Information evaluation method and system and electronic equipment

Abstract

The invention discloses an information evaluation method and system and electronic equipment, and the method comprises the steps: pre-storing a fact list of a plurality of entity objects with confidence higher than a target threshold value, and when to-be-evaluated information needs to be evaluated, firstly determining a target entity object in the to-be-evaluated information, then determining a fact list of the target entity object from pre-stored fact lists of a plurality of entity objects according to the target entity object, and comparing the to-be-evaluated information with the fact list of the target entity object in different dimensions, thereby determining comparison results of different dimensions, and further obtaining an evaluation result of the to-be-evaluated information. Therefore, the to-be-assessed information is assessed based on the pre-stored information with the confidence higher than the target threshold, the authenticity of the to-be-assessed information is assessed, and the problem that other users are affected due to the fact that the authenticity of the to-be-assessed information is unknown is avoided.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an information evaluation method, system and electronic device. Background Technology

[0002] There is a lot of travel-related content posted by users on various social media platforms. This content is usually posted by users during or after their trip.

[0003] For example, if User A posts on a social media platform about the high ticket prices at attraction B, and User C sees this post, User C will also get the impression that attraction B's tickets are expensive. However, the veracity of User A's post is unverified. If the veracity of User A's post is low, it may affect User C's travel plans for attraction B. Summary of the Invention

[0004] In view of this, this application provides an information evaluation method, system, and electronic device, the specific solutions of which are as follows:

[0005] An information assessment method, comprising:

[0006] Obtain the information to be evaluated;

[0007] The information to be evaluated is analyzed to determine the target entity object in the information to be evaluated;

[0008] The fact list of the target entity object is determined from a pre-stored fact list of multiple entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold.

[0009] The information to be evaluated is compared with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions;

[0010] The evaluation result of the information to be evaluated is determined based on the comparison results of the different dimensions.

[0011] Furthermore, it also includes:

[0012] Obtain multiple pre-stored contents from a resource pool, wherein the confidence level of each pre-stored content in the resource pool is higher than a target threshold;

[0013] Each of the pre-stored contents is analyzed to determine at least one entity object corresponding to each of the pre-stored contents and the description information of each entity object;

[0014] A fact list of multiple entity objects is formed by using at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object.

[0015] Furthermore, the step of forming a fact list of multiple entity objects using at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object includes:

[0016] Integrate at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object to obtain multiple description information corresponding to each entity object in the multiple entity objects;

[0017] The multiple descriptive information corresponding to each entity object is split into different types to obtain different types of descriptive information for each entity object;

[0018] The description information of each entity object of different types is arranged according to different types to obtain the fact list of each entity object.

[0019] Furthermore, the step of comparing the information to be evaluated with the fact list of the target entity object across different dimensions to obtain comparison results across different dimensions includes:

[0020] The information to be evaluated is compared with each descriptive information in the fact list of the target entity object to determine the comparison results of the information to be evaluated with each descriptive information in different dimensions.

[0021] Furthermore, determining the evaluation result of the information to be evaluated based on the comparison results of the different dimensions includes:

[0022] Determine the weighting coefficients for different dimensions;

[0023] The comparison results of the different dimensions are weighted and summed according to the corresponding weight coefficients to obtain the evaluation result of the information to be evaluated.

[0024] Furthermore, the step of comparing the information to be evaluated with the fact list of the target entity object across different dimensions to obtain comparison results across different dimensions includes:

[0025] Based on the information to be evaluated, at least one target type description information is determined from the pre-stored fact list of the target entity object, wherein the target type is a type that matches the information to be evaluated;

[0026] The information to be evaluated is compared with the description information of at least one target type in different dimensions to obtain comparison results in different dimensions.

[0027] Furthermore, obtaining the information to be evaluated includes at least one of the following:

[0028] Obtain the link information in the evaluation request, and obtain the information to be evaluated through the link information;

[0029] Obtain the image from the evaluation request, and analyze the image to determine the information to be evaluated;

[0030] Obtain the information to be evaluated from the evaluation request.

[0031] An information evaluation system, comprising:

[0032] The acquisition unit is used to acquire the information to be evaluated.

[0033] An analysis unit is used to analyze the information to be evaluated and determine the target entity object in the information to be evaluated;

[0034] The first determining unit is configured to determine the fact list of the target entity object from a pre-stored fact list of multiple entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than a target threshold.

[0035] The comparison unit is used to compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions.

[0036] The second determining unit is used to determine the evaluation result of the information to be evaluated based on the comparison results of the different dimensions.

[0037] An electronic device, comprising:

[0038] A processor is configured to: obtain information to be evaluated; analyze the information to be evaluated to determine a target entity object within the information; determine a fact list of the target entity object from a pre-stored fact list of multiple entity objects, wherein the fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than a target threshold; compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions; and determine the evaluation result of the information to be evaluated based on the comparison results in different dimensions.

