Information analysis method and device, electronic equipment, and storage medium

Abstract

Embodiments of the present application disclose an information analysis method, comprising: obtaining original information and extracting key information of the original information; determining a presentation parameter value of the key information in the original information, and determining a weight of the key information according to the presentation parameter value; and determining an information influence degree of the original information based on the weight of the key information, in combination with information entropy of the original information and emotional polarity of the original information. Embodiments of the present application also provide an information analysis device, an electronic device and a storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronic devices, and relates to but is not limited to an information analysis method and device, an electronic device, and a storage medium. BACKGROUND

[0002] Information analysis is an information labor process of deep thinking processing and analysis research on a large amount of related information according to the needs of a specific problem, to form new information that helps to solve the problem. In related technologies, the method for obtaining the influence degree of information through information analysis is one-sided, and the influence degree of information in different application scenarios cannot be understood. Therefore, an information analysis method that can accurately determine the influence degree of information according to multiple factors is needed. SUMMARY

[0003] The embodiments of the present application provide an information analysis method and device, an electronic device, and a storage medium.

[0004] The technical solutions of the embodiments of the present application are implemented as follows.

[0005] The embodiments of the present application provide an information analysis method, which comprises: obtaining original information and extracting key information of the original information; determining a presentation parameter value of the key information in the original information, and determining a weight of the key information according to the presentation parameter value; and determining an information influence degree of the original information based on the weight of the key information, in combination with information entropy of the original information and emotional polarity of the original information.

[0006] In an implementable manner, the presentation parameter value comprises an information expression value, and the method further comprises: determining the information expression value according to a layout parameter value of the key information; wherein factors affecting the layout parameter value at least include a position of the key information in the original information.

[0007] In an implementable manner, the presentation parameter value further comprises a perception attention value, and the method further comprises: determining the perception attention value according to a receiving matching value of the key information.

[0008] In an implementable manner, the method further comprises: obtaining corresponding original information from at least two information sources; determining a first original information in any one of the information sources, and determining a first information publishing group according to the first original information; determining a second information publishing group and a second original information in any other one of the information sources according to the first information publishing group and the first original information; determining information influence degrees of information publishing groups of the at least two information sources, and determining an information difference degree according to the information influence degrees of the at least two information sources.

[0009] In an implementable manner, the method further comprises: if the information difference degree is greater than a threshold, generating prompt information; determining the target information source and the target information publishing group according to the prompt information.

[0010] In an implementable manner, the method further comprises: predicting a third information publishing group according to the information influence degree and the newly acquired original information; and predicting information published by the information publishing group according to the information influence degree and the corresponding information publishing group.

[0011] In an implementable manner, determining the first information publishing group according to the first original information comprises: determining at least one information publishing user according to the first original information, and clustering the at least one information publishing user to obtain the first information publishing group.

[0012] Embodiments of the present application provide an information analysis device, the device comprising: an acquisition module configured to acquire original information and extract key information of the original information; a determination module configured to determine a presentation parameter value of the key information in the original information, and determine a weight of the key information according to the presentation parameter value; and determine an information influence degree of the original information based on the weight of the key information, in combination with an information entropy of the original information and a sentiment polarity of the original information.

[0013] Embodiments of the present application provide an electronic device comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor implements steps in the above method when executing the program.

[0014] Embodiments of the present application provide a computer readable storage medium, which stores a computer program capable of being executed by a processor to implement steps in the above method. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings, wherein:

[0016] Figure 1A A flowchart of an information analysis method provided by an embodiment of the present application is shown in the figure;

[0017] Figure 1B An application scenario diagram of an information analysis method provided by an embodiment of the present application is shown in the figure;

[0018] Figure 1CAn application scenario schematic diagram of an information analysis method provided by an embodiment of the present application is shown in FIG. 1.

[0019] Figure 1D An application scenario schematic diagram of an information analysis method provided by an embodiment of the present application is shown in FIG. 1.

[0020] Figure 2 An application scenario schematic diagram of an information analysis method provided by an embodiment of the present application is shown in FIG. 1.

