Information determination method and apparatus, electronic device, and storage medium

Abstract

The application discloses an information determination method and device, electronic equipment and a storage medium, and is used for improving the efficiency and accuracy of information identification. In the embodiment of the application, the text information of a target object is split to obtain at least one sample object; a scoring model is used to score each sample object to obtain an initial score; for each sample object, based on the initial score of the target sample object and the initial score of the sample object, the final score of the sample object is obtained; based on the final score of each sample object of the target object, the text score of the target object is obtained; if the text score of the target object is within a preset threshold range, the target object is determined to be standard information. In the application, the text information of the target object is split and scored respectively, so that the determination of the text information of the target object is more accurate, and the scoring process of the target object does not require manual access, so that the identification efficiency of the information is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an information determination method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the field of data business, data processing is basically done by using scenario rule recognition and manual intervention.

[0003] Manual data identification relies heavily on manual configuration of data rule recognition libraries based on real-world scenarios. This involves matching inappropriate content from images, videos, and text on websites and recording its context and source. This method requires significant human effort and time to accumulate, iterate, and maintain the rule recognition library; it is extremely costly in terms of manpower and time, resulting in low efficiency and accuracy. Summary of the Invention

[0004] The purpose of this application is to provide an information determination method, apparatus, electronic device, and storage medium to improve the efficiency and accuracy of information identification.

[0005] In a first aspect, embodiments of this application provide an information determination method, the method comprising:

[0006] Text extraction is performed on the target object to obtain its text information;

[0007] The text information is split to obtain at least one sample object; the sample object includes a single Chinese character from the text information.

[0008] A scoring model is used to score each of the sample objects to obtain an initial score for each sample object;

[0009] For each sample object, the final score of the sample object is obtained based on the initial score of the target sample object and the initial score of the sample object; wherein, the target sample object is the sample object with the largest initial score;

[0010] Based on the final score of each sample object of the target object, the text score of the target object is obtained;

[0011] If the text score of the target object is within a preset threshold range, then the target object is determined to be standard information.

[0012] In this application, the text information of the target object is split and scored separately, which makes the determination of the text information of the target object more accurate. Moreover, the scoring process of the target object does not require manual intervention, thus improving the efficiency of information recognition.

[0013] In some possible embodiments, obtaining the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object includes:

[0014] Based on the initial score of the target sample object, a first indicator score, a second indicator score, and a third indicator score are obtained for the sample object; wherein, the first indicator is a negative indicator of the sample object's derogatory terms, the second indicator is a negative indicator of the sample object's neutral terms, and the third indicator is a negative indicator of the sample object's positive terms; and,

[0015] Based on the Gaussian function and the first index score of the sample object, the first weight of the sample object is obtained; based on the Gaussian function and the second index score of the sample object, the second weight of the sample object is obtained; based on the Gaussian function and the third index score of the sample object, the third weight of the sample object is obtained.

[0016] Based on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight, the final score of the sample object is obtained.

[0017] In this application, three index scores are set for each sample object, and different weights are set according to different indicators, so as to make the final score evaluation of the sample object more accurate, and thus make the evaluation of the target object more accurate.

[0018] In some possible embodiments, obtaining the first index score of the sample object based on the initial score of the target sample object includes:

[0019] The difference between the initial score of the target object and the initial score of the sample object is taken as the first indicator score of the sample object.

[0020] The reciprocal of the initial score of the target object is used as the first indicator score of the sample object.

[0021] This application sets out two methods for determining the score of the first indicator, making this application more universal.

[0022] In some possible embodiments, obtaining the second index score of the sample object based on the initial score of the target sample object and the initial score of the sample object includes:

[0023] A first intermediate value is obtained based on the initial score of the target sample object and the initial score of the sample object;

[0024] The ratio of the absolute value of the difference between the target sample object and the sample object to the first median value is used as the second indicator score.

[0025] Wherein, the first intermediate value is the maximum value among the absolute values ​​of the differences between the initial score of each sample object and the initial score of the target sample object.

[0026] In this application, a second indicator score is determined based on the initial score of the target sample object and the initial score of the sample object, making the determined second indicator score more accurate.

[0027] In some possible embodiments, obtaining the third indicator score of the sample object based on the initial score of the target sample object and the initial score of the sample object includes:

[0028] A second intermediate value is determined based on the upper and lower limits of a preset interval; wherein the upper and lower limits of the preset interval are determined based on the target object;

[0029] Determine the first difference between the lower limit value and the initial score of the sample object;

[0030] The ratio of the first difference to the second median value is used as the score of the third indicator.