[0039] The memory is used to store the programs required by the processor to perform the above-described processing.

[0040] A readable storage medium for storing at least one set of instructions;

[0041] The instruction set is used to be invoked and to execute at least the information evaluation method described in any of the preceding items.

[0042] As can be seen from the above technical solutions, the information evaluation method, system, and electronic device disclosed in this application obtain information to be evaluated; analyze the information to be evaluated to determine the target entity object in the information to be evaluated; determine the fact list of the target entity object from a pre-stored fact list of multiple entity objects, wherein the fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold; compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions; and determine the evaluation result of the information to be evaluated based on the comparison results in different dimensions. This solution pre-stores a fact list of multiple entity objects with confidence levels higher than a target threshold. When evaluating information to be evaluated, the target entity object in the information to be evaluated is first identified. Then, the fact list of the target entity object is determined from the pre-stored fact list of multiple entity objects according to the target entity object. The information to be evaluated is compared with the fact list of the target entity object on different dimensions to determine the comparison results of different dimensions. The evaluation result of the information to be evaluated is then obtained. This achieves the evaluation of information to be evaluated based on pre-stored information with confidence levels higher than the target threshold, thus realizing the evaluation of the authenticity of the information to be evaluated and avoiding the problem of unclear authenticity of the information to be evaluated affecting other users. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of an information evaluation method disclosed in an embodiment of this application;

[0045] Figure 2 This is a flowchart of an information evaluation method disclosed in an embodiment of this application;

[0046] Figure 3 This is a flowchart of an information evaluation method disclosed in an embodiment of this application;

[0047] Figure 4 This is a flowchart of an information evaluation method disclosed in an embodiment of this application;

[0048] Figure 5This is a schematic diagram of the structure of an information evaluation system disclosed in an embodiment of this application;

[0049] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0050] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0051] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0052] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0053] This application discloses an information evaluation method, the flowchart of which is shown below. Figure 1 As shown, it includes:

[0054] Step S11: Obtain the information to be evaluated;

[0055] Step S12: Analyze the information to be evaluated and determine the target entity objects in the information to be evaluated;

[0056] Step S13: Determine the fact list of the target entity object from the fact lists of multiple pre-stored entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object. The confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold.

[0057] Step S14: Compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain the comparison results in different dimensions;

[0058] Step S15: Determine the evaluation result of the information to be evaluated based on the comparison results of different dimensions.

[0059] There is a lot of travel-related content posted by users on various social media platforms. This content is usually posted by users during or after their trip.

[0060] For example, if User A posts on a social media platform about the high ticket prices at attraction B, and User C sees this post, User C will also get the impression that attraction B's tickets are expensive. However, the veracity of User A's post is unverified. If the veracity of User A's post is low, it may affect User C's travel plans for attraction B.

[0061] Based on this, this solution discloses a method for evaluating the authenticity of information to be evaluated. When it is determined that the authenticity of certain information needs to be evaluated, the target entity object in the information to be evaluated can be identified, and the fact list of the target entity object in a pre-stored fact list of multiple entity objects can be identified. The information to be evaluated is compared with the fact list of the target entity object to finally determine the evaluation result of the information to be evaluated. By evaluating the information to be evaluated using the fact list of entity objects with a confidence level higher than the target threshold, the accuracy of the evaluation result is guaranteed, and the problem of doubts about the authenticity of unevaluated information, which could affect users who see the information, is avoided.

[0062] The information evaluation method disclosed in this embodiment is applied to an information evaluation system.

[0063] When information needs to be evaluated, the system obtains the information to be evaluated and analyzes it. This information may be a descriptive text of an address or attraction. The system evaluates this information primarily to determine its authenticity. For example, if the information to be evaluated is "Attraction A is very small and can be visited in half an hour," the system evaluates the authenticity of this statement. That is, it assesses whether attraction A is truly small and can be visited in half an hour. Only when the authenticity of this statement is guaranteed can it provide a basis for other users' travel planning.

[0064] The system analyzes the information to be evaluated to determine the target entities within that information. Specifically, it identifies which entities are mentioned in the information. For example, if the information states, "Attraction A is very small; you can see it in half an hour," then the target entity is attraction A. Similarly, if the information states, "The Ferris wheel at XX amusement park is very crowded; you have to wait in line for two hours," then the target entity is the Ferris wheel at XX amusement park.

[0065] In addition, the target entity object in the information to be evaluated can be one or multiple, without specific limitations.

[0066] A fact list of multiple entity objects is pre-stored, meaning descriptive information for multiple entity objects is pre-stored. Each entity object may correspond to multiple descriptive information sets. These multiple descriptive information sets are used to form a fact list for each entity object. When there are multiple entity objects, multiple fact lists exist. Furthermore, if the confidence level of the pre-stored descriptive information for these entity objects is higher than a target threshold, then the pre-stored information can be identified as high-confidence information, i.e., information that is truthful and reliable.