[0021] Figure 3A An application scenario schematic diagram of an information analysis method provided by an embodiment of the present application is shown in FIG. 1.

[0022] Figure 3B An application scenario schematic diagram of an information analysis method provided by an embodiment of the present application is shown in FIG. 1.

[0023] Figure 4 An application scenario schematic diagram of an information analysis method provided by an embodiment of the present application is shown in FIG. 1. DETAILED DESCRIPTION

[0024] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application but not all embodiments of the present application. The following embodiments are used to describe the present application but not to limit the scope of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0025] In the following description, “some embodiments” are described, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0026] It should be noted that the terms “first\second\third” involved in the embodiments of the present application are only to distinguish similar objects and do not represent a specific order of the objects. It can be understood that “first\second\third” can be interchanged in a specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0027] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which embodiments of the present application belong. It should also be understood that terms such as those defined in a general dictionary should be understood to have meanings consistent with meanings in the context of the relevant art and should not be interpreted ideally or overly formally unless specifically defined as such herein.

[0028] The present application provides an information analysis method, Figure 1A A flowchart of an information analysis method provided by embodiments of the present application is shown in Figure 1A The method comprises at least the following steps:

[0029] Step S101, obtaining original information and extracting key information of the original information.

[0030] Here, the original information can at least include text, pictures, audio or video, etc. Here, the original information can be information including different information sources. Here, the different information sources can be two books in the same field, two social platforms; or a broadcast and a newspaper, a television or a book in different fields, etc. Different forms of communication including different forms of communication.

[0031] Here, the key information can include but is not limited to emotional information, object information, event description, etc., such as common information of multiple information sources, comments on the same event, object or crowd by multiple information sources. For example, in the case of two books in the same field, the key information can be a summary of the same argument in the two books; in the case of two social platforms, the key information can be the content published by the same blogger in different social platforms, or the evaluation of the same model; in the case of a broadcast, a newspaper and a television in different fields, the key information can be the description of the same event; in the case of text, the key information can be words expressing positive emotions, or evaluation scripts containing negative emotions; in the case of pictures, the key information can be patterns expressing positive emotions or positive guidance, or patterns containing negative emotions or negative effects; in the case of audio or video, the key information can be words expressing positive emotions, or tone containing negative emotions, such as the frequency of the sound.

[0032] Step S102, determining the presentation parameter value of the key information in the original information, and determining the weight of the key information according to the presentation parameter value.

[0033] In an implementable manner, the presentation parameter value comprises an information expression value, and the method further comprises: determining the information expression value according to a layout parameter value of the key information, wherein factors influencing the layout parameter value at least include a position of the key information in the original information.

[0034] Here, the presentation parameter value can further comprise influence of an information source, for example, the presentation parameter value is determined according to average daily browsing volume, like number, comment number, forwarding number, subscription number or sharing value of the information source.

[0035] Here, the layout parameter value can be dynamically adjusted according to length of the original information and position of the key information in the original information. Here, the position x of the key information in the original information and the layout parameter value y form a quadratic function relationship, for example, a monomial quadratic function, which can be expressed as: y=ax 2 +bx+c. When the position x is at the beginning or the end, the corresponding layout parameter value y is larger than that when the position x is in the middle.

[0036] Here, the function relationship formed by the position x of the key information in the original information and the layout parameter value y can also be determined by reading habits of the information receiver. For example, for the information receiver who pays attention to the beginning and the end, the layout parameter value y of the position at the beginning is larger; for the information receiver who pays attention to the whole text, the function relationship formed by the position x and the layout parameter value y can be a constant.

[0037] Exemplarily, for the information receiver who pays attention to the beginning and the end, in the case that the original information is an original text, the text information corresponding to the key information is at the beginning or the end of a paragraph in the original text, and the layout parameter value can be 10; while the text information corresponding to the key information is not at the beginning or the end of a paragraph in the original text, and the layout parameter value can be 00; obviously, the layout parameter value 10 is larger than the layout parameter value 00, which means that the layout parameter value of the key information at the beginning or the end of a paragraph in the original text is larger, and the information receiver who pays attention to the beginning and the end can pay more attention to the key information at the beginning or the end, and the influence of the key information is larger.

