Time pressure identification method and device

Abstract

The invention discloses a time pressure identification method and device, relates to the technical field of big data processing, and provides a solution for effectively identifying time pressure. According to the main technical scheme, the method comprises the steps of obtaining a to-be-read target text; a reading area and an operation area are divided in the target text, the operation area comprises a plurality of interest areas obtained through division based on dimensions and options, and the interest areas are used for supporting a user to carry out corresponding operation behaviors after data information is obtained based on the reading area; in the process of reading and processing the target text, acquiring fixation point data falling into each interest area and reading track data among the interest areas by tracking eye movement; and according to the fixation point data and the reading track data in the operation area, identifying the time pressure of the user when the user reads and processes the target text.

Description

Technical Field

[0001] The present application relates to the technical field of big data processing, and in particular to a time pressure identification method and device. Background Art

[0002] Time pressure is the time limit imposed on individuals to complete tasks. When individuals perceive this time limit, they will feel a sense of pressure. This pressure will manifest itself in the following ways: for the same judicial document, if the time pressure is greater, people will speed up their browsing speed, skip some minor elements for information screening, and prefer to use heuristic-based information search strategies.

[0003] However, since time pressure is an emotional experience after all, and emotions are difficult to express concretely, how to identify the degree of time pressure users are under during the reading process urgently requires an effective solution. Summary of the invention

[0004] In view of this, the present application provides a time pressure identification method and device, which uses comprehensive gaze point data and reading trajectory data on the target text to identify the time pressure that the user has when reading and processing the target text, thereby converting the subjective emotional state of reading pressure into data for measurement, providing a solution for effectively identifying time pressure.

[0005] In order to achieve the above objectives, this application mainly provides the following technical solutions:

[0006] In a first aspect, the present application provides a time pressure identification method, the method comprising:

[0007] Obtain the target text to be read and processed;

[0008] A reading area and an operation area are divided in the target text, wherein the operation area includes a plurality of interest areas divided based on dimensions and options, and the interest areas are used to support the user to perform corresponding operation behaviors based on the data information obtained from the reading area;

[0009] In the process of reading and processing the target text, obtaining gaze point data falling within each of the interest areas and reading trajectory data between each of the interest areas by tracking eye movements;

[0010] The time pressure of the user when reading the target text is identified based on the gaze point data and the reading trajectory data in the operation area.

[0011] In some modified implementations of the first aspect of the present application, the tracking of eye movements to obtain gaze point data falling within each of the interest areas and reading trajectory data between the interest areas includes:

[0012] By tracking the position and dwell time of the sight corresponding to the eye movement projected on the target text, the fixation point falling within each of the interest areas and the fixation duration corresponding to the fixation point are determined to form fixation point data falling within each of the interest areas;

[0013] Among the plurality of gaze points in the interest area, according to the time sequence of formation of the gaze points, trajectory data is formed based on any two adjacent gaze points to obtain a plurality of trajectory data;

[0014] Filter out first eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same dimension from the plurality of trajectory data, and filter out second eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same option;

[0015] Reading trajectory data between the respective interest areas are composed according to the first eye movement trajectory data and the second eye movement trajectory data.

[0016] In some modified implementations of the first aspect of the present application, the step of selecting first eye movement trajectory data that meets the requirements for performing a cross-interest area reading search on the same dimension from the plurality of trajectory data, and selecting second eye movement trajectory data that meets the requirements for performing a cross-interest area reading search on the same option, comprises:

[0017] For any target trajectory data selected from the plurality of trajectory data, determining two target fixation points included in the target trajectory data;

[0018] Determine a first target interest area and a second target interest area where the two target gaze points respectively fall;

[0019] If the first target interest area and the second target interest area are different and are in the same dimension, determining that the target trajectory data is consistent with the first eye movement trajectory data;

[0020] If the first target interest area and the second target interest area are different and are on the same option, then the target trajectory data is determined to be consistent with the first eye movement trajectory data.

[0021] In some modified implementations of the first aspect of the present application, identifying the time pressure of the user when reading and processing the target text according to the gaze point data and the reading trajectory data in the operation area includes:

[0022] According to the gaze points falling into each of the interest areas, counting the number of gaze points in the operation area;

[0023] Calculating an average fixation time of the fixation points in the operation area according to the number of fixation points and the fixation time of each fixation point in the interest area;

[0024] Determining, according to the first eye movement trajectory data and the second eye movement trajectory data, a reading search strategy executed when reading and processing the target text, wherein the reading search strategy is used to represent a search strategy obtained by switching based on dimensions and switching based on options when performing a cross-interest area reading search;

[0025] By comparing the number of fixation points and the average fixation duration with the preset normative average value, and then integrating the reading search strategy, the time pressure of the user when reading and processing the target text is identified.