[0031] In this application, the third indicator score is determined based on the initial score of the target sample object and the initial score of the sample object, so that the determined third indicator score is more accurate.

[0032] In some possible embodiments, determining the second intermediate value based on the upper and lower limits of a preset interval includes:

[0033] Determine a second difference between the lower limit and the initial score of the minimum sample object; and determine a third difference between the upper limit and the initial score of the target sample object; wherein the minimum sample object is the sample object with the smallest initial score;

[0034] If the second difference is greater than or equal to the third difference, then the second difference is taken as the second intermediate value;

[0035] If the second difference is less than the third difference, then the third difference is taken as the second intermediate value.

[0036] In this application, different values ​​are selected as the second intermediate value according to different situations, which further makes the determined third indicator score more accurate.

[0037] In some possible embodiments, obtaining the final score of the sample object based on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight includes:

[0038] The sum of the first and second product values, and the difference between the third product value, are used as the final score of the sample object. The first product value is the product of the first indicator score and the first weight, the second product value is the product of the second indicator score and the second weight, and the third product value is the product of the third indicator score and the third weight.

[0039] In this application, different weights are assigned to different indicator scores, making the determination of sample objects more accurate.

[0040] Secondly, this application also provides an information determining device, the device comprising:

[0041] The extraction module is used to extract text from the target object to obtain the text information of the target object;

[0042] A splitting module is used to split the text information to obtain at least one sample object; the sample object includes a single Chinese character in the text information;

[0043] The scoring module is used to score each of the sample objects using a scoring model to obtain an initial score for each of the sample objects;

[0044] The scoring calculation module is used to obtain the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object; wherein, the target sample object is the sample object with the largest initial score;

[0045] The scoring acquisition module is used to obtain a text score for the target object based on the final score of each sample object of the target object;

[0046] The information determination module is used to determine that the target object is standardized information if the text score of the target object is within a preset threshold range.

[0047] In some possible embodiments, when the scoring calculation module performs the operation of obtaining the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object, it is configured to:

[0048] Based on the initial score of the target sample object, a first indicator score, a second indicator score, and a third indicator score are obtained for the sample object; wherein, the first indicator is a negative indicator of the sample object's derogatory terms, the second indicator is a negative indicator of the sample object's neutral terms, and the third indicator is a negative indicator of the sample object's positive terms; and,

[0049] Based on the Gaussian function and the first index score of the sample object, the first weight of the sample object is obtained; based on the Gaussian function and the second index score of the sample object, the second weight of the sample object is obtained; based on the Gaussian function and the third index score of the sample object, the third weight of the sample object is obtained.

[0050] Based on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight, the final score of the sample object is obtained.

[0051] In some possible embodiments, when the scoring calculation module performs an initial score based on the target sample object to obtain a first indicator score for the sample object, it is configured to:

[0052] The difference between the initial score of the target object and the initial score of the sample object is taken as the first indicator score of the sample object.

[0053] The reciprocal of the initial score of the target object is used as the first indicator score of the sample object.

[0054] In some possible embodiments, when the scoring calculation module performs a second index score for the sample object based on the initial score of the target sample object and the initial score of the sample object, it is configured to:

[0055] A first intermediate value is obtained based on the initial score of the target sample object and the initial score of the sample object;

[0056] The ratio of the absolute value of the difference between the target sample object and the sample object to the first median value is used as the second indicator score.

[0057] Wherein, the first intermediate value is the maximum value among the absolute values ​​of the differences between the initial score of each sample object and the initial score of the target sample object.

[0058] In some possible embodiments, when the scoring calculation module performs a third indicator score for the sample object based on the initial score of the target sample object and the initial score of the sample object, it is configured to:

[0059] A second intermediate value is determined based on the upper and lower limits of a preset interval; wherein the upper and lower limits of the preset interval are determined based on the target object;

[0060] Determine the first difference between the lower limit value and the initial score of the sample object;

[0061] The ratio of the first difference to the second median value is used as the score of the third indicator.

[0062] In some possible embodiments, when the score calculation module determines the second intermediate value based on the upper and lower limits of a preset interval, it is configured as follows:

[0063] Determine a second difference between the lower limit and the initial score of the minimum sample object; and determine a third difference between the upper limit and the initial score of the target sample object; wherein the minimum sample object is the sample object with the smallest initial score;

[0064] If the second difference is greater than or equal to the third difference, then the second difference is taken as the second intermediate value;

[0065] If the second difference is less than the third difference, then the third difference is taken as the second intermediate value.