[0038] Here, the factors affecting the layout parameter value can also include the length of the original information, the prominence of the key information. Here, the prominence of the key information can be determined at least in one of the following ways: font size, color, and the like. Exemplarily, the layout parameter can be represented by a two-bit binary number, the high bit of the binary number is high to indicate that the length of the original information exceeds the length threshold, and the low bit is high to indicate that the color / font size of the key information is different from the text in the same line. Therefore, if the length of the original information exceeds the length threshold, the layout parameter is 10; if the font size of the key information is larger than other text content, the color of the key information is different from the color of the text in the same line, or the color of the text in the same paragraph; or the key information is marked with a preset color, for example, red; or there is highlighting, underlining, and the like, the layout parameter is 01. Exemplarily, the layout parameter value can change with the length of the original information, for example, decrease with the increase of the length of the original information.

[0039] Here, the factors affecting the layout parameter value can also include the number of repetitions of the key information in the original information. Exemplarily, in the application scenario where the original information is text information, the more the key information is repeated in the original information, the deeper the influence of the key information on the information receiver, therefore, if the number of repetitions is greater than the number threshold, the layout parameter value is 10; if the number of repetitions is less than the number threshold, the layout parameter value is 00; the layout parameter value 00 is less than the layout parameter value 10. In another example, the layout parameter value increases with the increase of the number of repetitions.

[0040] Here, the information expression value can be equal to the layout parameter value, or can include other quantitative values in addition to the layout parameter value. Determining the information expression value can be achieved by summing the layout parameter value and other quantitative values, or by weighted sum of the layout parameter value and other quantitative values. Exemplarily, the layout parameter can be represented by a two-bit binary number, the high bit of the binary number is high to indicate that the font size of the key information is larger than other text content, and the low bit is high to indicate that the color of the key information is different from the text in the same line. Therefore, in the case where the information expression value can be equal to the layout parameter value, when the font size of the key information is larger than other text content, the information expression value is determined to be 10; when the color of the key information is different from the color of the text in the same line, or the color of the text in the same paragraph, the information expression value is determined to be 01; when both of the above conditions are met, the information expression value is determined to be 11.

[0041] In another example, the weights can also be adjusted. If it is more inclined that the color of the text has a greater impact, the weight before the layout parameter value of the color of the text is increased, the sum of all weights is 1, and the weights are balanced to achieve the balance of the weights of each factor.

[0042] In an implementable manner, the presentation parameter value further comprises a perceptual attention value, and the method further comprises: determining the perceptual attention value according to the reception matching value of the key information.

[0043] Here, factors affecting the reception matching value include prominence of the key information and perceptual degree of the information receiver. Here, the receiver can receive information through visual, auditory, tactile, etc. Here, the prominence can at least include but is not limited to: data font size, text color, audio volume. The perceptual degree can at least include: the habit of receiving information by the receiver according to historical personal information receiving mode analysis. Here, the reception matching value of the information can be inferred by the prominence and the perceptual degree. Here, the object of obtaining personal information can be a virtual user, or information obtained with authorization of the user, and does not involve any privacy information.

[0044] Here, the weight of the key information can be determined according to the information expression value. Exemplarily, according to the characteristics of short texts such as e-commerce comments and social media, different weights are given to texts appearing in different positions. m represents the number of times the opinion appears in the first sentence, n represents the number of times it appears in other positions, and words represent the number of all opinions in the text. The greater the word frequency, the greater the influence of the opinion in the text, and the greater the weight of the key information.

[0045] In another example, according to the characteristics of short videos, different weights are given to the content appearing at different time points in the video. For example, the weight of the summary content at the beginning or end of the short video is greater than the weight of the descriptive content appearing in the middle of the video.

[0046] Step S103, based on the weight of the key information, the information entropy of the original information and the sentiment polarity of the original information are combined to determine the information influence degree of the original information.