[0026] In some modified implementations of the first aspect of the present application, determining a reading search strategy to be executed when reading and processing the target text according to the first eye movement trajectory data and the second eye movement trajectory data includes:

[0027] According to the first eye movement trajectory data, counting the frequency of first eye saccades performed when performing reading search on the same dimension;

[0028] According to the second eye movement trajectory data, counting the frequency of the second eye saccade performed when performing reading search on the same option;

[0029] Using a preset reading search strategy formula to process the first eye saccade frequency, the second eye saccade frequency, the number of dimensions and the number of options, an evaluation index value is obtained, and the evaluation index value is used to characterize the tendency of switching between dimensions or options when performing a cross-interest area reading search;

[0030] If the evaluation index value is greater than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on options is adopted more than switching on dimensions;

[0031] If the evaluation index value is less than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on dimensions is adopted more than switching on options.

[0032] In some modified implementation modes of the first aspect of the present application, the dividing of the target text into a reading area and an operation area includes:

[0033] Convert the target text into a corresponding picture;

[0034] By identifying content information in the picture, an area in the picture that requires user participation in operation is used as an operation area;

[0035] Using other areas of the image except the operation area as a reading area;

[0036] The operation area is divided into a plurality of interest areas according to a plurality of preset dimensions and a plurality of preset options on the preset dimensions.

[0037] In some modified implementation manners of the first aspect of the present application, the operation area is divided into a plurality of interest areas according to a plurality of preset dimensions and a plurality of preset options on the preset dimensions, including:

[0038] Determining a target number of interest areas into which the operating area is divided according to a product of the number of the preset dimensions and the number of the preset options;

[0039] Based on the number of targets, the operation area is equally divided to obtain the interest area.

[0040] A second aspect of the present application provides a time pressure identification device, the device comprising:

[0041] A first acquisition unit, used to acquire a target text to be read and processed;

[0042] A division unit, used to divide the target text into a reading area and an operation area, wherein the operation area includes a plurality of interest areas divided based on dimensions and options, and the interest areas are used to support the user to perform corresponding operation behaviors after obtaining data information based on the reading area;

[0043] A second acquisition unit is used to acquire gaze point data falling within each of the interest areas and reading trajectory data between each of the interest areas by tracking eye movements during the process of reading and processing the target text;

[0044] The recognition unit is used to recognize the time pressure of the user when reading and processing the target text according to the gaze point data and the reading trajectory data in the operation area.

[0045] In some modified implementation modes of the second aspect of the present application, the second acquisition unit includes:

[0046] A first determination module is used to determine the gaze points falling within each of the interest areas and the gaze duration corresponding to the gaze points by tracking the position and the dwell time of the gaze corresponding to the eye movement projected on the target text, so as to form the gaze point data falling within each of the interest areas;

[0047] A second determination module, among the plurality of gaze points in the interest area, forms trajectory data based on any two adjacent gaze points in a time sequence of the gaze points, to obtain a plurality of trajectory data;

[0048] A screening module, used to screen out first eye movement track data that is suitable for performing a cross-interest area reading search on the same dimension from the plurality of track data, and screen out second eye movement track data that is suitable for performing a cross-interest area reading search on the same option;

[0049] A composition module is used to compose reading trajectory data between each of the interest areas according to the first eye movement trajectory data and the second eye movement trajectory data.

[0050] In some modified implementations of the second aspect of the present application, the screening module is further specifically used for:

[0051] For any target trajectory data selected from the plurality of trajectory data, determining two target fixation points included in the target trajectory data;

[0052] Determine a first target interest area and a second target interest area where the two target gaze points respectively fall;

[0053] If the first target interest area and the second target interest area are different and are in the same dimension, determining that the target trajectory data is consistent with the first eye movement trajectory data;

[0054] If the first target interest area and the second target interest area are different and are on the same option, then the target trajectory data is determined to be consistent with the first eye movement trajectory data.

[0055] In some modified implementation modes of the second aspect of the present application, the identification unit includes:

[0056] A statistics module, used for counting the number of gaze points in the operation area according to the gaze points falling into each of the interest areas;

[0057] A calculation module, used for calculating an average fixation time of the fixation points in the operation area according to the number of fixation points and the fixation time of the fixation points in each of the interest areas;

[0058] A third determination module is used to determine a reading search strategy executed when reading and processing the target text according to the first eye movement trajectory data and the second eye movement trajectory data, wherein the reading search strategy is used to represent a search strategy obtained by switching based on dimensions and switching based on options when performing a cross-interest area reading search;

[0059] The identification module is used to identify the time pressure of the user when reading and processing the target text by comparing the number of fixation points and the average fixation duration with the preset norm average value and then integrating the reading search strategy.