[0067] For example, the pre-stored description information of attraction b may include: dining options at attraction b, prices inside attraction b, and hygiene conditions inside attraction b; the pre-stored description information of attraction b may also include: descriptions of attraction b according to different seasons or time periods, descriptions of attraction b according to different moods, and descriptions of different locations within attraction b, etc.

[0068] Using pre-stored high-confidence information (i.e., a pre-stored list of facts about multiple entity objects) as the standard for evaluating the information to be evaluated ensures the accuracy of the evaluation and avoids large evaluation errors.

[0069] After identifying the target entity in the information to be evaluated, a fact list of the target entity is determined from a pre-stored fact list of multiple entity pairs. The information to be evaluated is then directly compared with the fact list of the target entity to obtain the comparison result, thereby determining the evaluation result of the information to be evaluated.

[0070] In this process, when comparing the information to be evaluated with the fact list of the target entity, comparisons can be made from different dimensions to obtain comparison results from different dimensions. Then, the comparison results from multiple different dimensions are combined to obtain the evaluation result of the information to be evaluated.

[0071] The different dimensions can be: time dimension, location dimension, description similarity dimension, etc. When the comparison result between the information to be evaluated and a certain description of the target entity object in the time dimension shows a high similarity, the comparison result between the information to be evaluated and the description in the location dimension shows a high similarity, and the comparison result between the information to be evaluated and the description in the description similarity dimension also shows a high similarity, then the authenticity of the information to be evaluated can be determined to be high, thereby determining the evaluation result of the information to be evaluated; or, if the comparison result between the information to be evaluated and any description of the target entity object in the description similarity dimension shows a low similarity, then the authenticity of the information to be evaluated can be determined to be low, thereby determining the evaluation result of the information to be evaluated.

[0072] This embodiment discloses an information evaluation method that obtains information to be evaluated; analyzes the information to be evaluated to determine the target entity object within the information; determines the fact list of the target entity object from a pre-stored fact list of multiple entity objects, where the fact list includes descriptive information of the entity object in different dimensions, and the confidence level of the descriptive information in the fact list of the entity object is higher than a target threshold; compares the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions; and determines the evaluation result of the information to be evaluated based on the comparison results in different dimensions. In this scheme, a fact list of multiple entity objects with confidence levels higher than the target threshold is pre-stored. When it is necessary to evaluate the information to be evaluated, the target entity object in the information to be evaluated is first determined. Then, according to the target entity object, the fact list of the target entity object is determined from the pre-stored fact list of multiple entity objects, and the information to be evaluated is compared with the fact list of the target entity object in different dimensions to determine the comparison results in different dimensions, and further obtains the evaluation result of the information to be evaluated. This achieves the evaluation of the information to be evaluated based on pre-stored information with confidence levels higher than the target threshold, realizing the evaluation of the authenticity of the information to be evaluated and avoiding the problem of unclear authenticity of the information to be evaluated affecting other users.

[0073] This embodiment discloses an information evaluation method, the flowchart of which is shown below. Figure 2 As shown, it includes:

[0074] Step S21: Obtain multiple pre-stored contents in the resource pool, where the confidence level of each pre-stored content in the resource pool is higher than the target threshold;

[0075] Step S22: Analyze each pre-stored content to determine at least one entity object corresponding to each pre-stored content and the description information of each entity object;

[0076] Step S23: Use at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object to form a fact list of multiple entity objects;

[0077] Step S24: Obtain the information to be evaluated;

[0078] Step S25: Analyze the information to be evaluated and determine the target entity objects in the information to be evaluated;

[0079] Step S26: Determine the fact list of the target entity object from the fact list of multiple pre-stored entity objects;

[0080] Step S27: Compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain the comparison results in different dimensions;

[0081] Step S28: Determine the evaluation result of the information to be evaluated based on the comparison results of different dimensions.

[0082] When it is necessary to evaluate the information to be evaluated, the target entity object in the information to be evaluated can be identified, and the fact list of the target entity object can be determined from the fact list of multiple entity objects stored in advance. The information to be evaluated is compared with the fact list of the target entity object in different dimensions to obtain the comparison results of different dimensions, so as to determine the evaluation result of the information to be evaluated, thereby realizing the evaluation of the authenticity of the information to be evaluated and ensuring the accuracy of the evaluation.

[0083] To ensure the accuracy of the assessment, it is necessary to ensure the authenticity of the data compared with the information to be assessed, that is, to verify the authenticity of the fact list of multiple pre-stored entity objects.

[0084] A pre-stored fact list of multiple entity objects can be determined based on information in a resource pool. The resource pool contains multiple pre-stored contents, and the confidence level of each pre-stored content in the resource pool is higher than the target threshold.

[0085] The pre-stored content in the resource pool can be either: information can be placed into the resource pool as long as its confidence level is higher than the target threshold, or information that is clearly determined to be true can be placed into the resource pool.