[0066] In some possible embodiments, when the score calculation module performs calculations on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight to obtain the final score of the sample object, it is configured as follows:

[0067] The sum of the first and second product values, and the difference between the third product value, are used as the final score of the sample object. The first product value is the product of the first indicator score and the first weight, the second product value is the product of the second indicator score and the second weight, and the third product value is the product of the third indicator score and the third weight.

[0068] Thirdly, another embodiment of this application also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the methods provided in the first aspect embodiment of this application.

[0069] Fourthly, another embodiment of this application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for causing a computer to perform any of the methods provided in the first aspect of this application.

[0070] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0071] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application 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.

[0072] Figure 1 This application provides an illustration of an information determination method according to an embodiment of the present application.

[0073] Figure 2 This is a schematic diagram of the overall process of an information determination method provided in an embodiment of this application;

[0074] Figure 3 This is a schematic diagram of the target object of an information determination method provided in an embodiment of this application;

[0075] Figure 4 A schematic diagram illustrating the process of determining the final score of a sample object using an information determination method provided in this application embodiment;

[0076] Figure 5 A flowchart illustrating the determination of a third indicator score in an information determination method provided in this application embodiment;

[0077] Figure 6 A flowchart illustrating the determination of a second intermediate value in an information determination method provided in this application embodiment;

[0078] Figure 7 A schematic diagram of an apparatus for an information determination method provided in an embodiment of this application;

[0079] Figure 8 This is a schematic diagram of an electronic device for an information determination method provided in an embodiment of this application. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0081] The terms "first" and "second" in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses. The term "multiple" in this application can mean at least two, for example, two, three, or more, and is not limited by the embodiments of this application.

[0082] The inventors' research revealed that data processing in the data business field primarily utilizes scenario-based rule recognition and manual intervention. Manual data recognition relies heavily on individuals continuously configuring corresponding data rule recognition libraries based on real-world scenarios, matching inappropriate content from images, videos, and text on websites, and recording their corresponding context and data source. This method requires significant human effort and time to accumulate, iterate, and maintain the rule recognition library; it is extremely labor-intensive and time-consuming, inefficient, and lacks accuracy.

[0083] In view of this, this application proposes an information determination method, apparatus, electronic device, and storage medium to solve the above-mentioned problems. The inventive concept of this application can be summarized as follows: extracting text from a target object to obtain its text information; splitting the text information to obtain at least one sample object; each sample object includes a single Chinese character from the text information; scoring each sample object using a scoring model to obtain an initial score for each sample object; for each sample object, obtaining a final score based on the initial score of the target sample object and the initial scores of the sample objects; wherein the target sample object is the sample object with the highest initial score; obtaining a text score for the target object based on the final scores of each sample object of the target object; if the text score of the target object is within a preset threshold range, then the target object is determined to be standard information.

[0084] For ease of understanding, the information determination method provided by an embodiment of this application will be described in detail below with reference to the accompanying drawings:

[0085] like Figure 1 The diagram shown illustrates an application scenario of an information determination method according to an embodiment of this application. The diagram includes: a server 10, a storage device 20, and a terminal device 30; wherein:

[0086] Server 10 extracts text from the target object uploaded by the user to terminal device 30 to obtain the text information of the target object; then, it splits the text information to obtain at least one sample object; the sample object includes a single Chinese character in the text information; a scoring model is used to score each sample object to obtain an initial score for each sample object; the scoring model is pre-trained and stored in memory; for each sample object, based on the initial score of the target sample object and the initial score of the sample object, a final score for the sample object is obtained; the target sample object is the sample object with the highest initial score; based on the final score of each sample object of the target object, a text score for the target object is obtained; if the text score of the target object is within a preset threshold range, the target object is determined to be standard information.

[0087] The description in this application details only a single server, memory, and terminal device. However, those skilled in the art should understand that the illustrated servers, memory, and terminal devices are intended to illustrate the operation of the servers, memory, and terminal devices involved in the technical solutions of this application, and do not imply any limitation on the number, type, or location of the servers, memory, or terminal devices. It should be noted that adding additional modules to or removing individual modules from the illustrated environment will not change the underlying concept of the exemplary embodiments of this application. Furthermore, although for ease of explanation... Figure 1The diagram shows a bidirectional arrow from memory 20 to server 10, but those skilled in the art will understand that the sending and receiving of the aforementioned data also needs to be achieved through a network.