[0047] Here, the information entropy of the original information can include text information entropy or information entropy of other propagation forms corresponding to the propagation information of the video. Here, the information entropy is used to measure the information amount and richness of the information. The greater the negative text information entropy, the more the user uses rich words to describe and express dissatisfaction, and the greater the adverse impact.

[0048] Here, the sentiment polarity of the original information can be a negative probability, a positive probability or a neutral probability of the text. The probability that the text belongs to the positive, neutral or negative category reflects the sentiment polarity of the text. The greater the negative probability, the stronger the negative degree of the text, and the greater the impact.

[0049] In an implementable manner, the information influence degree can be determined by the product of the weight of the key information, the information entropy of the original information, and the sentiment polarity of the original information. Exemplarily, the information influence degree I of the key information x in the user group text can be obtained by formula (1-1):

[0050] I =∑ x∈用户群组文本 H(x) * K(x) * E(x) formula (1-1);

[0051] wherein K(x) is the weight of the key information, H(x) is the text information entropy, and E(x) is the negative probability of the text.

[0052] Exemplarily, the influence degree of a certain opinion in the e-commerce group and the corresponding media group is calculated, and the influence degree is evaluated according to the text information entropy, the weight of the key information, and the sentiment polarity. Wherein, the text information entropy H(x) is determined according to formula (1-2), the weight of the key information K(x) is determined according to formula (1-3), and the sentiment polarity E(x) is determined according to formula (1-4). The product of the three can evaluate the information influence degree of a certain opinion in a certain text.

[0053]

[0054]

[0055] E(x) = p(emotion = -1) formula (1-4);

[0056] wherein p(x i ) is the probability of the opinion belonging to the negative opinion according to the word frequency, m is the number of times the opinion appears in the first sentence, n is the number of times the opinion appears in other positions, and words is the number of all opinions in the text. p(emotion = -1) is the probability of the opinion belonging to the negative opinion according to the sentiment polarity.

[0057] Exemplarily, as shown in Figure 1B , product a, product b and product c for the review information text 11 of the information source of the e-commerce platform and the review information text 12 of the information source of the social media software: wherein product a, product b and product c are used for example, and the information analysis method involved in the present application can be applied to various product and various username information analysis scenarios.

[0058] Text 11: Received the computer for five days, and it works well so far. The heat is a little serious, and there is no other major flaw. It is said that many of this model have been turned over. At present, it is safe to get off the car. Continue to observe. According to the negative comments "heat" and "serious" and formula (1-1) to formula (1-4), the information influence degree is determined: H (1) = 7.5; K (1) = 1; E(1) = 0.4; information impact degree = H (2) *K (2) *E (2) = 3.

[0059] Text 12: The heating is serious, the key is to send the office that can not be activated at all, and deliberately set the difficulty for others to let you not activate …… According to the negative comments "serious heating" and "office can not be activated" and formulas (1-1) to (1-4) to determine the information impact degree: H (1) = 6.7; K (1) = 0.5; E (1) = 1; impact degree = H (2) *K (2) *E (2) = 3.35. Calculate all (x) values: I 电商 = 23.2; media matching text (x) value I 媒体 = 1.2.

[0060] Here, the factors of the information impact degree can also include the information parameter value of the original information and the data volume parameter value of the original information. Among them, the information parameter value can be determined according to the information volume, the release time and other factors of the original information; the data volume parameter can be determined according to the information browsing volume, the fan activity degree of the publisher and other factors. Exemplarily, in the case of including information parameter value P(x) and data volume parameter value Q(x), the information impact degree I of the key information x in the user group text can be obtained by formula (1-5):

[0061] I = ∑ x∈用户群组文本 H(x)*K(x)*E(x)*P(x)*Q(x) formula (1-5);

[0062] Wherein, K(x) is the weight of the key information, H(x) is the text information entropy, E(x) is the negative probability of the text, P(x) is the information parameter value, and Q(x) is the data volume parameter value.