[0086] Each pre-stored content in the resource pool is analyzed to determine at least one entity object corresponding to each pre-stored content and the descriptive information for each entity object. The entity objects corresponding to all pre-stored content are determined, and the same entity objects corresponding to different pre-stored content are merged to obtain all the descriptive information corresponding to each entity object. This constructs a fact list for each entity object, thereby obtaining a fact list of multiple entity objects, which is then stored.

[0087] Before analyzing each pre-stored content in the resource pool, each pre-stored content can be pre-processed, such as removing irrelevant information and standardizing the format, to improve the processing efficiency of the pre-stored content.

[0088] When information needs to be evaluated, the fact list of the target entity is retrieved from the fact list of multiple entity objects stored in the database to facilitate the evaluation of the information to be evaluated. Since the confidence level of the fact list of the target entity is higher than the target threshold, the authenticity of the fact list of the target entity is reliable. Therefore, the accuracy of the evaluation result of the information to be evaluated based on the fact list of the target entity is also high.

[0089] Furthermore, by utilizing at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object to form a fact list of multiple entity objects, the specific steps can be as follows:

[0090] Integrate at least one entity object corresponding to each pre-stored content in multiple pre-stored contents and the description information of each entity object to obtain multiple description information corresponding to each entity object in multiple entity objects; split the multiple description information corresponding to each entity object according to different types to obtain different types of description information for each entity object; arrange the different types of description information for each entity object according to different types to obtain a fact list for each entity object.

[0091] After determining at least one entity object corresponding to each pre-stored content and the description information of each entity object, the entity objects corresponding to all pre-stored content and the description information of the entity objects can be integrated to obtain all the description information corresponding to each entity object in all pre-stored content.

[0092] When obtaining the fact list for each entity object based on all the descriptive information corresponding to each entity object, it can be arranged according to different types so that when evaluating the information to be evaluated, it can be evaluated according to the different types of descriptive information corresponding to the target entity object.

[0093] The process involves arranging information according to different types. First, all descriptive information corresponding to each entity object is classified to determine the type of each descriptive information for each entity object. Then, descriptive information of the same type among multiple descriptive information corresponding to each entity object is arranged sequentially, and descriptive information of different types among multiple descriptive information corresponding to each entity object is arranged separately to obtain a fact list of each entity object arranged according to different types.

[0094] Arrange the fact list for each entity object according to different types, such as time, event, etc.

[0095] For example: determine the description information of scenic spot 'a' in all pre-stored content, arrange the seasonal description information of scenic spot 'a' together, arrange the description information related to spring together, arrange the description information related to summer together, arrange the description information related to autumn together, and arrange the description information related to winter together; or, arrange the description information related to food together, arrange the description information related to photography together, etc.

[0096] The information evaluation method disclosed in this embodiment first obtains multiple pre-stored contents in a resource pool. The confidence level of each pre-stored content in the resource pool is higher than a target threshold. Each pre-stored content is analyzed to determine at least one entity object corresponding to each pre-stored content and the description information of each entity object. Based on this, a fact list of multiple entity objects is obtained so that when it is necessary to evaluate the information to be evaluated, the information to be evaluated can be evaluated based on the fact list of multiple entity objects to ensure the accuracy of the evaluation results.

[0097] This embodiment discloses an information evaluation method, the flowchart of which is shown below. Figure 3 As shown, it includes:

[0098] Step S31: Obtain the information to be evaluated;

[0099] Step S32: Analyze the information to be evaluated and determine the target entity objects in the information to be evaluated;

[0100] Step S33: Determine the fact list of the target entity object from the fact lists of multiple pre-stored entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object. The confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold.

[0101] Step S34: Compare the information to be evaluated with each descriptive information in the fact list of the target entity object to determine the comparison results of the information to be evaluated with each descriptive information in different dimensions.

[0102] Step S35: Determine the evaluation result of the information to be evaluated based on the comparison results of different dimensions.

[0103] When it is necessary to evaluate the information to be evaluated, the target entity object in the information to be evaluated can be identified, and the fact list of the target entity object can be determined from the fact list of multiple pre-stored entity objects. The information to be evaluated is compared with the fact list of the target entity object in different dimensions to obtain the comparison results in different dimensions, so as to determine the evaluation result of the information to be evaluated. This realizes the evaluation of the authenticity of the information to be evaluated and ensures the accuracy of the evaluation.

[0104] When comparing the information to be evaluated with the fact list of the target entity object across different dimensions, since the fact list of the target entity object includes multiple descriptive information, it is necessary to compare the information to be evaluated with each descriptive information of the target entity object during the comparison. Furthermore, for each descriptive information, comparisons need to be performed across different dimensions to ensure the completeness of the evaluation of the information to be evaluated.