[0060] In some modified implementation modes of the second aspect of the present application, the third determination module is further specifically configured to:

[0061] According to the first eye movement trajectory data, counting the frequency of first eye saccades performed when performing reading search on the same dimension;

[0062] According to the second eye movement trajectory data, counting the frequency of the second eye saccade performed when performing reading search on the same option;

[0063] Using a preset reading search strategy formula to process the first eye saccade frequency, the second eye saccade frequency, the number of dimensions and the number of options, an evaluation index value is obtained, and the evaluation index value is used to characterize the tendency of switching between dimensions or options when performing a cross-interest area reading search;

[0064] If the evaluation index value is greater than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on options is adopted more than switching on dimensions;

[0065] If the evaluation index value is less than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on dimensions is adopted more than switching on options.

[0066] In some modified implementation modes of the second aspect of the present application, the division unit includes:

[0067] A conversion module, used for converting the target text into a corresponding image;

[0068] A fourth determination module is used to identify content information in the picture and to select an area in the picture that requires user participation in the operation as an operation area;

[0069] The fourth determination module is further configured to use other areas of the image except the operation area as a reading area;

[0070] The division module is used to divide the operation area into multiple interest areas according to multiple preset dimensions and multiple preset options on the preset dimensions.

[0071] In some modified implementation modes of the second aspect of the present application, the division module is further specifically used for:

[0072] Determining a target number of the interest areas into which the operating area is divided according to a product of the number of the preset dimensions and the number of the preset options;

[0073] Based on the number of targets, the operation area is equally divided to obtain the interest area.

[0074] A third aspect of the present application provides a storage medium, which includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the time pressure identification method as described above.

[0075] A fourth aspect of the present application provides an electronic device, the device comprising at least one processor, and at least one memory and a bus connected to the processor;

[0076] Wherein, the processor and the memory communicate with each other through the bus;

[0077] The processor is used to call the program instructions in the memory to execute the time pressure identification method as described above.

[0078] By means of the above technical solution, the technical solution provided by this application has at least the following advantages:

[0079] The present application provides a method and device for identifying time pressure. For the target text to be read and processed, the present application first divides it into a reading area and an operation area, and the operation area is divided into multiple interest areas based on dimensions and options. Since the interest area can be used to support the user to perform corresponding operation behaviors after obtaining data information based on the reading area, the operation area can more concentratedly represent the time pressure generated by the user when reading and processing the target text; then the present application tracks eye movements to obtain the gaze point data falling into each interest area and the reading trajectory data between the interest areas, thereby combining the gaze point data and the reading trajectory data to identify the time pressure that the user has when reading and processing the target text. Compared with the existing problem that time pressure is a stressful emotion that is difficult to express concretely, the present application converts the subjective emotional state of reading pressure into data for measurement, providing a solution for effectively identifying time pressure.

[0080] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0082] Figure 1 A flow chart of a time pressure identification method provided in an embodiment of the present application;

[0083] Figure 2 The reading and processing text of the judicial document cited in the embodiment of the present application;

[0084] Figure 3 A flow chart of another time pressure identification method provided in an embodiment of the present application;

[0085] Figure 4 A schematic diagram illustrating a cross-area-of-interest reading search operation on the same dimension and a cross-area-of-interest reading search operation on the same option for an embodiment of the present application;

[0086] Figure 5 A block diagram of a time pressure recognition device provided in an embodiment of the present application;

[0087] Figure 6 A block diagram of another time pressure identification device provided in an embodiment of the present application;

[0088] Figure 7 An electronic device for identifying time pressure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0089] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0090] Now, during the reading process, when individuals perceive this time limit, they will experience a sense of stress, namely time pressure, which is a subjective emotional state that is difficult to express clearly and concretely.

[0091] However, after in-depth research, the inventors found that, for example, for the same judicial document, if the time pressure is greater, people will skip some minor elements to achieve information screening, so the gaze points on the target text that track the eye movements will also decrease. In particular, when encountering a choice position that can be distinguished based on dimensions and options, the line of sight will directly ignore some simple choice positions and make decisions directly, so the reading trajectory will also change. Therefore, the gaze point data and reading trajectory data in the target text can be combined to indirectly use the data to measure, which can effectively identify whether the user is under great or small time pressure.

[0092] Accordingly, the present application provides a time pressure identification method, such as Figure 1 , the present application embodiment provides the following specific steps:

[0093] 101. Obtain a target text to be read and processed.

[0094] 102. A reading area and an operation area are divided in the target text. The operation area includes a plurality of interest areas divided based on dimensions and options. The interest areas are used to support users to perform corresponding operation behaviors based on the data information obtained in the reading area.