[0088] It should be noted that the memory in the embodiments of this application can be, for example, a cache system, hard disk storage, memory storage, etc. Furthermore, the information determination method proposed in this application is not only applicable to… Figure 1 The application scenarios shown can also be applied to any device that requires information determination.

[0089] like Figure 2 The diagram shown is an overall flowchart of an information determination method provided in an embodiment of this application, wherein:

[0090] In step 201: extract text from the target object to obtain the text information of the target object;

[0091] In step 202: the text information is split to obtain at least one sample object; the sample object includes a single Chinese character in the text information;

[0092] In step 203: a scoring model is used to score each sample object to obtain an initial score for each sample object;

[0093] In step 204: For each sample object, based on the initial score of the target sample object and the initial score of the sample object, the final score of the sample object is obtained; where the target sample object is the sample object with the largest initial score.

[0094] In step 205: Based on the final score of each sample object of the target object, the text score of the target object is obtained;

[0095] In step 206: If the text score of the target object is within the preset threshold range, then the target object is determined to be standard information.

[0096] In this application, the text information of the target object is split and scored separately, which makes the determination of the text information of the target object more accurate. Moreover, the scoring process of the target object does not require manual intervention, thus improving the efficiency of information recognition.

[0097] For ease of understanding, the following is... Figure 2 The steps are explained in detail below:

[0098] In this application's embodiments, the target object can be text, a video frame containing text, an image containing text, etc.; any object containing text can be used as the target object in this application. To facilitate determining whether the target object is standard information, text extraction is required after obtaining the target object. When extracting text from the target object, OCR (optical character recognition) or other text recognition technologies can be used. Any text recognition technology that can extract text is applicable to this application.

[0099] For example: Figure 3 As shown, for a video frame containing text, OCR text recognition technology is used to extract the text in the video frame, resulting in the text information "for a sample".

[0100] In some embodiments, to ensure the accuracy of target object recognition, the text information of the target object needs to be split after extraction. For example, for... Figure 3 The text information "for a sample" is broken down into "needle", "pair", "one", "item", "sample", and each of these is treated as a sample object for scoring. It should be noted that the target objects in this application all conform to a normal distribution.

[0101] In this embodiment, after obtaining the sample objects, a scoring model is used to score each sample object to obtain an initial score of each sample object. In this application, the scoring model is a pre-trained scoring model, and the training process is the same as the training model method in related technologies, which will not be described in detail here.

[0102] In some embodiments, for each sample object, the final score of the sample object is obtained based on the initial score of the target sample object and the initial score of the sample object. Specifically, this can be implemented as follows: Figure 4 The steps shown are as follows:

[0103] In step 401: Based on the initial score of the target sample object, the first indicator score, the second indicator score, and the third indicator score of the sample object are obtained;

[0104] In this application, different methods for determining different indicators are set. The determination methods for each indicator are explained below:

[0105] 1. Score of the first indicator

[0106] In this application, the first indicator is the negative vocabulary inverse indicator of the sample object. The difference between the initial score of the target object and the initial score of the sample object is taken as the first indicator score of the sample object, or the reciprocal of the initial score of the target object is taken as the first indicator score of the sample object.

[0107] For example: Regarding such Figure 3 The sample objects “needle”, “pair”, “one”, “item”, “sample”, and “sample” in the target object are input into the scoring model to obtain the initial scores for each sample object as follows: sample object “needle” scores 7 points, sample object “pair” scores 7 points, sample object “one” scores 8 points, sample object “item” scores 9 points, sample object “sample” scores 7 points, and sample object “sample” scores 6 points. Since the initial score for sample object “needle” is 7 points and the target sample object “item” scores 9 points, the first indicator score for sample object “needle” is 2 or 1 / 7.

[0108] 2. Second indicator score

[0109] In this application, the second indicator is a neutral lexical inverse indicator of the sample object. When determining the second indicator score of the sample object, it can be implemented as follows: obtain a first intermediate value based on the initial score of the target sample object and the initial score of the sample object; take the ratio of the absolute value of the difference between the target sample object and the sample object to the first intermediate value as the second indicator score; wherein, the first intermediate value is the maximum value among the absolute values ​​of the difference between the initial score of each sample object and the initial score of the target sample object.