[0105] Furthermore, in the information evaluation method disclosed in this embodiment, the evaluation result of the information to be evaluated is determined based on the comparison results of different dimensions, which can be specifically as follows:

[0106] Determine the weight coefficients corresponding to different dimensions; sum the comparison results of different dimensions according to their corresponding weight coefficients to obtain the evaluation results of the information to be evaluated.

[0107] Since the comparison between the information to be evaluated and each descriptive information is performed on different dimensions, whether the information to be evaluated matches the descriptive information needs to be determined by combining multiple dimensions. That is, the comparison results of multiple dimensions are integrated to obtain an evaluation result.

[0108] The importance of comparison results in different dimensions varies in the evaluation of the information to be evaluated. Therefore, the weight coefficients corresponding to comparison results in different dimensions are also different. The higher the importance, the larger the corresponding weight coefficient, and the lower the importance, the smaller the corresponding weight coefficient.

[0109] For example, if the target entity corresponding to the information to be evaluated is scenic spot a, when comparing the descriptive information in the fact list of scenic spot a, comparisons can be made from the time dimension, event dimension, and description similarity dimension. Compared with the time dimension and event dimension, the description similarity dimension is more important, so its corresponding weight coefficient is larger, while the weight coefficients corresponding to the time dimension and event dimension are relatively smaller.

[0110] After determining the comparison results for each dimension and the corresponding weight coefficient for each dimension, the comparison results for each dimension can be weighted and summed according to their corresponding weight coefficients to obtain the evaluation result, thereby determining the authenticity evaluation result of the information to be evaluated relative to each descriptive information.

[0111] It should be noted that the evaluation result is not a fixed value, that is, it does not directly determine whether the information to be evaluated is true or false. Instead, it uses a percentage or score to characterize the authenticity of the evaluation result.

[0112] For example: if the evaluation result of a certain piece of information to be evaluated is 90% relative to a certain descriptive information, then the information to be evaluated is likely true; if the evaluation result of a certain piece of information to be evaluated is 60% relative to a certain descriptive information, then the authenticity of the information to be evaluated is questionable; if the evaluation result of a certain piece of information to be evaluated is 30% relative to a certain descriptive information, then the information to be evaluated is likely false.

[0113] Specifically, whether the evaluation result of the information to be evaluated represents its authenticity can be determined by the range corresponding to the evaluation result.

[0114] For example: if the evaluation result of a certain piece of information relative to a certain descriptive information is 85, which is within the range of 70-90, then the information to be evaluated is likely true; if the evaluation result of a certain piece of information relative to a certain descriptive information is 60, which is within the range of 40-60, then the authenticity of the information to be evaluated is questionable; if the evaluation result of a certain piece of information relative to a certain descriptive information is 25, then the information to be evaluated is likely false.

[0115] Of course, it should be noted that, since the information evaluation method disclosed in this embodiment requires comparing the information to be evaluated with each description of the target entity object in different dimensions, the evaluation result of the information to be evaluated relative to each description will be obtained first. That is, to determine the evaluation result based on the comparison results in different dimensions, the evaluation result of the information to be evaluated relative to each description needs to be obtained first. After that, the final evaluation result of the information to be evaluated needs to be obtained.

[0116] Specifically, the final evaluation result is obtained based on the evaluation result of the information to be evaluated relative to each descriptive information. This can be achieved by: determining whether there is an evaluation result greater than a specific threshold among the evaluation results of the information to be evaluated and each descriptive information in the target entity object. If such a result exists, the final evaluation result of the information to be evaluated is determined to indicate that its authenticity is relatively high. If not, that is, the evaluation results of the information to be evaluated and each descriptive information in the target entity object are all less than the specific threshold, the final evaluation result of the information to be evaluated is determined to indicate that its authenticity is relatively low.

[0117] The information evaluation method disclosed in this embodiment, after obtaining the information to be evaluated, identifies the target entity object within the information. It then determines the fact list of the target entity object from a pre-stored fact list of multiple entity objects. Next, it compares the information to be evaluated with each descriptive piece of information in the fact list of the target entity object to determine the comparison result of the information to be evaluated with each descriptive piece of information in different dimensions, thereby determining the evaluation result of the information to be evaluated. This solution accurately determines the evaluation result between the information to be evaluated and each descriptive piece of information by comparing the information to be evaluated with each descriptive piece of information in the target entity object separately and determining the comparison result with each descriptive piece of information in different dimensions, thus ensuring the accuracy of the evaluation.

[0118] This embodiment discloses an information evaluation method, the flowchart of which is shown below. Figure 4 As shown, it includes:

[0119] Step S41: Obtain the information to be evaluated;

[0120] Step S42: Analyze the information to be evaluated and determine the target entity objects in the information to be evaluated;

[0121] Step S43: Determine the fact list of the target entity object from the fact lists of multiple pre-stored entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object. The confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold.