[0095] The reading area is an area in the target text that provides basic content information. After the relevant content information is obtained from the reading area, the operation area is an area that provides users with input, circle selection and other operations.

[0096] like Figure 2 The example of the reading and processing text of the judgment document is "a divorce dispute case material in which the plaintiff suspected that the defendant had cheated on her. In the case material, both the plaintiff and the defendant agreed to divorce, there was no property dispute, and the only dispute between the two parties was the allocation of child custody. In addition, the plaintiff claimed that the defendant had cheated on her and provided vague evidence, and the defendant denied the cheating." Figure 2 The "Case Summary" section on the left is the "Reading Area", which provides information about the case; the "Comparison of the Advantages and Disadvantages of the Plaintiff and the Defendant" section on the right is the operation area, which is displayed in a table in the operation area, providing 9 dimensions of "wide interests", "plenty of time to take care of children", "humorous and interesting", "emotionally stable", "school district housing", "high salary", "love for children", "stable job", and "care for children during marriage" and the two options of "plaintiff" and "defendant". Based on the dimensions and options, the embodiment of the present application obtains 18 interest areas, each of which is a combination of a dimension and an option.

[0097] 103. In the process of reading and processing the target text, the gaze point data falling into each area of ​​interest and the reading trajectory data between each area of ​​interest are obtained by tracking eye movements.

[0098] The embodiment of the present application uses an eye tracker to track eye movements to obtain the gaze points of the user when reading and processing the target text and the reading trajectory obtained based on the connection of these gaze points.

[0099] The fixation point data includes the number of fixation points and the fixation duration of each fixation point. In the application scenario of eye tracker tracking eye movement data, a saccade is an eye movement with a speed exceeding 30° / s and an acceleration exceeding 8000° / s, and a fixation point is a period of time between two saccades when the eye position is relatively stable, for example, generally greater than or equal to 60ms.

[0100] The reading trajectory data includes: trajectory data formed based on two gaze points that form a line of sight and cross the interest area.

[0101] It should be noted that since the reading area is equivalent to providing descriptive information and the operation area is equivalent to making decisions based on this descriptive information, the operation area requires more analysis and thinking. Therefore, the time pressure in the process of reading and processing the entire target text is concentrated in the operation area. Then, by analyzing the time pressure generated in the operation area, the time pressure of the user in reading and processing the entire target text can be identified.

[0102] Therefore, the embodiment of the present application mainly tracks eye movements to obtain gaze point data falling within each area of ​​interest and reading trajectory data between each area of ​​interest, which is used to evaluate the time pressure in the operation area.

[0103] 104. According to the gaze point data and the reading trajectory data in the operation area, the time pressure of the user when reading the target text is identified.

[0104] As for the fixation point data, its impact on the evaluation of time pressure is: since it includes the number of fixation points and the fixation duration of each fixation point, the more fixation points and the longer the fixation duration, the slower the user's reading speed, which further indicates that the user has less time pressure; conversely, the fewer fixation points and the shorter the fixation duration, the faster the user's reading speed, which further indicates that the user has greater time pressure.

[0105] As for the reading trajectory data, its impact on the evaluation of time pressure is: since it is mainly based on trajectory data formed by two gaze points that form a line of sight and cross the interest area, the faster the target text is read across different interest areas, the greater the user's time pressure is. Conversely, the slower the target text is read, the less time pressure the user has.

[0106] For example, Figure 2 As shown, if the user's reading trajectory in the operation area is: switching on dimensions more than switching on options, if the user's line of sight is projected to "broad interests" under "plaintiff" and then to "enough time to take care of children", that is, the answer is directly given as "√" based on the two interest areas across the dimensions, and the line of sight is not projected to the option position under "defendant", thereby completing the answers to these two dimensions more quickly.

[0107] Thus, by analogy with reading processing such as Figure 2 Among the 18 interest areas shown, if the line of sight switches more on dimensions than on options, it means that the user quickly reads and processes the 9 dimensions and answers them. The faster the reading process, the greater the time pressure on the user.

[0108] Accordingly, based on the fact that both gaze point data and reading trajectory data will have an impact on the evaluation of time pressure, the embodiment of the present application combines these two aspects to form a variety of evaluation indicators, which are not specifically limited here, thereby providing a more effective way to identify the time pressure that users have when reading and processing the target text.

[0109] As described above, the embodiment of the present application provides a method for identifying time pressure. Compared with the existing problem that time pressure is a stressful emotion that is difficult to express concretely, the embodiment of the present application converts the subjective emotional state of reading pressure into data for measurement, providing a solution for effectively identifying time pressure.

[0110] In order to explain the above embodiment in more detail, the present application embodiment also provides another time pressure identification method, such as Figure 3 As shown, the present application embodiment provides the following specific steps:

[0111] 201. Obtain a target text to be read and processed.