[0110] For example: Regarding such Figure 3The sample objects "needle", "for", "one", "individual", "sample", and "copy" in the target object as shown are respectively input into the scoring model, and the initial scores for each sample object are obtained as follows: the sample object "needle" has a score of 7, the sample object "for" has a score of 7, the sample object "one" has a score of 8, the sample object "individual" has a score of 9, the sample object "sample" has a score of 7, and the sample object "copy" has a score of 6; the target sample object is "individual" with a score of 9. First, determine the absolute value of the difference between the initial score of each sample object and the initial score of the target sample object, wherein the absolute value of the difference between the initial score of the sample object "needle" and the initial score of the target sample object "individual" is 2, the absolute value of the difference between the initial score of the sample object "for" and the initial score of the target sample object "individual" is 2, the absolute value of the difference between the initial score of the sample object "one" and the initial score of the target sample object "individual" is 1, the absolute value of the difference between the initial score of the sample object "sample" and the initial score of the target sample object "individual" is 2, and the absolute value of the difference between the initial score of the sample object "copy" and the initial score of the target sample object "individual" is 3; thus it can be determined that the first intermediate value is 3, and the absolute value of the difference between the target sample object and the sample object "one" is 1, so it can be determined that the second indicator score of the sample object "one" is 1 / 3.

[0111] 3. Score of the third indicator

[0112] In the present application, the third indicator is a reverse indicator of commendatory terms for sample objects; when determining the third indicator score of a sample object, it can be implemented as shown in Figure 5 the following steps:

[0113] In step 501: a second intermediate value is determined according to the upper limit and the lower limit of a preset interval; wherein the upper limit and the lower limit of the preset interval are determined based on the target object;

[0114] In the present application, the upper limit and the lower limit of the preset interval can be set by technicians according to the target object. For example, for the target object as shown in Figure 3 the figure, the upper limit of the preset interval can be set as b, and the lower limit of the preset interval can be set as a.

[0115] In the present application, after determining the upper limit and the lower limit of the preset interval, the second intermediate value can be determined by implementing the steps shown in Figure 6 below:

[0116] In step 601: determining a second difference between the lower limit and the initial score of the minimum sample object; and determining a third difference between the upper limit and the initial score of the target sample object; wherein the minimum sample object is the sample object with the smallest initial score;

[0117] In step 602: if the second difference is greater than or equal to the third difference, taking the second difference as the second intermediate value;

[0118] In step 603: If the second difference is less than the third difference, then the third difference is taken as the second intermediate value.

[0119] For example: Regarding such Figure 3 The target object's sample objects "needle", "pair", "one", "piece", "sample", and "book" are input into the scoring model, resulting in initial scores for each sample object: "needle" scores 7 points, "pair" scores 7 points, "one" scores 8 points, "piece" scores 9 points, "sample" scores 7 points, and "book" scores 6 points. The target sample object "piece" scores 9 points, and the smallest sample object "book" scores 6 points. The second difference is a-6, and the third difference is b-9. The larger of these two values ​​is selected as the second median value.

[0120] In step 502: Determine the first difference between the lower limit and the initial score of the sample object;

[0121] For example: Regarding such Figure 3 The target objects shown are input into the scoring model as follows: "needle", "pair", "one", "item", "sample", and "book". The initial scores for each sample object are as follows: "needle" scores 7 points, "pair" scores 7 points, "one" scores 8 points, "item" scores 9 points, "sample" scores 7 points, and "book" scores 6 points. The first difference for the sample object "one" is a-8.

[0122] In step 503: the ratio of the first difference to the second median value is used as the score for the third indicator.

[0123] For example: targeting Figure 3 For the sample object of the target object shown, the second difference is a-6, the third difference is b-9, and the second difference is greater than the third difference. Therefore, the third indicator score of the sample object "one" is (a-8) / (a-6).

[0124] In step 402: Based on the Gaussian function and the first index score of the sample object, the first weight of the sample object is obtained; based on the Gaussian function and the second index score of the sample object, the second weight of the sample object is obtained; based on the Gaussian function and the third index score of the sample object, the third weight of the sample object is obtained.

[0125] In some possible embodiments, the Gaussian formula is as shown in Formula 1:

[0126]

[0127] Where σ is the variance and μ is the mean.