[0063] In the above embodiment, a presentation parameter value of the key information in the original information is determined, and a weight of the key information is determined according to the presentation parameter value; and based on the weight of the key information, the information influence degree of the original information is determined by combining the information entropy of the original information and the sentiment polarity of the original information. In this way, the relationship between various factors and the information influence degree can be considered, and the influencing factors can be quantified, and the information influence degree can be accurately determined from multiple aspects, thereby improving the accuracy of the determined information influence degree. In this way, it is beneficial to pay attention to the key information with a high information influence degree in a timely manner, and in the case that the key information with a high information influence degree includes negative information, the spread and propagation of the negative information are reduced; and in the case that the key information with a high information influence degree includes positive information, the propagation of the key information is facilitated, so as to expand the influence of the positive information.

[0064] In an implementable manner, the method further includes:

[0065] Step S104, obtaining corresponding original information from at least two information sources.

[0066] Here, the information sources can include, but are not limited to, the following two kinds: social media software, shopping software, books and journals, and audio and video websites.

[0067] Here, the corresponding original information is information related to the same subject in different information sources. For example, the obtained corresponding information can be information of the same product or the same event. For example, information about the use experience of a notebook computer of the same brand in social media software and shopping software. In another example, the corresponding original information can be videos, texts or pictures published by a media person on different platforms.

[0068] Step S105, determining a first original information in any one of the information sources, and determining a first information publishing group according to the first original information.

[0069] Here, the publishing group can be a user group composed of publishing users of multiple original information.

[0070] For example, two comment information used for information difference degree analysis is determined in the shopping software, and a user group composed of publishing users is determined according to the comment information.

[0071] In an implementable manner, the determining of the first information publishing group according to the first original information includes: determining at least one information publishing user according to the first original information, and clustering the at least one information publishing user to obtain the first information publishing group.

[0072] Here, at least one information publishing user can be clustered according to product keywords and event keywords. For example, three pieces of comment information including the notebook keyword are clustered into one category; four pieces of comment information including the notebook heat dissipation keyword are clustered into one category.

[0073] For example, the comment information in different information sources is analyzed in real time by using the opinion extraction and sentiment analysis technology, the key information is extracted from the original information, and the comment information is clustered according to the key information, so as to form publishing groups holding different opinions. For the publishing group holding negative opinions, the information difference degree is defined to monitor the negative opinions in the social media software, so as to avoid causing more extensive and severe influence. Here, the media group corresponding to the e-commerce group can be defined by using the nickname + mentioned product. When the publishing user name corresponding to the e-commerce comment and the media text can be matched and the text mentions the same product, it is considered to be the same publishing user. As shown in the following table, the two nicknames are completely matched at the beginning and end, and the same product 101: AAA is mentioned, so it can be determined to be the same publishing user. By using this method, all publishing users corresponding to the publishing group can be matched. Figure 1D

[0074] Step S106, determining a second information publishing group and second original information in any one of the other information sources according to the first information publishing group and the first original information.

[0075] Here, the first original information and the second original information are at least one of the original information in the plurality of original information. For example, it can be at least one piece of comment information in the shopping software, or at least one piece of short text in the social media software.

[0076] In one implementation mode, the second information publishing group and the second original information in any one of the other information sources are determined according to the first information publishing group and the first original information, including: determining the second information publishing group according to the first information publishing group and the first original information; and determining the second original information based on the second information publishing group.

[0077] In another implementation mode, the second information publishing group and the second original information in any one of the other information sources are determined according to the first information publishing group and the first original information, including: determining the second information publishing group according to the first information publishing group; and determining the second original information according to the first original information.

[0078] Step S107, determining the information influence degree of the information publishing group of at least two information sources, and determining the information difference degree according to the information influence degree of at least two information sources.

[0079] ​Here, the information dissimilarity is used to assess the degree of dissimilarity of information across various information sources, that is, the degree of influence of comments on the public.

[0080] In one feasible approach, the information difference between at least two information sources can be determined by determining the ratio or difference of the information influence of any two information sources.

[0081] For example, the information difference F between comment information from two information sources, social media software and shopping software, can be determined using formulas (1-6).

[0082]

[0083] Among them, I 社交媒体软件 The informational impact of social media software; I 购物软件 The impact of information on shopping apps.