[0112] 202. A reading area and an operation area are divided in the target text, wherein the operation area includes a plurality of interest areas divided based on dimensions and options, and the interest areas are used to support the user to perform corresponding operation behaviors based on the data information obtained from the reading area.

[0113] This step can be further refined to include: first, converting the target text into a corresponding picture; second, identifying the content information in the picture and defining the area in the picture that requires user participation as the operation area; defining the other areas in the picture except the operation area as the reading area; and third, dividing the operation area into multiple interest areas according to multiple preset dimensions and multiple preset options on the preset dimensions.

[0114] The embodiment of the present application first converts the target text into an image and then performs a reading process, which is not only convenient for circling text and marking it into an area, but also more convenient for further dividing it into small areas, and convenient for tracking the line of sight of eye movements to obtain the gaze point position.

[0115] Furthermore, with respect to dividing the operating area into multiple interest areas, an embodiment of the present application determines the target number of interest areas for dividing the operating area according to the product of the number of preset dimensions and the number of preset options, and based on the target number, divides the operating area equally to obtain multiple interest areas.

[0116] For example, Figure 2 As shown, since the number of dimensions is "9" and the number of options is "2", "18" interest areas are obtained.

[0117] 203. By tracking the position and dwell time of the sight corresponding to the eye movement projected on the target text, the fixation points falling into each interest area and the fixation duration corresponding to the fixation points are determined to form the fixation point data falling into each interest area.

[0118] In the process of reading and processing the target text, the embodiment of the present application can use an eye tracker to track eye movements to obtain eye movement data, and then export the eye movement data for subsequent analysis, such as determining the gaze points falling into each interest area and the gaze duration corresponding to the gaze points based on the position and dwell time of the tracked eye movements corresponding to the line of sight projected on the target text.

[0119] 204. Among the gaze points in the multiple interest areas, according to the time sequence of the formation of the gaze points, trajectory data is formed based on any two adjacent gaze points to obtain multiple trajectory data.

[0120] For example, Figure 2 For example, a trajectory data is as follows: the user's sight is projected to "broad interests" under "plaintiff" and then to "enough time to take care of children", thus forming a reading trajectory based on the two gaze points obtained from the two projections.

[0121] 205. Filter out first eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same dimension from the multiple trajectory data, and filter out second eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same option.

[0122] This step can be further refined to include the following:

[0123] First, for any target trajectory data selected from multiple trajectory data, two target fixation points contained in the target trajectory data are determined; and the first target interest area and the second target interest area where the two target fixation points fall respectively are determined. Secondly, a judgment is made: if the first target interest area and the second target interest area are different and are on the same dimension, the target trajectory data is determined to be consistent with the first eye movement trajectory data; if the first target interest area and the second target interest area are different and are on the same option, the target trajectory data is determined to be consistent with the first eye movement trajectory data.

[0124] It should be noted that in order to distinguish the target interest areas where two adjacent target gaze points fall, the embodiment of the present application uses the words "first" and "second" for identification, and before any judgment is made, it is not denied that the "first target interest area" and the "second target interest area" may be the same, that is, the two target gaze points fall into the same target interest area.

[0125] For example, Figure 4 As shown, the embodiment of the present application exemplifies a schematic diagram of performing a cross-interest area reading search operation on the same dimension and performing a cross-interest area reading search operation on the same option. Figure 4 In the example, options A and B, dimensions 1 and 2 are listed, and "a", "b", "c" and "d" are used to refer to the four interest areas respectively.

[0126] If the nth fixation point is located in area a and the n+1th fixation point is located in area b, then it is regarded as a cross-area reading search operation on the same dimension, that is, switching between options.

[0127] If the nth fixation point is located in area a and the n+1th fixation point is located in area c, then it is regarded as a cross-interest area reading search operation on the same option, that is, switching between dimensions.

[0128] 206. Composing reading trajectory data between each interest area according to the first eye movement trajectory data and the second eye movement trajectory data.

[0129] 207. According to the fixation points falling into each area of ​​interest, the number of fixation points in the operation area is counted.

[0130] 208. Calculate the average fixation duration of the fixation points in the operation area according to the number of fixation points and the fixation duration of the fixation points in each area of ​​interest.

[0131] In the embodiment of the present application, steps 207-208 are to count the number of gaze points contained in the operation area and calculate the average gaze duration.

[0132] 209. Determine a reading search strategy to be executed when reading and processing a target text based on the first eye movement trajectory data and the second eye movement trajectory data, wherein the reading search strategy is used to characterize a search strategy obtained based on switching on dimensions and switching on options when performing a reading search across interest areas.