[0128] Since the target objects in this application all conform to a normal distribution, μ equals 0 and σ equals 1. Therefore, the Gaussian formula can be transformed into Equation 2:

[0129]

[0130] Where x is the first indicator score of the sample object, then f(x) is the reciprocal of the first weight of the sample object; if x is the second indicator score of the sample object, then f(x) is the reciprocal of the second weight of the sample object; if x is the third indicator score of the sample object, then f(x) is the reciprocal of the third weight of the sample object. Thus, the first weight, second weight, and third weight of each sample object can be obtained.

[0131] In step 403: Based on the first indicator score and first weight, the second indicator score and second weight, and the third indicator score and third weight, the final score of the sample object is obtained.

[0132] In this application, after obtaining the first indicator score and first weight, the second indicator score and second weight, and the third indicator score and third weight for a sample object, the following can be implemented: the difference between the sum of the first and second product values ​​and the third product value can be used as the final score of the sample object, wherein the first product value is the product of the first indicator score and the first weight, the second product value is the product of the second indicator score and the second weight, and the third product value is the product of the third indicator score and the third weight.

[0133] For example: For sample object A, if we determine that the first indicator score of sample object A is b1, the second indicator score is b2, and the third indicator score is b3; and the first weight is w1, the second weight is w2, and the third weight is w3, then we can determine that the final score of sample object A is: f(x) = b2*w2 + b3*w3 - b1*w1.

[0134] In summary, the final score of each sample object of the target object can be determined, and the sum of the values ​​of each sample object of the target object is used as the text score of the target object.

[0135] like Figure 7 As shown, based on the same inventive concept, an information determining device 700 is proposed, the device comprising:

[0136] The extraction module 7001 is used to extract text from a target object to obtain the text information of the target object;

[0137] The splitting module 7002 is used to split the text information to obtain at least one sample object; the sample object includes a single Chinese character in the text information;

[0138] The scoring module 7003 is used to score each of the sample objects using a scoring model to obtain an initial score for each of the sample objects;

[0139] The score calculation module 7004 is used to obtain the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object; wherein, the target sample object is the sample object with the largest initial score;

[0140] The scoring acquisition module 7005 is used to obtain a text score of the target object based on the final score of each sample object of the target object;

[0141] The information determination module 7006 is used to determine that the target object is standardized information if the text score of the target object is within a preset threshold range.

[0142] In some possible embodiments, when the score calculation module 7004 performs the operation of obtaining the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object, it is configured to:

[0143] Based on the initial score of the target sample object, a first indicator score, a second indicator score, and a third indicator score are obtained for the sample object; wherein, the first indicator is a negative indicator of the sample object's derogatory terms, the second indicator is a negative indicator of the sample object's neutral terms, and the third indicator is a negative indicator of the sample object's positive terms; and,

[0144] Based on the Gaussian function and the first index score of the sample object, the first weight of the sample object is obtained; based on the Gaussian function and the second index score of the sample object, the second weight of the sample object is obtained; based on the Gaussian function and the third index score of the sample object, the third weight of the sample object is obtained.

[0145] Based on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight, the final score of the sample object is obtained.

[0146] In some possible embodiments, when the scoring calculation module 7004 performs an initial scoring based on the target sample object to obtain a first indicator score for the sample object, it is configured to:

[0147] The difference between the initial score of the target object and the initial score of the sample object is taken as the first indicator score of the sample object.

[0148] The reciprocal of the initial score of the target object is used as the first indicator score of the sample object.

[0149] In some possible embodiments, when the score calculation module 7004 performs the calculation based on the initial score of the target sample object and the initial score of the sample object to obtain the second indicator score of the sample object, it is configured to:

[0150] A first intermediate value is obtained based on the initial score of the target sample object and the initial score of the sample object;

[0151] The ratio of the absolute value of the difference between the target sample object and the sample object to the first median value is used as the second indicator score.

[0152] Wherein, the first intermediate value is the maximum value among the absolute values ​​of the differences between the initial score of each sample object and the initial score of the target sample object.

[0153] In some possible embodiments, when the scoring calculation module 7004 performs the calculation based on the initial score of the target sample object and the initial score of the sample object to obtain the third indicator score of the sample object, it is configured to:

[0154] A second intermediate value is determined based on the upper and lower limits of a preset interval; wherein the upper and lower limits of the preset interval are determined based on the target object;

[0155] Determine the first difference between the lower limit value and the initial score of the sample object;

[0156] The ratio of the first difference to the second median value is used as the score of the third indicator.