[0084] For example, such as Figure 1B As shown, the impact of e-commerce information: I 电商 =23.2; Media Information Impact I 媒体 =1.2, resulting in an information dissimilarity factor F = 5%. For example... Figure 1C As shown, the information dissimilarity of opinion 13 regarding severe fever is 5%.

[0085] In one feasible approach, the information difference between at least two information sources can be determined by determining the ratio of the information influence between any two information sources, wherein the methods for determining the ratio of the information influence between each pair of information sources and the information difference are as shown in formulas (1-1) to (1-6).

[0086] In the above embodiments, the information influence of information publishing groups from at least two information sources is determined, and the information difference is determined based on the information influence of the at least two information sources. This allows for the quantification of influencing factors and accurate determination of information difference from multiple perspectives. Based on the information difference, a prompt message is generated to remind relevant personnel to pay attention to information sources and original information content with high information difference. If it is negative news, its spread can be suppressed; if it is positive news, its influence can be amplified.

[0087] In one possible implementation, the method further includes: generating a prompt message if the information difference is greater than a threshold; and determining the target information source and the target information publishing group based on the prompt message.

[0088] Here, the prompt message may include: the target information and the target information posting group. For example, when the information difference is greater than or equal to 5%, a prompt message is generated to indicate that the information source with the large information difference belongs to social media software and shopping software.

[0089] In an implementable manner, the target information source can be determined according to the prompt information. Here, the influence degree of the information source with the information difference degree greater than the threshold value is determined according to the prompt information, and the target information source of the prompt information is obtained by comparing the influence degree with the influence degree of each information source.

[0090] In another implementable manner, the target information publishing group can be determined according to the prompt information. Here, the publishing user can be included in the prompt information, and the target information publishing group is determined according to the publishing user.

[0091] The present application provides an information analysis method, Figure 2 The flowchart of the information analysis method provided by the embodiment of the present application is shown in Figure 2 The method at least includes the following steps:

[0092] Step S201, obtaining original information and extracting key information of the original information.

[0093] Step S202, determining the presentation parameter value of the key information in the original information, and determining the weight of the key information according to the presentation parameter value.

[0094] Step S203, determining the information influence degree of the original information based on the weight of the key information, combining the information entropy of the original information and the emotional polarity of the original information.

[0095] Step S204, predicting a third information publishing group according to the information influence degree and newly obtained original information.

[0096] Here, the newly obtained original information can include opinion information or product information.

[0097] Step S205, predicting the information published by the information publishing group according to the information influence degree and the corresponding information publishing group.

[0098] Illustratively, the comment information with fever is obtained, the information influence degree of the comment information with fever in the group is determined, and then the new opinion information or product information is obtained, and it is confirmed which group the new opinion information or product information is sent from.

[0099] In the above embodiment, the third information publishing group is predicted according to the information influence degree and the newly obtained original information, and the information published by the information publishing group is predicted according to the information influence degree and the corresponding information publishing group. In this way, the information influence degree accurately determined according to various quantitative factors accurately predicts the information published by other groups, so that the negative information can be processed before the influence degree is expanded, reducing the spread and propagation of negative information; for positive information, the information propagation amount can be expanded, and the propagation and diffusion rate of positive information can be improved.​​

[0100] The above embodiment is further described with the original information as the original text, the key information as the opinion and the keyword as an example. Generally, the user will first publish the use experience, shopping experience and the like in different information sources after purchasing the product. If extremely dissatisfied situation occurs, the user will further publish the opinion in the social media software, that is, the negative evaluation in different information sources has a certain possibility to spread, thereby causing more extensive adverse influence. In order to timely monitor the influence degree and thus make good early warning and processing, the information difference degree needs to be measured. Figure 3A The information analysis method provided in the application comprises:

[0101] Step S301, discovering the negative key information;

[0102] Step S302, circumscribing the user mentioning the negative key information in the shopping software (e-commerce) comment information;

[0103] Step S303, matching the user of the social media software;

[0104] Step S304, extracting the original text, and calculating the influence degree score according to the text information entropy, opinion keyword frequency and sentiment polarity;

[0105] Step S305, extracting the original text, and calculating the influence degree score according to the text information entropy, opinion keyword frequency and sentiment polarity;

[0106] Step S306, calculating the information difference degree based on the e-commerce user group according to the influence degrees of the two.