[0133] This step can be further broken down into the following:

[0134] First, according to the first eye movement trajectory data, the frequency of the first eye saccade performed when reading search is performed on the same dimension is counted; according to the second eye movement trajectory data, the frequency of the second eye saccade performed when reading search is performed on the same option is counted.

[0135] Secondly, the preset reading search strategy formula is used to process the first saccade frequency, the second saccade frequency, the number of dimensions and the number of options to obtain an evaluation index value. The evaluation index value is used to characterize the tendency of evaluating the reading search strategy when conducting cross-interest area reading search on the target text.

[0136] Specifically, there are two situations:

[0137] In one case, if the evaluation index value is greater than the preset threshold, it is determined that when conducting a cross-interest area reading search on the target text, switching on options is more often used than switching on dimensions; in another case, if the evaluation index value is less than the preset threshold, it is determined that when conducting a cross-interest area reading search on the target text, switching on dimensions is more often used than switching on options.

[0138] For example, the present application embodiment provides a preset reading search strategy formula, as shown in the following formula (1):

[0139]

[0140] Where A and D represent the number of options and dimensions respectively (A=2, D=9); a and r d represents the frequency of alternative-based and dimension-based saccades, respectively, and N represents the total frequency of saccades. And the SM value is used to characterize the tendency of switching between alternative-based and dimension-based reading search schemes.

[0141] And the preset threshold value is "0". If the SM value is greater than "0", in the process of reading search across interest areas, the evaluation of switching on options is more than switching on dimensions; if the SM value is less than "0", in the process of reading search across interest areas, the evaluation of switching on options is less than switching on dimensions.

[0142] 210. By comparing the number of fixations and the average fixation duration with the preset normative averages and then integrating the reading search strategy, the time pressure of the user when reading and processing the target text can be identified.

[0143] The norm is a standard quantity for comparison. The embodiment of the present application collects a large amount of sample data obtained when a user group reads and processes the target text, such as Figure 2 For this target sample, the embodiment of the present application can collect the average value of the number of fixations and the average fixation duration obtained by a large number of judges reading and processing such a target text, as the normative average value, which is used as reference data representing the time pressure when it is moderate.

[0144] Then, by combining the number of fixations, average fixation duration, and SM value, we can obtain the following results for identifying time pressure, for example:

[0145] If the number of user fixations and the average fixation duration are lower than the normative average, and the SM value is less than 0, the user is under great time pressure.

[0146] If the number of user fixations and the average fixation duration are higher than the normative average, and the SM value is greater than 0, the user has less time pressure.

[0147] Furthermore, as a response to the above Figure 1 , Figure 3 The embodiment of the present application provides a device for identifying time pressure. The device embodiment corresponds to the aforementioned method embodiment. For ease of reading, the device embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. The device is used to convert the subjective emotional state of reading pressure into data for measurement, specifically, Figure 5 As shown, the device comprises:

[0148] A first acquisition unit 31 is used to acquire a target text to be read and processed;

[0149] A dividing unit 32 is used to divide the target text into a reading area and an operation area, wherein the operation area includes a plurality of interest areas divided based on dimensions and options, and the interest areas are used to support the user to perform corresponding operation behaviors based on the data information obtained from the reading area;

[0150] A second acquisition unit 33 is used to acquire gaze point data falling within each of the interest areas and reading trajectory data between each of the interest areas by tracking eye movements during the process of reading and processing the target text;

[0151] The identification unit 34 is used to identify the time pressure of the user when reading and processing the target text according to the gaze point data and the reading trajectory data in the operation area.

[0152] Further, such as Figure 6 As shown, the second acquisition unit 33 includes:

[0153] The first determination module 331 is used to determine the gaze points falling into each of the interest areas and the gaze duration corresponding to the gaze points by tracking the position and the dwell time of the gaze corresponding to the eye movement projected onto the target text, so as to form the gaze point data falling into each of the interest areas;

[0154] A second determining module 332, among the plurality of gaze points in the interest area, forms trajectory data based on any two adjacent gaze points according to the time sequence of the gaze points, to obtain a plurality of trajectory data;

[0155] A screening module 333 is used to screen out first eye movement track data that is suitable for performing a cross-interest area reading search on the same dimension from the plurality of track data, and screen out second eye movement track data that is suitable for performing a cross-interest area reading search on the same option;

[0156] The composition module 334 is used to compose the reading trajectory data between the respective interest areas according to the first eye movement trajectory data and the second eye movement trajectory data.

[0157] Further, such as Figure 6 As shown, the screening module 333 is further specifically used for:

[0158] For any target trajectory data selected from the plurality of trajectory data, determining two target fixation points included in the target trajectory data;

[0159] Determine a first target interest area and a second target interest area where the two target gaze points respectively fall;

[0160] If the first target interest area and the second target interest area are different and are in the same dimension, determining that the target trajectory data is consistent with the first eye movement trajectory data;

[0161] If the first target interest area and the second target interest area are different and are on the same option, then the target trajectory data is determined to be consistent with the first eye movement trajectory data.