[0157] In some possible embodiments, when the score calculation module 7004 determines the second intermediate value based on the upper and lower limits of a preset interval, it is configured to:

[0158] Determine a second difference between the lower limit and the initial score of the minimum sample object; and determine a third difference between the upper limit and the initial score of the target sample object; wherein the minimum sample object is the sample object with the smallest initial score;

[0159] If the second difference is greater than or equal to the third difference, then the second difference is taken as the second intermediate value;

[0160] If the second difference is less than the third difference, then the third difference is taken as the second intermediate value.

[0161] In some possible embodiments, when the score calculation module 7004 performs calculations on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight to obtain the final score of the sample object, it is configured as follows:

[0162] The sum of the first and second product values, and the difference between the third product value, are used as the final score of the sample object. The first product value is the product of the first indicator score and the first weight, the second product value is the product of the second indicator score and the second weight, and the third product value is the product of the third indicator score and the third weight.

[0163] Having described the information determination method and apparatus according to exemplary embodiments of this application, we will now describe an electronic device according to another exemplary embodiment of this application.

[0164] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0165] In some possible implementations, the electronic device according to this application may include at least one processor and at least one memory. The memory stores program code that, when executed by the processor, causes the processor to perform the steps of the information determination method according to the various exemplary embodiments of this application described above.

[0166] The following reference Figure 8 To describe an electronic device 130 according to this embodiment of the present application. Figure 8 The electronic device 130 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0167] like Figure 8 As shown, the electronic device 130 is presented in the form of a general-purpose electronic device. The components of the electronic device 130 may include, but are not limited to: at least one processor 131, at least one memory 132, and a bus 133 connecting different system components (including memory 132 and processor 131).

[0168] Bus 133 represents one or more of several bus structures, including a memory bus or memory controller, peripheral bus, processor, or local bus using any of the various bus structures.

[0169] The memory 132 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 1321 and / or cache memory 1322, and may further include read-only memory (ROM) 1323.

[0170] The memory 132 may also include a program / utility 1325 having a set (at least one) of program modules 1324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0171] Electronic device 130 can also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), and with one or more devices that enable a user to interact with electronic device 130, and / or with any device that enables electronic device 130 to communicate with one or more other electronic devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 135. Furthermore, electronic device 130 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 136. As shown, network adapter 136 communicates with other modules used in electronic device 130 via bus 133. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0172] In some possible implementations, various aspects of the information determination method provided in this application can also be implemented in the form of a program product, which includes program code that, when the program product is run on a computer device, causes the computer device to perform the steps in the information determination method according to the various exemplary embodiments of this application described above.

[0173] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0174] The program product for information determination according to the embodiments of this application can be a portable compact disc read-only memory (CD-ROM) and include program code, and can run on an electronic device. However, the program product of this application is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0175] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take many forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0176] The program code contained on the readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wired, fiber optic, RF, etc., or any suitable combination thereof.

[0177] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's electronic device, partially on the user's device, as a standalone software package, partially on the user's electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In cases involving remote electronic devices, the remote electronic device can be connected to the user's electronic device via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external electronic device (e.g., via the Internet using an Internet service provider).

[0178] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0179] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0180] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0181] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0182] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0183] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0184] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for determining information, characterized in that, Applied to a server, the method includes: The server extracts text from the target object to obtain the text information of the target object; The server performs splitting processing on the text information to obtain at least one sample object; the sample object includes a single Chinese character from the text information. The server uses a scoring model to score each sample object to obtain an initial score for each sample object. The scoring model is pre-trained and stored in the server's memory. For each sample object, the server obtains a final score based on the initial score of the target sample object and the initial score of the sample object; wherein the target sample object is the sample object with the highest initial score; the server obtains a final score for each sample object based on the initial score of the target sample object and the initial score of the sample object, including: the server obtains a first indicator score, a second indicator score, and a third indicator score for the sample object based on the initial score of the target sample object; wherein the first indicator is a negative word inverse indicator for the sample object, the second indicator is a neutral word inverse indicator for the sample object, and the third indicator is a positive word inverse indicator for the sample object; and the server obtains a first weight for the sample object based on a Gaussian function and the first indicator score; the server obtains a second weight for the sample object based on the Gaussian function and the second indicator score; the server obtains a third weight for the sample object based on the Gaussian function and the third indicator score; and the server obtains the final score for the sample object based on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight. The server obtains the final score of the sample object based on the first indicator score and the first weight, the second indicator score and the second weight, and the third indicator score and the third weight, including: the server takes the difference between the sum of the first product and the second product and the third product as the final score of the sample object, wherein the first product is the product of the first indicator score and the first weight, the second product is the product of the second indicator score and the second weight, and the third product is the product of the third indicator score and the third weight; The server obtains a text score for the target object based on the final score of each sample object of the target object; obtaining a text score for the target object based on the final score of each sample object of the target object includes: the server using the sum of the final scores of each sample object of the target object as the text score of the target object; If the text score of the target object is within a preset threshold range, the server determines that the target object is normal information, and the normal information is non-harmful information.