[0107] In the above embodiment, the user nickname and the product mentioning are used to match the publishing user group of the social media software corresponding to the user group of the e-commerce comment, and then the information difference degree of the negative opinion is calculated according to the text features of the publishing user group, the prompt information is generated, and the spread and transmission of the negative opinion are reduced.

[0108] Based on the foregoing embodiment, the embodiment of the application further provides an information analysis device, which comprises various modules and can be realized by a processor in an electronic device. Of course, it can also be realized by a specific logic circuit. In the implementation process, the processor can be a central processing unit (CPU), a micro processing unit (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA).

[0109] Figure 3B A schematic diagram of a component structure of an information analysis device provided by an embodiment of the present application is shown in Figure 3B The device 300 includes an acquisition module 301 and a determination module 302, wherein:

[0110] The acquisition module 301 is configured to acquire original information and extract key information of the original information.

[0111] The determination module 302 is configured to determine a presentation parameter value of the key information in the original information, and determine a weight of the key information according to the presentation parameter value; and determine an information influence degree of the original information based on the weight of the key information, in combination with information entropy of the original information and emotional polarity of the original information.

[0112] In an implementable manner, the presentation parameter value includes an information expression value, and the determination module 302 is further configured to determine the information expression value according to a layout parameter value of the key information; wherein factors affecting the layout parameter value at least include a position of the key information in the original information.

[0113] In an implementable manner, the presentation parameter value further includes a perception attention value, and the determination module 302 is further configured to determine the perception attention value according to a reception matching value of the key information.

[0114] In an implementable manner, the acquisition module 301 is further configured to acquire corresponding original information from at least two information sources; and the determination module 302 is further configured to determine a first original information in any one of the information sources, determine a first information publishing group according to the first original information, determine a second information publishing group and a second original information in any other one of the information sources according to the first information publishing group and the first original information, determine information influence degrees of information publishing groups of the at least two information sources, and determine an information difference degree according to the information influence degrees of the at least two information sources.

[0115] In an implementable manner, the device 300 further includes a prompt module configured to generate prompt information if the information difference degree is greater than a threshold value; and the determination module 302 is further configured to determine a target information source and a target information publishing group according to the prompt information.

[0116] In an implementable manner, the method further includes that the device 300 further includes a prediction module configured to predict a third information publishing group according to the information influence degree and newly acquired original information, and predict information published by an information publishing group according to the information influence degree and the information publishing group.

[0117] In an implementable manner, the determining module 302 is further configured to determine at least one information publishing user according to the first original information, and cluster the at least one information publishing user to obtain a first information publishing group.

[0118] It should be noted that the above description of the device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects to the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application.

[0119] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a plurality of instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read only memory (ROM), a magnetic disk or an optical disk, and various media that can store program codes. Thus, the embodiments of the present application are not limited to any specific hardware and software combination.

[0120] Correspondingly, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps in any of the methods described in the above embodiments.

[0121] Correspondingly, the embodiments of the present application also provide a chip, which includes a programmable logic circuit and / or program instructions, and when the chip is running, it is used to implement the steps in any of the methods described in the above embodiments.

[0122] Correspondingly, the embodiments of the present application also provide a computer program product, which is executed by a processor of an electronic device to implement the steps in any of the methods described in the above embodiments.

[0123] Based on the same technical concept, the embodiments of the present application provide an electronic device for implementing the information analysis method described in the above method embodiments. Figure 4 A hardware entity diagram of an electronic device provided by the embodiments of the present application is shown in FIG. 4, which includes a memory 410 and a processor 420. The memory 410 stores a computer program that can be run on the processor 420. When the processor 420 executes the program, it implements the steps in any of the methods described in the embodiments of the present application. Figure 4 ​

[0124] The memory 410 is configured to store instructions and applications executable by the processor 420, and can also cache data (e.g., image data, audio data, voice communication data, and video communication data) to be processed by the processor 420 and modules in the electronic device, or data processed by the processor 420 and the modules. The memory 410 can be implemented by a FLASH or a Random Access Memory (RAM).