[0162] Further, such as Figure 6 As shown, the identification unit 34 includes:

[0163] A counting module 341 is used to count the number of gaze points in the operation area according to the gaze points falling into each of the interest areas;

[0164] A calculation module 342, configured to calculate an average fixation time of fixations in the operation area according to the number of fixations and fixation time of fixations in each of the interest areas;

[0165] A third determination module 343 is used to determine a reading search strategy to be performed when reading and processing the target text according to the first eye movement trajectory data and the second eye movement trajectory data, wherein the reading search strategy is used to represent a search strategy obtained by switching based on dimensions and switching based on options when performing a cross-interest area reading search;

[0166] The identification module 344 is used to identify the time pressure of the user when reading and processing the target text by comparing the number of fixation points and the average fixation duration with the preset norm average value and then integrating the reading search strategy.

[0167] Further, such as Figure 6 As shown, the third determination module 343 is further specifically used for:

[0168] According to the first eye movement trajectory data, counting the frequency of first eye saccades performed when performing reading search on the same dimension;

[0169] According to the second eye movement trajectory data, counting the frequency of the second eye saccade performed when performing reading search on the same option;

[0170] Using a preset reading search strategy formula to process the first eye saccade frequency, the second eye saccade frequency, the number of dimensions and the number of options, an evaluation index value is obtained, and the evaluation index value is used to characterize the tendency of switching between dimensions or options when performing a cross-interest area reading search;

[0171] If the evaluation index value is greater than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on options is adopted more than switching on dimensions;

[0172] If the evaluation index value is less than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on dimensions is adopted more than switching on options.

[0173] Further, such as Figure 6 As shown, the division unit 32 includes:

[0174] A conversion module 321, used for converting the target text into a corresponding image;

[0175] A fourth determining module 322 is used to identify content information in the picture and to select an area in the picture that requires user participation in the operation as an operation area;

[0176] The fourth determining module 322 is further configured to use other areas of the image except the operating area as a reading area;

[0177] The division module 323 is used to divide the operation area into multiple interest areas according to multiple preset dimensions and multiple preset options on the preset dimensions.

[0178] Further, such as Figure 6 As shown, the division module 323 is also specifically used for:

[0179] Determining a target number of the interest areas into which the operating area is divided according to a product of the number of the preset dimensions and the number of the preset options;

[0180] Based on the number of targets, the operation area is equally divided to obtain the interest area.

[0181] In summary, the embodiments of the present application provide a method and device for identifying time pressure, which uses comprehensive gaze point data and reading trajectory data on the target text to identify the time pressure that the user has when reading and processing the target text, thereby converting the subjective emotional state of reading pressure into data for measurement, providing a solution for effectively identifying time pressure.

[0182] The time pressure identification device includes a processor and a memory. The first acquisition unit, the division unit, the second acquisition unit and the identification unit are all stored in the memory as program units. The processor executes the program units stored in the memory to implement corresponding functions.

[0183] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to convert the subjective emotional state of reading pressure into data for measurement, providing a solution for effectively identifying time pressure.

[0184] An embodiment of the present application provides a storage medium on which a program is stored. When the program is executed by a processor, the time pressure identification method is implemented.

[0185] An embodiment of the present application provides a processor, which is used to run a program, wherein the time pressure identification method is executed when the program is running.

[0186] The present application embodiment provides an electronic device 4, such as Figure 7 As shown, the device includes at least one processor 41, and at least one memory 42 and a bus 43 connected to the processor 41; wherein the processor 41 and the memory 42 communicate with each other through the bus 43; the processor 41 is used to call the program instructions in the memory 42 to execute the above-mentioned time pressure identification method.

[0187] The device in this article can be a server, PC, etc.

[0188] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing the steps of the time pressure identification method.

[0189] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0190] In a typical configuration, the device includes one or more processors (CPU), memory and bus. The device may also include input / output interface, network interface and the like.

[0191] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

[0192] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0193] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0194] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0195] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A time pressure identification method, characterized in that: The method comprises: Obtain the target text to be read and processed; A reading area and an operation area are divided in the target text, wherein the operation area includes a plurality of interest areas divided based on dimensions and options, and the interest areas are used to support the user to perform corresponding operation behaviors based on the data information obtained from the reading area; In the process of reading and processing the target text, obtaining gaze point data falling within each of the interest areas and reading trajectory data between each of the interest areas by tracking eye movements; The time pressure of the user when reading the target text is identified based on the gaze point data and the reading trajectory data in the operation area.