[0122] Step S44: Determine at least one target type description information from the pre-stored fact list of target entity objects based on the information to be evaluated. The target type is the type matched based on the information to be evaluated.

[0123] Step S45: Compare the information to be evaluated with the description information of at least one target type in different dimensions to obtain the comparison results in different dimensions;

[0124] Step S46: Determine the evaluation result of the information to be evaluated based on the comparison results of different dimensions.

[0125] When it is necessary to evaluate the information to be evaluated, the target entity object in the information to be evaluated can be identified, and the fact list of the target entity object can be determined from the fact list of multiple pre-stored entity objects. The information to be evaluated is compared with the fact list of the target entity object in different dimensions to obtain the comparison results in different dimensions, so as to determine the evaluation result of the information to be evaluated. This realizes the evaluation of the authenticity of the information to be evaluated and ensures the accuracy of the evaluation.

[0126] In this method, when comparing the information to be evaluated with the fact list of the target entity object in different dimensions to obtain the comparison results, the target type that matches the information to be evaluated can be determined first, and only the information to be evaluated can be compared with the description information of the target type in the fact list of the target entity object, instead of comparing the information to be evaluated with all the description information in the fact list of the target entity object. This improves the comparison efficiency while ensuring accuracy.

[0127] Analyze the information to be evaluated to determine the target type. For example, if the information to be evaluated describes the consumption level of a scenic spot, then it is only necessary to identify the descriptions related to the consumption level in the fact list of the target entity and compare the information to be evaluated with the identified descriptions, without comparing the information to be evaluated with the descriptions related to visitor flow in the fact list of the target entity. Or, if the information to be evaluated describes the visitor flow of a scenic spot, then it is only necessary to identify the descriptions related to visitor flow in the fact list of the target entity and compare the information to be evaluated with the identified descriptions, without comparing the information to be evaluated with the descriptions related to sanitation in the fact list of the target entity, and so on.

[0128] For example, if the information to be evaluated is "The cost of living at XX amusement park is too high," then the fact list corresponding to the entity XX amusement park is determined from a pre-stored fact list of multiple entities. The determined fact list of XX amusement park includes three types of descriptive information. Type 1 corresponds to the description information "Traffic congestion on the way to XX amusement park," Type 2 corresponds to the description information "There are many attractions at XX amusement park," and Type 3 corresponds to the description information "Eating and playing at XX amusement park is expensive." Since the description information corresponding to Type 1 is related to traffic conditions, Type 2 is related to attractions, and Type 3 is related to cost, and the information to be evaluated is related to cost, then Type 3 can be determined as the target type. Therefore, it is only necessary to compare the information to be evaluated with the description information corresponding to Type 3.

[0129] When determining the descriptive information of the target type and comparing the information to be evaluated with the descriptive information of at least one target type, it is still necessary to compare them on different dimensions to ensure the completeness of the comparison results.

[0130] The information evaluation method disclosed in this embodiment, after obtaining the information to be evaluated, determines the target entity object in the information to be evaluated, determines the fact list of the target entity object from a pre-stored fact list of multiple entity objects, and then determines at least one target type of descriptive information in the fact list of the target entity object based on the information to be evaluated. Then, the information to be evaluated is compared with the descriptive information of only at least one target type in different dimensions to obtain the comparison results of the descriptive information of that target type in different dimensions, thereby determining the evaluation result. This solution does not compare the information to be evaluated with every descriptive information in the fact list of the target entity object; instead, it first determines the descriptive information of the target type, and then compares the information to be evaluated only with the descriptive information of that target type, reducing the computational load of the evaluation and improving the evaluation efficiency.

[0131] Furthermore, in the information evaluation method disclosed in this embodiment, obtaining the information to be evaluated can be at least one of the following: obtaining link information in the evaluation request, and obtaining the information to be evaluated through the link information; obtaining an image in the evaluation request, and analyzing the image to determine the information to be evaluated; obtaining the information to be evaluated in the evaluation request.

[0132] The information evaluation system used in the information evaluation method disclosed in this embodiment can first obtain an evaluation request, analyze the evaluation request, and determine whether the evaluation request includes link information, images, or directly text information.

[0133] If the evaluation request includes link information, the system needs to determine the information to be evaluated through the link information, that is, read the information to be evaluated corresponding to the link information; if the evaluation request includes an image, the image needs to be recognized to determine the information to be evaluated in the image; if the evaluation request includes text information, the information to be evaluated can be determined by directly reading the text information.

[0134] This embodiment discloses an information evaluation system, the structural diagram of which is shown below. Figure 5 As shown, it includes:

[0135] The system includes a receiving unit 51, an analysis unit 52, a first determining unit 53, a comparison unit 54, and a second determining unit 55.

[0136] Among them, the obtaining unit 51 is used to obtain the information to be evaluated;

[0137] Analysis unit 52 is used to analyze the information to be evaluated and determine the target entity objects in the information to be evaluated;

[0138] The first determining unit 53 is used to determine the fact list of the target entity object from the fact list of multiple pre-stored entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold.