2. The method according to claim 1, characterized in that, The server obtains a first indicator score for the target sample object based on its initial score, including: The server uses the difference between the initial score of the target object and the initial score of the sample object as the first indicator score of the sample object. The server uses the reciprocal of the initial score of the target object as the first indicator score of the sample object.

3. The method according to claim 1, characterized in that, The server obtains a second indicator score for the sample object based on the initial score of the target sample object and the initial score of the sample object, including: The server obtains a first intermediate value based on the initial score of the target sample object and the initial score of the sample object; The server uses the ratio of the absolute value of the difference between the target sample object and the sample object to the first median value as the second indicator score. Wherein, the first intermediate value is the maximum value among the absolute values ​​of the differences between the initial score of each sample object and the initial score of the target sample object.

4. The method according to claim 1, characterized in that, The server obtains a third indicator score for the sample object based on the initial score of the target sample object and the initial score of the sample object, including: The server determines a second intermediate value based on the upper and lower limits of a preset range; wherein the upper and lower limits of the preset range are determined based on the target object; The server determines a first difference between the lower limit value and the initial score of the sample object; The server uses the ratio of the first difference to the second median value as the score for the third indicator.

5. The method according to claim 4, characterized in that, The server determines the second intermediate value based on the upper and lower limits of a preset range, including: The server determines a second difference between the lower limit and the initial score of the smallest sample object; and the server determines a third difference between the upper limit and the initial score of the target sample object; wherein the smallest sample object is the sample object with the smallest initial score; If the second difference is greater than or equal to the third difference, then the server uses the second difference as the second intermediate value; If the second difference is less than the third difference, the server uses the third difference as the second intermediate value.

6. An information determining device, characterized in that, The device is used in a server, and the device includes: The extraction module is used to extract text from the target object to obtain the text information of the target object; A splitting module is used to split the text information to obtain at least one sample object; the sample object includes a single Chinese character in the text information; The scoring module is used to score each of the sample objects using a scoring model to obtain an initial score for each of the sample objects, wherein the scoring model is pre-trained and stored in the memory of the server; The scoring calculation module is used to obtain the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object; wherein the target sample object is the sample object with the largest initial score; the process of obtaining the final score of each sample object based on the initial score of the target sample object and the initial score of the sample object includes: obtaining a first indicator score, a second indicator score, and a third indicator score of the sample object based on the initial score of the target sample object; wherein the first indicator is the negative word inverse indicator of the sample object, the second indicator is the neutral word inverse indicator of the sample object, and the third indicator is the positive word inverse indicator of the sample object; and, based on the Gaussian function and the first indicator score of the sample object, obtaining the first weight of the sample object; based on the Gaussian function and the sample... The second indicator score of the object is used to obtain the second weight of the sample object; the third indicator score of the sample object is used to obtain the third weight of the sample object based on the Gaussian function and the third indicator score of the sample object; the final score of the sample object is obtained based on the first indicator score and the first weight, the second indicator score and the second weight, the third indicator score and the third weight; obtaining the final score of the sample object based on the first indicator score and the first weight, the second indicator score and the second weight, the third indicator score and the third weight includes: taking the difference between the sum of the first product and the second product and the third product as the final score of the sample object, wherein the first product is the product of the first indicator score and the first weight, the second product is the product of the second indicator score and the second weight, and the third product is the product of the third indicator score and the third weight; The scoring acquisition module is used to obtain a text score of the target object based on the final score of each sample object of the target object; the step of obtaining a text score of the target object based on the final score of each sample object of the target object includes: using the sum of the final scores of each sample object of the target object as the text score of the target object; The information determination module is used to determine that if the text score of the target object is within a preset threshold range, the target object is considered normal information and the normal information is considered non-adverse information.

7. An electronic device, characterized in that, The method includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement the method as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that, The computer storage medium stores a computer program that enables the computer to perform the method as described in any one of claims 1-5.

Images