2. The method according to claim 1, characterized in that The step of tracking eye movements to obtain gaze point data falling within each of the interest areas and reading trajectory data between the interest areas includes: By tracking the position and dwell time of the sight corresponding to the eye movement projected on the target text, the fixation point falling within each of the interest areas and the fixation duration corresponding to the fixation point are determined to form fixation point data falling within each of the interest areas; Among the plurality of gaze points in the interest area, according to the time sequence of formation of the gaze points, trajectory data is formed based on any two adjacent gaze points to obtain a plurality of trajectory data; Filter out first eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same dimension from the plurality of trajectory data, and filter out second eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same option; Reading trajectory data between the respective interest areas are composed according to the first eye movement trajectory data and the second eye movement trajectory data.

3. The method according to claim 2, characterized in that The step of selecting first eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same dimension from the plurality of trajectory data, and selecting second eye movement trajectory data that is suitable for performing a cross-interest area reading search on the same option, comprises: For any target trajectory data selected from the plurality of trajectory data, determining two target fixation points included in the target trajectory data; Determine a first target interest area and a second target interest area where the two target gaze points respectively fall; If the first target interest area and the second target interest area are different and are in the same dimension, determining that the target trajectory data is consistent with the first eye movement trajectory data; If the first target interest area and the second target interest area are different and are on the same option, then the target trajectory data is determined to be consistent with the first eye movement trajectory data.

4. The method according to claim 2, characterized in that: The step of identifying the time pressure of the user when reading the target text according to the gaze point data and the reading trajectory data in the operation area includes: According to the gaze points falling into each of the interest areas, counting the number of gaze points in the operation area; Calculating an average fixation time of the fixation points in the operation area according to the number of fixation points and the fixation time of each fixation point in the interest area; Determining, according to the first eye movement trajectory data and the second eye movement trajectory data, a reading search strategy executed when reading and processing the target text, wherein the reading search strategy is used to represent a search strategy obtained by switching based on dimensions and switching based on options when performing a cross-interest area reading search; By comparing the number of fixation points and the average fixation duration with the preset normative average value, and then integrating the reading search strategy, the time pressure of the user when reading and processing the target text is identified.

5. The method according to claim 4, characterized in that The step of determining a reading search strategy to be executed when reading and processing the target text according to the first eye movement trajectory data and the second eye movement trajectory data includes: According to the first eye movement trajectory data, counting the frequency of first eye saccades performed when performing reading search on the same dimension; According to the second eye movement trajectory data, counting the frequency of the second eye saccade performed when performing reading search on the same option; Using a preset reading search strategy formula to process the first eye saccade frequency, the second eye saccade frequency, the number of dimensions and the number of options, an evaluation index value is obtained, and the evaluation index value is used to characterize the tendency of switching between dimensions or options when performing a cross-interest area reading search; If the evaluation index value is greater than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on options is adopted more than switching on dimensions; If the evaluation index value is less than a preset threshold, it is determined that when performing a cross-interest area reading search on the target text, switching on dimensions is adopted more than switching on options.

6. The method according to any one of claims 1 to 5, characterized in that The step of dividing the target text into a reading area and an operation area includes: Convert the target text into a corresponding picture; By identifying content information in the picture, an area in the picture that requires user participation in operation is used as an operation area; Using other areas of the image except the operation area as a reading area; The operation area is divided into a plurality of interest areas according to a plurality of preset dimensions and a plurality of preset options on the preset dimensions.

7. The method according to claim 6, characterized in that The step of dividing the operation area into a plurality of interest areas according to a plurality of preset dimensions and a plurality of preset options on the preset dimensions comprises: Determining a target number of the interest areas into which the operating area is divided according to a product of the number of the preset dimensions and the number of the preset options; Based on the number of targets, the operation area is equally divided to obtain the interest area.

8. A time pressure recognition device, characterized in that: The device comprises: A first acquisition unit, used to acquire a target text to be read and processed; A division unit, used to divide the target text into a reading area and an operation area, wherein the operation area includes a plurality of interest areas divided based on dimensions and options, and the interest areas are used to support the user to perform corresponding operation behaviors after obtaining data information based on the reading area; A second acquisition unit is used to acquire gaze point data falling within each of the interest areas and reading trajectory data between each of the interest areas by tracking eye movements during the process of reading and processing the target text; The recognition unit is used to recognize the time pressure of the user when reading and processing the target text according to the gaze point data and the reading trajectory data in the operation area.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the time pressure identification method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The device includes at least one processor, and at least one memory and a bus connected to the processor; Wherein, the processor and the memory communicate with each other through the bus; The processor is used to call the program instructions in the memory to execute the time pressure identification method according to any one of claims 1-7.

Images