[0139] The comparison unit 54 is used to compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions.

[0140] The second determining unit 55 is used to determine the evaluation result of the information to be evaluated based on the comparison results of different dimensions.

[0141] Furthermore, the information evaluation system disclosed in this embodiment may also include:

[0142] A pre-storage unit is used to obtain multiple pre-storage contents from the resource pool, where the confidence level of each pre-storage content in the resource pool is higher than a target threshold; each pre-storage content is analyzed to determine at least one entity object corresponding to each pre-storage content and the descriptive information of each entity object; and a fact list of multiple entity objects is formed using the at least one entity object corresponding to each pre-storage content and the descriptive information of each entity object.

[0143] Furthermore, the pre-storage unit is used for:

[0144] Integrate at least one entity object corresponding to each pre-stored content in multiple pre-stored contents and the description information of each entity object to obtain multiple description information corresponding to each entity object in multiple entity objects; split the multiple description information corresponding to each entity object according to different types to obtain different types of description information for each entity object; arrange the different types of description information for each entity object according to different types to obtain a fact list for each entity object.

[0145] Furthermore, the comparison unit is used for:

[0146] The information to be evaluated is compared with each descriptive information in the fact list of the target entity object to determine the comparison results of the information to be evaluated with each descriptive information in different dimensions.

[0147] Furthermore, the second determining unit is used for:

[0148] Determine the weight coefficients corresponding to different dimensions; sum the comparison results of different dimensions according to their corresponding weight coefficients to obtain the evaluation results of the information to be evaluated.

[0149] Furthermore, the comparison unit is used for:

[0150] Based on the information to be evaluated, at least one target type of descriptive information is determined from the fact list of pre-stored target entity objects. The target type is the type that matches the information to be evaluated. The information to be evaluated is compared with the descriptive information of at least one target type in different dimensions to obtain comparison results in different dimensions.

[0151] Furthermore, the obtaining unit is used for:

[0152] Obtain the link information in the evaluation request, and obtain the information to be evaluated through the link information; obtain the image in the evaluation request, analyze the image to determine the information to be evaluated; obtain the information to be evaluated in the evaluation request.

[0153] The information evaluation system disclosed in this embodiment is based on the information evaluation method disclosed in the above embodiments, and will not be described again here.

[0154] This embodiment discloses an information evaluation system that obtains information to be evaluated; analyzes the information to be evaluated to determine the target entity object within it; determines the fact list of the target entity object from a pre-stored fact list of multiple entity objects, where each fact list includes multiple different descriptive information about the entity object, and the confidence level of the descriptive information in the fact list is higher than a target threshold; compares the information to be evaluated with the fact list of the target entity object across different dimensions to obtain comparison results; and determines the evaluation result of the information to be evaluated based on these comparison results. In this scheme, a fact list of multiple entity objects with confidence levels higher than the target threshold is pre-stored. When it is necessary to evaluate the information to be evaluated, the target entity object within it is first determined. Then, according to the target entity object, the fact list of the target entity object is determined from the pre-stored fact list of multiple entity objects, and the information to be evaluated is compared with the fact list of the target entity object across different dimensions to determine the comparison results. This further yields the evaluation result of the information to be evaluated, thus realizing the evaluation of the information to be evaluated based on pre-stored information with confidence levels higher than the target threshold. This achieves the evaluation of the authenticity of the information to be evaluated, avoiding the problem of unclear authenticity of the information to be evaluated affecting other users.

[0155] This embodiment discloses an electronic device, the structural schematic diagram of which is shown below. Figure 6 As shown, it includes:

[0156] Processor 61 and memory 62.

[0157] The processor 61 is used to obtain the information to be evaluated; analyze the information to be evaluated to determine the target entity object in the information to be evaluated; determine the fact list of the target entity object from a pre-stored fact list of multiple entity objects, wherein the fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold; compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions; and determine the evaluation result of the information to be evaluated based on the comparison results in different dimensions.

[0158] The memory 62 is used to store the program required by the processor to perform the above-mentioned processing.

[0159] The electronic device disclosed in this embodiment is implemented based on the information evaluation method disclosed in the above embodiments, and will not be described again here.

[0160] The electronic device disclosed in this embodiment obtains information to be evaluated; analyzes the information to be evaluated to determine the target entity object in the information to be evaluated; determines the fact list of the target entity object from a pre-stored fact list of multiple entity objects, wherein the fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than a target threshold; compares the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions; and determines the evaluation result of the information to be evaluated based on the comparison results in different dimensions. In this scheme, a fact list of multiple entity objects with confidence levels higher than a target threshold is pre-stored. When it is necessary to evaluate the information to be evaluated, the target entity object in the information to be evaluated is first determined. Then, the fact list of the target entity object is determined from the pre-stored fact list of multiple entity objects according to the target entity object, and the information to be evaluated is compared with the fact list of the target entity object in different dimensions to determine the comparison results in different dimensions, and further obtains the evaluation result of the information to be evaluated. This realizes the evaluation of the information to be evaluated based on pre-stored information with confidence levels higher than a target threshold, realizes the evaluation of the authenticity of the information to be evaluated, and avoids the problem of the unknown authenticity of the information to be evaluated affecting other users.