[0125] The processor 420 implements the steps of any of the information analysis methods described above when executing a program. The processor 420 generally controls the overall operation of the electronic device 400.

[0126] The processor described above can be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, or a microprocessor. It can be understood that the electronic device implementing the functions of the processor described above can also be other electronic devices, and the embodiments of the present application are not limited in this respect.

[0127] The computer storage medium / memory can be a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Ferromagnetic Random Access Memory (FRAM), a Flash Memory, a magnetic surface storage, an optical disc, a Compact Disc Read-Only Memory (CD-ROM), or the like memory; or can be various electronic devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, and the like.

[0128] It should be noted that the above description of the storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0129] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that the size of the sequence number of each process in various embodiments of the present application does not mean the execution order, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The sequence number of the above embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0130] It should be noted that, in the present document, the terms "comprising", "containing", or any other similar term are intended to encompass non-exclusive inclusions, such that a process, method, article, or apparatus that comprises a list of elements does not necessarily include those elements only, but can include other elements not expressly listed, or can include elements inherent in such process, method, article, or apparatus. Without more limitations, an element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0131] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative, for example, the division of the units is only a logical functional division, and actual implementation can have another division manner, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0133] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0134] Alternatively, the integrated unit of the present application, if implemented in the form of a software function module and sold or used as an independent product, can also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing an apparatus to perform all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes: mobile storage devices, ROM, magnetic or optical disks, and various other media that can store program codes.

[0135] The methods disclosed in the several method embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments.

[0136] The features disclosed in the several method or device embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments or device embodiments.

[0137] The above merely provides the implementation manners of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An information analysis method, comprising: obtaining original information and extracting key information of the original information; determining a presentation parameter value of the key information in the original information, and determining a weight of the key information according to the presentation parameter value; determining an information influence degree of the original information based on the weight of the key information, in combination with information entropy of the original information and sentiment polarity of the original information; predicting a third information publishing group according to the information influence degree and newly obtained original information; and predicting information published by the information publishing group according to the information influence degree and the corresponding information publishing group. 2.The method of claim 1, wherein the presentation parameter value comprises an information expression value, and the method further comprises: determining the information expression value according to a layout parameter value of the key information; and wherein factors affecting the layout parameter value include at least a position of the key information in the original information. 3.The method of claim 2, wherein the presentation parameter value further comprises a perceived attention value, and the method further comprises: determining the perceived attention value according to a reception matching value of the key information. 4.The method of claim 1, further comprising: obtaining corresponding original information from at least two information sources; determining a first original information in any one of the information sources, and determining a first information publishing group according to the first original information; determining a second information publishing group and a second original information in any other one of the information sources according to the first information publishing group and the first original information; determining an information influence degree of the information publishing groups of the at least two information sources, and determining an information difference degree according to the information influence degrees of the at least two information sources. 5.The method of claim 4, further comprising: generating a prompt information if the information difference degree is greater than a threshold value; and determining a target information source and a target information publishing group according to the prompt information. 6.The method of claim 4, wherein determining a first information publishing group according to the first original information comprises: determining at least one information publishing user according to the first original information, and clustering the at least one information publishing user to obtain the first information publishing group. 7.An information analysis device, comprising: an obtaining module configured to obtain original information and extract key information of the original information; a determining module configured to determine a presentation parameter value of the key information in the original information, and determine a weight of the key information according to the presentation parameter value; determine an information influence degree of the original information based on the weight of the key information, in combination with information entropy of the original information and sentiment polarity of the original information; a predicting device configured to predict a third information publishing group according to the information influence degree and newly obtained original information; and predict information published by the information publishing group according to the information influence degree and the corresponding information publishing group. The processor implements the steps in the method of any one of claims 1 to 6 when executing the program. The computer program implements the steps in the method of any one of claims 1 to 6 when executed by the processor.

8. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, ​ 9. A computer readable storage medium having stored thereon a computer program, characterized in that, ​

Images