field of origin is not the same field as the target field; obtaining a correlation between the target interest point and the target field according to the ratio of the first sample number to the second sample number; obtaining interest points related to the target field according to the correlation; iterating through each interest point in the complete set of interest points, taking each interest point as a target interest point, and calculating a correlation between each target interest point and the target field by using the Bayesian principle to obtain a plurality of correlations; obtaining a set of interest points related to the target field according to the plurality of correlations; obtaining a set of user interest points related to the target field by performing an intersection operation on a set of user interest points and the set of interest points related to the target field.

2. The method of claim 1, wherein, The method for obtaining a set of interest points related to the target field according to the plurality of correlations comprises the following steps: filtering, from the plurality of correlations, a correlation greater than a correlation threshold value; determining a target interest point corresponding to the filtered correlation as an interest point related to the target field; and composing the target interest point related to the target field into the set of interest points related to the target field.

3. The method of claim 1, wherein, The method for obtaining a correlation between the target interest point and the target field according to the ratio of the first sample number to the second sample number comprises the following steps: taking the ratio of the first sample number to the second sample number as the correlation between the target interest point and the target field.

4. A point of interest selection apparatus characterized by comprising: The method comprises the following steps: a target determination module configured to select a target interest point from a complete set of interest points and determine a target field; a sample obtaining module configured to obtain a sample set comprising a plurality of samples, each sample comprising a field of origin and the target interest point; a correlation calculation module configured to calculate a first sample probability that the field of origin of the sample is the same field as the target field, and a second sample probability that the field of origin of the sample is not the same field as the target field; and obtain a ratio of a first sample number to a second sample number according to a ratio of the first sample probability to the second sample probability; the first sample number is the number of samples whose field of origin is the same field as the target field, and the second sample number is the number of samples whose field of origin is not the same field as the target field; and obtain a correlation between the target interest point and the target field according to the ratio of the first sample number to the second sample number; an interest point selection module configured to obtain interest points related to the target field according to the correlation. The interest point traversal module is configured to traverse each interest point in the interest point set, take each interest point as a target interest point, and calculate a correlation between each target interest point and the target field by using a Bayesian principle, to obtain a plurality of correlations; The interest point set obtaining module is configured to obtain a target field related interest point set according to the plurality of correlations; The intersection obtaining module is configured to obtain a target field related user interest point set by performing an intersection operation on the user interest point set and the target field related interest point set.

5. The apparatus of claim 4, wherein, The interest point set obtaining module includes: The correlation screening submodule is configured to screen, from the plurality of correlations, a correlation greater than a correlation threshold value; The field related interest point determining submodule is configured to determine a target interest point corresponding to the screened correlation as the target field related interest point; The interest point set obtaining submodule is configured to group the target field related interest points screened to obtain the target field related interest point set.

6. The apparatus of claim 4, wherein, The correlation calculating module is further configured to take a ratio of the first sample number to the second sample number as the correlation between the target interest point and the target field.

7. An electronic device, comprising: The computer program product includes: At least one processor; and A memory connected in communication with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

8. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are configured to enable the computer to perform the method of any one of claims 1-3.

Images