[0161] This application embodiment also provides a readable storage medium on which a computer program is stored. The computer program is loaded and executed by a processor to implement the steps of the above information evaluation method. The specific implementation process can be referred to the description of the corresponding part of the above embodiment, and will not be repeated in this embodiment.

[0162] This application also proposes a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the methods provided in the various optional implementations of the information evaluation method or information evaluation system described above. Specific implementation processes can be referred to the descriptions of the corresponding embodiments above, and will not be repeated here.

[0163] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0164] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0165] In the above embodiments, the implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, in the form of a computer program product.

[0166] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. An information evaluation method, characterized in that, include: Obtain the information to be evaluated; The information to be evaluated is analyzed to determine the target entity object in the information to be evaluated; The fact list of the target entity object is determined from a pre-stored fact list of multiple entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than the target threshold. The information to be evaluated is compared with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions; The evaluation result of the information to be evaluated is determined based on the comparison results of the different dimensions.

2. The method according to claim 1, characterized in that, Also includes: Obtain multiple pre-stored contents from a resource pool, wherein the confidence level of each pre-stored content in the resource pool is higher than a target threshold; Each of the pre-stored contents is analyzed to determine at least one entity object corresponding to each of the pre-stored contents and the description information of each entity object; A fact list of multiple entity objects is formed by using at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object.

3. The method according to claim 2, characterized in that, The step of forming a fact list of multiple entity objects using at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object includes: Integrate at least one entity object corresponding to each of the multiple pre-stored contents and the description information of each entity object to obtain multiple description information corresponding to each entity object in the multiple entity objects; The multiple descriptive information corresponding to each entity object is split according to different types to obtain different types of descriptive information for each entity object; The description information of each entity object of different types is arranged according to different types to obtain the fact list of each entity object.

4. The method according to claim 1, characterized in that, The step of comparing the information to be evaluated with the fact list of the target entity object across different dimensions to obtain comparison results across different dimensions includes: The information to be evaluated is compared with each descriptive information in the fact list of the target entity object to determine the comparison results of the information to be evaluated with each descriptive information in different dimensions.

5. The method according to claim 1, characterized in that, The determination of the evaluation result of the information to be evaluated based on the comparison results of the different dimensions includes: Determine the weighting coefficients for different dimensions; The comparison results of the different dimensions are weighted and summed according to the corresponding weight coefficients to obtain the evaluation result of the information to be evaluated.

6. The method according to claim 1, characterized in that, The step of comparing the information to be evaluated with the fact list of the target entity object across different dimensions to obtain comparison results across different dimensions includes: Based on the information to be evaluated, at least one target type description information is determined from the pre-stored fact list of the target entity object, wherein the target type is a type that matches the information to be evaluated; The information to be evaluated is compared with the description information of at least one target type in different dimensions to obtain comparison results in different dimensions.

7. The method according to claim 1, characterized in that, The information to be evaluated obtained includes at least one of the following: Obtain the link information in the evaluation request, and obtain the information to be evaluated through the link information; Obtain the image from the evaluation request, and analyze the image to determine the information to be evaluated; Obtain the information to be evaluated from the evaluation request.

8. An information evaluation system, characterized in that, include: The acquisition unit is used to acquire the information to be evaluated. An analysis unit is used to analyze the information to be evaluated and determine the target entity object in the information to be evaluated; The first determining unit is configured to determine the fact list of the target entity object from a pre-stored fact list of multiple entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than a target threshold. The comparison unit is used to compare the information to be evaluated with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions. The second determining unit is used to determine the evaluation result of the information to be evaluated based on the comparison results of the different dimensions.

9. An electronic device, characterized in that, include: A processor, used to obtain the information to be evaluated; The information to be evaluated is analyzed to determine the target entity object in the information to be evaluated; The fact list of the target entity object is determined from a pre-stored fact list of multiple entity objects. The fact list of the entity object includes multiple different descriptive information of the entity object, and the confidence level of the descriptive information in the fact list of the entity object is higher than a target threshold. The information to be evaluated is compared with the fact list of the target entity object in different dimensions to obtain comparison results in different dimensions. The evaluation result of the information to be evaluated is determined based on the comparison results in different dimensions. The memory is used to store the programs required by the processor to perform the above-described processing.

10. A readable storage medium, characterized in that, Used to store at least one set of instructions; The instruction set is used to be invoked and to execute at least the information evaluation method as described in any one of claims 1-7.

Images